Prediction device, communication control device, and prediction method
The prediction device classifies and predicts communication traffic flows in parallel to determine necessary route switching, addressing the challenge of accurate future traffic volume prediction and reducing communication delays in systems with multiple QoS flows, thereby ensuring efficient communication.
Patent Information
- Application Number
- PCT/JP2023/018384
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-17
- Publication Date
- 2024-11-21
AI Technical Summary
Conventional communication systems face challenges in predicting future traffic volume accurately across multiple flows, leading to increased calculation load, delayed route switching, and potential communication delays, especially when multiple Quality of Service (QoS) flows coexist.
A prediction device and method that classify communication traffic into flows, perform parallel traffic volume predictions for each flow, and calculate total traffic to determine necessary route switching, allowing for timely congestion prevention and reduced delays.
The solution effectively suppresses congestion and reduces communication delays while maintaining communication quality, even in environments with multiple coexisting flows, by completing the prediction process before congestion occurs and optimizing route switching.
Smart Images

Figure JP2023018384_21112024_PF_FP_ABST
Abstract
Description
Prediction device, communication control device, and prediction method
[0001] The present invention relates to a prediction device, a communication control device, and a prediction method.
[0002] When multiple communication devices communicate simultaneously, such as when multiple upper devices and multiple lower devices communicate with each other, congestion may occur, resulting in communication delays. Congestion may be resolved by switching the communication path (hereinafter referred to as "path switching") using a switching device installed on the communication path, thereby changing the connection relationship between the upper device and the lower device. If communication traffic (hereinafter simply referred to as "traffic") concentrated on a specific communication device (e.g., an upper device) can be distributed to multiple communication devices by path switching, congestion can be resolved, and communication delays can be reduced.
[0003] Conventionally, in a communication system having a switching device that can change the connection relationship between a higher-level device and a lower-level device, there is a technology that collects information indicating the amount of traffic measured by the higher-level device and the lower-level device (hereinafter simply referred to as "traffic volume"), determines whether congestion has occurred at the offload destination based on the collected traffic volume, and performs route switching.
[0004] JP2014-060610A JP10-285276A
[0005] Y.Okamoto, et al., “Short-term traffic prediction based on mobile control information for proactive optical switching to lower congestion delay,” International Conference on Emerging Technologies for Communications (ICETC), 2022
[0006] Conventional communication systems calculate a congestion value indicating the degree of congestion based on the traffic volume of each communication path, and perform route switching when the congestion value of any communication path exceeds a threshold. However, route switching generally requires a certain amount of time. Therefore, in conventional communication systems, congestion occurs from the time congestion occurs until the route switching is completed. Therefore, the time required for route switching is also one of the factors that cause communication delays. For example, in the technologies described in Patent Documents 1 and 2, it takes time from collecting actual traffic volume to performing route switching, making it difficult to determine whether congestion has occurred in real time (e.g., within several milliseconds) and to perform route switching within a predetermined period of time (e.g., within several tens of milliseconds).
[0007] In response to this, a method can be considered in which, instead of switching routes based on actual measured values of traffic volume, future traffic volume is predicted and route switching is performed in advance based on the predicted value to avoid congestion. However, in an actual communication environment in which multiple traffic flows (hereinafter simply referred to as "flows") coexist, as in the case of communications with various QoS (Quality of Service) being performed between a large number of communication devices these days, there is a problem in that predicting the future traffic volumes of all flows collectively results in low prediction accuracy.
[0008] On the other hand, when future traffic volume is predicted for each flow, the computational load associated with the prediction increases in proportion to the number of flows, and the computation time required for the prediction increases, resulting in the problem that route switching cannot be completed before congestion actually occurs. Thus, with the conventional technology, even if a decision to perform route switching is made based on a predicted value of traffic volume, congestion cannot be prevented, resulting in communication delays.
[0009] In view of the above circumstances, the present invention aims to provide a prediction device, a communication control device, and a prediction method that can reduce communication delay while satisfying communication quality even when multiple flows are mixed.
[0010] One aspect of the present invention is a prediction device comprising: a flow classification unit that classifies communication traffic input during a predetermined period into a plurality of flows based on characteristics of the communication traffic; a parallel number calculation unit that calculates a parallel number, which is the maximum number of prediction processes that can be completed before the second period begins, when prediction processes that predict the traffic volume for a second period after the first period are performed in parallel for each flow based on the traffic volume for each flow during a first period and predetermined conditions; a traffic prediction unit that, if the number of flows classified by the flow classification unit is greater than the parallel number, performs the prediction process on a number of flows that is within the parallel number; and a total traffic calculation unit that calculates the total traffic volume for the second period based on the results of the prediction process by the traffic prediction unit.
[0011] One aspect of the present invention is a communication control device comprising: a flow classification unit that classifies communication traffic input during a predetermined period based on characteristics of the communication traffic to form a plurality of flows; a parallel number calculation unit that calculates a parallel number, which is the maximum number of prediction processes that can be completed before the second period begins, when a prediction process that predicts the traffic volume for a second period after the first period is performed in parallel for each flow based on the traffic volume for each flow during a first period and predetermined conditions; a traffic prediction unit that, if the number of the flows classified by the flow classification unit is greater than the parallel number, performs the prediction process for a number of the flows within the parallel number; a total traffic calculation unit that calculates a total of the traffic volume for the second period based on the result of the prediction process by the traffic prediction unit; a switching determination unit that predicts whether congestion will occur during the second period based on the total traffic volume and determines whether a communication path needs to be switched based on the prediction result; and a switching instruction unit that, when the switching determination unit determines that a communication path needs to be switched, issues a switching instruction to a switching device that performs the communication path switching.
[0012] Another aspect of the present invention is a prediction method executed by a computer, the prediction method comprising: a flow classification step of classifying communication traffic input during a predetermined period into a plurality of flows based on characteristics of the communication traffic; a parallel number calculation step of calculating a parallel number, which is the maximum number of prediction processes that can be completed before the second period begins, when prediction processes that predict the traffic volume for a second period after the first period are performed in parallel for each flow based on the traffic volume for each flow during a first period and predetermined conditions; a traffic prediction step of performing the prediction process on a number of flows that is within the parallel number, if the number of flows classified by the flow classification step is greater than the parallel number; and a total traffic calculation step of calculating a total of the traffic volume for the second period based on the results of the prediction processes in the traffic prediction step.
[0013] According to the present invention, even when a plurality of flows are mixed, it is possible to suppress the occurrence of congestion and reduce communication delays while satisfying communication quality.
[0014] 1 is a diagram showing the configuration of a communication system 1, which is an example of a conventional communication system. FIG. 2 is a diagram showing the configuration of a mobile communication system 10, which is an example of a conventional communication system. FIG. 3 is a block diagram showing the configuration of a switching instruction device 17 of the mobile communication system 10, which is an example of a conventional communication system. FIG. 4 is a diagram showing the flow of processing in the switching instruction device 17 of the mobile communication system 10, which is an example of a conventional communication system. FIG. 5 is a flow diagram showing the remote station traffic volume prediction processing in the prediction unit 171. FIG. 6 is a flow diagram showing the traffic volume prediction model creation processing in the prediction unit 171. FIG. 7 is a flow diagram showing the future traffic volume prediction processing in the prediction unit 171. FIG. 8 is a flow diagram showing the upper link traffic volume prediction processing in the prediction unit 171. FIG. 9 is a flow diagram showing the switching threshold calculation processing in the switching threshold determination unit 172. FIG. 10 is a diagram showing an example of a lookup table. The lookup table is data in which prediction accuracy is associated with an error rate and a calculation formula for a switching threshold. FIG. 11 is a flow diagram showing the switching judgment processing in the switching judgment unit 175. FIG. 12 is a block diagram showing the functional configuration of a prediction unit 171a of a communication system in a first embodiment of the present invention. FIG. 1 is a schematic diagram for explaining the definition of a flow that is a prerequisite in the first embodiment of the present invention. FIG. 2 is a diagram showing an example of the configuration of a flow information table in the first embodiment of the present invention. FIG. 3 is a block diagram showing the functional configuration of a grouping prediction unit 730 of the communication system in the first embodiment of the present invention. FIG. 4 is a block diagram showing the functional configuration of a prediction unit 171b of the communication system in the second embodiment of the present invention. FIG. 5 is a diagram for explaining the functional configuration of a parallelizable number calculation unit 731b of the communication system in the second embodiment of the present invention. FIG. 6 is a block diagram showing the functional configuration of a prediction unit 171c of the communication system in the third embodiment of the present invention. FIG. 7 is a block diagram showing the functional configuration of a grouping prediction unit 730c of the communication system in the third embodiment of the present invention. FIG. 8 is a flowchart showing the operation of the grouping prediction unit 730c of the communication system in the third embodiment of the present invention. FIG. 9 is a block diagram showing the functional configuration of a prediction unit 171d of the communication system in the fourth embodiment of the present invention. FIG. 10 is a block diagram showing the functional configuration of a grouping prediction unit 730d of the communication system in the fourth embodiment of the present invention.10 is a flowchart showing the operation of a grouping prediction unit 730d of a communication system according to a fourth embodiment of the present invention. FIG. 11 is a flowchart showing the operation of a grouping prediction unit 730d of a communication system according to the fourth embodiment of the present invention. FIG. 12 is a block diagram showing the functional configuration of a prediction unit 171e of a communication system according to a fifth embodiment of the present invention. FIG. 13 is a block diagram showing the functional configuration of a grouping prediction unit 730e of a communication system according to the fifth embodiment of the present invention. FIG. 14 is a block diagram showing the functional configuration of a prediction unit 171f of a communication system according to a sixth embodiment of the present invention. FIG. 15 is a block diagram showing the functional configuration of a grouping prediction unit 730f of a communication system according to the sixth embodiment of the present invention. FIG. 16 is a block diagram showing the functional configuration of a prediction unit 171g of a communication system according to a seventh embodiment of the present invention. FIG. 17 is a block diagram showing the functional configurations of a switching threshold determination unit 172g and a switching determination unit 175g of a switching instruction device 17g according to the seventh embodiment of the present invention. FIG. 18 is a flowchart showing the operation of a switching flow calculation unit 177 of a switching determination unit 175g according to the seventh embodiment of the present invention. FIG. 19 is a diagram showing the flow of basic processing by a switching instruction device according to each embodiment of the present invention. FIG. 20 is a diagram for explaining the execution timing of grouping processing by a flow classification unit based on the number of parallelism according to each embodiment of the present invention. 10A and 10B are diagrams for explaining the execution timing of a grouping process by a flow classification unit based on the number of parallel flows according to each embodiment of the present invention.
[0015] Hereinafter, a prediction device, a communication control device, and a prediction method according to embodiments of the present invention will be described in detail with reference to the drawings. Note that components having the same functions in each embodiment will be assigned the same reference numerals, and repeated explanations of those functions may be omitted.
[0016] In order to make the description of the configuration of the communication system according to the embodiment of the present invention easier to understand, an example of the configuration of a conventional communication system will be described first for comparison.
[0017] FIG. 1 is a diagram showing the configuration of a communication system 1, which is an example of a conventional communication system. The communication system 1 has a plurality of lower-level devices 3, a plurality of upper-level devices 4, and a switching instruction device 7. The lower-level devices 3 and the upper-level device 4 are connected via a network 5. The network 5 is configured to include one or more transfer devices (not shown; devices corresponding to the transfer device 15 shown in FIG. 2, which will be described later). The transfer device also functions as a switching device that can change the connection relationship between the lower-level devices 3 and the upper-level device 4.
[0018] 1, the four lower devices 3 are referred to as lower devices 3-1 to 3-4, and the two upper devices 4 are referred to as upper devices 4-1 and 4-2. The direction from the lower device 3 to the upper device 4 is referred to as "upstream," and the direction from the upper device 4 to the lower device 3 is referred to as "downstream."
[0019] The lower device 3 transmits an upstream signal to the connected upper device 4. The network 5 transfers the upstream signal to the upper device 4 according to the communication path between the lower device 3 and the upper device 4. The upper device 4 also transmits a downstream signal to the connected lower device 3. The network 5 transfers the downstream signal to the lower device 3 according to the communication path between the lower device 3 and the upper device 4. The switching instruction device 7 instructs each device, such as a transfer device, to switch the communication path.
[0020] The switching instruction device 7 uses information such as traffic volume or traffic allocation volume (hereinafter collectively referred to as "traffic volume") acquired from the lower-level device 3 and the upper-level device 4 to predict in advance the traffic volume of some or all communication links (hereinafter simply referred to as "links" or "flows") in the communication path between the lower-level device 3 and the upper-level device 4. The switching instruction device 7 determines a switching threshold for each link based on the traffic volume prediction accuracy and the transmission capacity of the link.
[0021] The transmission capacity of a link can be, for example, a link rate. The link rate is the maximum communication speed of the link. The switching threshold is a threshold used to determine whether congestion that requires switching of the communication path (route switching) is predicted. For example, even if the link rate is the same, the switching instruction device 7 determines a lower switching threshold as the prediction accuracy decreases.
[0022] The switching instruction device 7 determines whether congestion will occur for each link using information on the predicted traffic volume and a switching threshold. If congestion is predicted to occur in any link, the switching instruction device 7 determines to perform path switching for load balancing. The switching instruction device 7 instructs switching of communication paths so that at least a portion of the traffic transmitted through a link predicted to be congested is transmitted through a link predicted not to be congested. This enables optimal communication path switching according to prediction accuracy. Furthermore, link congestion delays are reduced, achieving high bandwidth utilization efficiency.
[0023] As shown in FIG. 1 , the switching instruction device 7 includes a prediction unit 71, a switching threshold determination unit 72, and a switching determination unit 75. The prediction unit 71 acquires prediction information from each device to be used for predicting the traffic volume of each link. The prediction information includes, for example, the traffic volume observed by the device, the traffic allocation volume to the device, the number of terminals connected to the device, and communication quality. The prediction unit 71 uses the prediction information to predict the future traffic volume for each link (hereinafter referred to as "future traffic volume"). Note that any existing technology can be used to predict the future traffic volume.
[0024] The switching threshold determination unit 72 includes a prediction accuracy calculation unit 73 and a threshold calculation unit 74. The prediction accuracy calculation unit 73 calculates prediction accuracy for each link using past prediction results of future traffic volume and actual traffic volume. The threshold calculation unit 74 determines a switching threshold for each link such that the ratio to the link's transmission capacity (e.g., link rate) decreases as the prediction accuracy decreases.
[0025] The switching determination unit 75 determines in advance whether congestion will occur for each link using the value of the predicted future traffic volume and a switching threshold. If congestion is predicted, the switching determination unit 75 determines to perform route switching for load balancing. For example, the switching determination unit 75 determines to perform route switching from a link where congestion is predicted to occur to a link with a low link utilization rate. The switching determination unit 75 instructs each device to perform processing for route switching.
[0026] An example in which the communication system 1 is applied to a mobile communication system will be described below.
[0027] 2 is a diagram showing the configuration of a mobile communication system 10, which is an example of a conventional communication system. The mobile communication system 10 is an example of the communication system 1. The mobile communication system 10 is, for example, a fifth-generation mobile communication system (5G). The mobile communication system 10 includes a plurality of terminal stations 11, a plurality of antenna stations 12, a plurality of remote stations 13, a plurality of central stations 14, a transfer device 15, a switching instruction device 17, and a resource allocation device 16.
[0028] The terminal station 11, the antenna station 12, the distributed stations 13, and the central station 14 are UE (User Equipment), RU (Radio Unit), DU (Distributed unit), and CU (Central unit), respectively, of the fifth-generation mobile communication system. The distributed stations 13 are an example of a lower-level device 3, and the central station 14 is an example of a higher-level device 4. The transfer device 15 is an example of a transfer device that constitutes the network 5.
[0029] The transfer device 15 also functions as a switching device that can change the connection relationship between the remote stations 13 and the central station 14. The transfer function and the switching function of the transfer device 15 may be configured as separate devices. Devices such as the switching instruction device 17, the transfer device 15, and the resource allocation device 16 may be configured as an integrated device.
[0030] The mobile communication system 10 is connected to an upper network 20. Here, the M (M is an integer equal to or greater than 1) remote stations 13 are respectively referred to as remote stations 13-1 to 13-M. Furthermore, the Km (Km is an integer equal to or greater than 1) antenna stations 12 subordinate to the remote station 13-m (m is an integer equal to or greater than 1 and equal to or less than M) are respectively referred to as antenna stations 12-m. Furthermore, the N (N is an integer equal to or greater than 2) central stations 14 are respectively referred to as central stations 14-1 to 14-N. Therefore, the mobile communication system 10 shown in FIG. 2 is an example of a mobile communication system in which M=4, K1=2, K2=2, K3=2, K4=2, and N=2.
[0031] The terminal station 11 transmits and receives radio signals to and from the antenna station 12 using radio resources allocated by the remote station 13. The allocated radio resources include information indicating the start and end timings of time periods during which radio signal transmission and reception are permitted. The start and end timings are represented by, for example, slots. A slot is a unit of scheduling for data transmission and reception in a radio frame. The allocated radio resources may further include information indicating a coding rate and a modulation method.
[0032] The antenna station 12 receives uplink data from the terminal station 11 via a wireless signal. The antenna station 12-m sets the received uplink data as an uplink signal and transmits the uplink signal to the remote station 13-m via a wired interface. The antenna station 12-m also receives a downlink signal from the remote station 13-m via a wired interface. The antenna station 12 transmits the downlink data addressed to the terminal station 11, which is set in the received downlink signal, to the terminal station 11 via a wireless signal.
[0033] The remote station 13-m receives uplink signals from each of the Km antenna stations 12-m. The uplink signals received by the remote station 13-m include uplink data received by the antenna station 12-m from the terminal stations 11 under its control. The remote station 13 generates an uplink signal that aggregates the uplink data and transmits the generated uplink signal to the central station 14 to which the remote station 13 is connected. The remote station 13 also receives a downlink signal from the central station 14 to which the remote station 13 is connected, in which downlink data addressed to the terminal stations 11 under its control is set. The remote station 13-m converts the received downlink signal into a downlink signal corresponding to the radio signal to be transmitted from each antenna station 12-m. The remote station 13-m transmits the converted downlink signal to the antenna station 12-m corresponding to the downlink signal.
[0034] The central station 14 aggregates the upstream signals received from the subordinate remote stations 13 and transfers them to the upper network 20. The central station 14 also receives a downstream signal containing downstream data addressed to a terminal station 11 from the upper network 20, and transfers the received downstream signal to the remote station 13 connected to the destination terminal station 11.
[0035] The transfer device 15 (switching device) is connected to the remote stations 13, the central station 14, and the switching instruction device 17. The transfer device 15 transfers signals along the communication path between the remote stations 13 and the central station 14. That is, the transfer device 15 transfers an upstream signal received from the remote station 13 to the destination central station 14 along the communication path. The transfer device 15 also transfers a downstream signal received from the central station 14 to the destination remote station 13 along the communication path. The transfer along the communication path is instructed by the switching instruction device 17. The resource allocation device 16 manages the resources of the central station 14.
[0036] The switching instruction device 17 is connected to the remote station 13, the central station 14, and the transfer device 15. The switching instruction device 17 may further be connected to the resource allocation device 16. The switching instruction device 17 instructs the transfer device 15 (switching device) to switch the communication path between the remote station 13 and the central station 14. In the mobile communication system 10, the communication path between the remote station 13 and the central station 14 is determined by the connection relationship between the remote station 13 and the central station 14. Therefore, in the mobile communication system 10, the path between the remote station 13 and the central station 14 is switched by controlling the transfer device 15 (switching device) to change the central station 14 to which the remote station 13 is connected.
[0037] In addition, the switching instruction device 17 of the mobile communication system 10 determines whether congestion has occurred based on the upstream traffic. Therefore, unless otherwise specified, the traffic here refers to the traffic of the upstream signal.
[0038] 3 is a block diagram showing the configuration of a switching instruction device 17 of a mobile communication system 10, which is an example of a conventional communication system. The switching instruction device 17 includes a prediction unit 171, a switching threshold value determination unit 172, and a switching determination unit 175.
[0039] The prediction unit 171 receives radio information from the remote stations 13 as prediction information. The radio information indicates radio resources to be allocated to terminal stations 11 subordinate to the remote stations 13. The radio information is, for example, link control information (DCI: Downlink Control Information). The prediction unit 171 calculates the future traffic volume of each remote station 13 using the radio information from the remote stations 13.
[0040] Furthermore, the prediction unit 171 calculates the future traffic volume of each upper link based on the connection relationship between the remote stations 13 and the aggregation station 14 and the future traffic volume of each remote station 13. The upper link is the link between the aggregation station 14 and the transfer device 15. The upstream traffic volume of the upper link between the aggregation station 14-n (n is an integer between 1 and N) and the transfer device 15 corresponds to the total traffic volume of the upstream signals that the aggregation station 14-n receives from each of the remote stations 13 under its control. The prediction unit 171 outputs the future traffic volume of the upper link to the switching threshold determination unit 172 and the switching determination unit 175.
[0041] The switching threshold determination unit 172 includes a prediction accuracy calculation unit 173 and a threshold calculation unit 174. The prediction accuracy calculation unit 173 receives information indicating actual traffic volume from the remote station 13. The prediction accuracy calculation unit 173 calculates the actual traffic volume that actually flows through each upper link based on the actual traffic volume from the remote station 13 and the connection relationship between the remote station 13 and the central station 14. The prediction accuracy calculation unit 173 calculates prediction accuracy for each upper link based on the future traffic volume predicted in the past by the prediction unit 171 and the actual traffic volume. The threshold calculation unit 174 calculates a switching threshold for each upper link based on the link rate and prediction accuracy. The threshold calculation unit 174 outputs the switching threshold for each upper link to the switching determination unit 175.
[0042] The switching determination unit 175 calculates a predicted link utilization rate for each upper link using the value of the future traffic volume received from the prediction unit 171 and the switching threshold received from the threshold calculation unit 174. When the switching determination unit 175 determines that congestion will occur in an upper link because the predicted link utilization rate is high, the switching determination unit 175 determines to perform path switching by changing the aggregation station 14 to which the remote station 13 is connected. When the switching determination unit 175 determines to perform path switching, it instructs each device (the remote station 13, the aggregation station 14, and the transfer device 15) to perform path switching.
[0043] Specifically, the switching determination unit 175 instructs the central station 14 that was the connection destination before the path switching (hereinafter referred to as the "switching source") to release the connection with the remote station 13, and instructs the central station 14 that is the connection destination after the path switching (hereinafter referred to as the "switching destination") to connect with the remote station 13. Furthermore, the switching instruction device 17 instructs the transfer device 15 (switching device) to switch the path so that signal transfer is performed via the communication path after the path switching.
[0044] 4 is a diagram showing a processing flow in the switching instruction device 17 of the mobile communication system 10, which is an example of a conventional communication system. The prediction unit 171 predicts future traffic volume of an upper link, for example, for a period D(a) (step S1). The prediction accuracy calculation unit 173 obtains information indicating the future traffic volume predicted in step S1 from the prediction unit 171 and stores the information until it obtains information indicating the actual traffic volume for the period D(a) (step S2).
[0045] The prediction accuracy calculation unit 173 receives information indicating the actual traffic volume of the upper link for period D(a) (step S3). The prediction accuracy calculation unit 173 calculates the prediction accuracy based on the stored future traffic volume for period D(a) and the received actual traffic volume for period D(a). The threshold calculation unit 174 determines a switching threshold based on the link rate and prediction accuracy of the upper link (step S4). The threshold calculation unit 174 outputs the determined switching threshold to the switching determination unit 175.
[0046] Meanwhile, the prediction unit 171 calculates the future traffic volume of the upstream link for period D(b), which is a period after period D(a) (step S5). The switching determination unit 175 acquires the switching threshold output from the threshold calculation unit 174 in step S4 (step S6). Furthermore, the switching determination unit 175 acquires information indicating the future traffic volume for period D(b) calculated in step S5 from the prediction unit 171 (step S7). The switching determination unit 175 determines whether or not route switching is necessary based on the switching threshold and the value of the future traffic volume for period D(b) (step S8).
[0047] As described above, the future traffic volume acquired by the switching threshold value determination unit 172 is the traffic volume at a time earlier than the future traffic volume acquired by the switching determination unit 175 .
[0048] Next, a detailed description will be given of the processing of the switching instruction device 17. First, a description will be given of the processing of predicting future traffic volume of each upper link in the prediction unit 171. The prediction unit 171 performs the processing of steps S1 and S5 in Fig. 4 by the processing of Figs. 5 to 8 below.
[0049] FIG. 5 is a flow diagram showing the remote station traffic volume prediction process in the prediction unit 171. At time t(i-1), the remote station 13 notifies the terminal station 11 of DCI(i) for the next transmission period, and further notifies the switching instruction device 17 of DCI information in which DCI(i) is set (i is an integer). DCI(i) indicates the radio resources to be allocated to the terminal station 11 in slot SL(i) from time t(i) to time t(i+1), as well as the coding rate and modulation scheme used by the terminal station 11. Specifically, the DCI includes scheduling information, MCS (Modulation and Coding Scheme), and other information required for the terminal station 11 to transmit uplink data. The scheduling information is represented by resource blocks. The resource block is represented by a channel and the transmission start and end timings using that channel. The MCS represents the data modulation and channel coding rate. The TBS (Transport Block Size) is determined based on the size of the resource block and the MCS. TBS allows for predictable traffic volumes.
[0050] At time t(i-1), the switching instruction device 17 receives DCI information in which DCI(i) is set from each remote station 13. Based on the information included in DCI(i), the prediction unit 171 calculates the predicted traffic volume DU(i) of the remote station 13 for the period D(i) corresponding to the slot SL(i) (step S111). Furthermore, the prediction unit 171 calculates the allocation time interval T(i) from the difference between time t(i) and time t(i+1) (step S112). The allocation time interval T(i) corresponds to the duration of the slot SL(i), i.e., the duration of the period D(i) from time t(i) to time t(i+1). The prediction unit 171 may receive the allocation time interval T(i) from the remote station 13. The prediction unit 171 stores the predicted traffic volume DU(i) of each remote station 13, the allocation time interval T(i), and the period D(i) in association with each other.
[0051] The prediction unit 171 creates a traffic volume prediction model (step S113). The traffic volume prediction model is a model that uses traffic volumes of q (e.g., q=100) slots in a time series as input data and predicts the traffic volume of the slot next to the input data. Details of creating the traffic volume prediction model will be described later using FIG. 6.
[0052] The prediction unit 171 predicts the future traffic volume DU(i+1) of each remote station 13 during the period D(i+1) from time t(i+1) to time t(i+2) using the traffic volume prediction model created in step S113 (step S114). Details of the prediction process will be described later with reference to Fig. 7. After the process of step S114, the prediction unit 171 performs the process of Fig. 8, which will be described later, to calculate the traffic volume for each upper link.
[0053] 6 is a flowchart showing the traffic volume prediction model creation process of the prediction unit 171. FIG. 6 shows the detailed process of step S113 in FIG.
[0054] The prediction unit 171 stores in advance K time intervals to be processed: T_1, T_2, ..., T_k-1, and T_req. The time intervals T_1 to T_k-1 are the time lengths of slots that can be used when allocating resource blocks to the terminal station 11. For example, T_1 to T_k-1 are 125 us, 250 us, 500 us, and 1 ms. The allocation time interval T(i) has the same value as one of the time intervals T_1 to T_k-1. The time interval T_req is a value required by an application or the like. The time interval T_req has a value greater than T_1 to T_k-1. The prediction unit 171 selects one of the time intervals T_1 to T_req that has not been selected yet, and sets it to T_x (step S121).
[0055] The prediction unit 171 determines whether the allocated time interval T(i) is equal to or greater than the time interval T_x (step S122). If the prediction unit 171 determines that the allocated time interval T(i) is equal to or greater than the time interval T_x (step S122: YES), the prediction unit 171 converts the predicted traffic volume DU(i) of the remote station 13 into a predicted traffic volume for each time interval T_x (step S123). That is, the prediction unit 171 calculates that a predicted traffic volume DU_T_x will occur for each time interval T_x between time t(i) and time t(i+1), where DU(i) is the predicted traffic volume DU(i) × (time interval T_x / allocated time interval T(i)). For example, suppose the allocated time interval T(i) is 250 us and the time interval T_x is 125 us. The prediction unit 171 predicts that a traffic volume of DU_125us = DU(i) / 2 will occur between time t(i) and time t(i)+125us and between time t(i)+125us and time t(i+1).
[0056] The prediction unit 171 adds the predicted traffic volume calculated in step S123 to the time-series predicted traffic volume previously calculated for the time interval T_x for each remote station 13 and stores the result (step S124). The prediction unit 171 learns a traffic volume prediction model for the time interval T_x using the stored time-series predicted traffic volumes of the remote stations 13 for the time interval T_x (step S125).
[0057] For example, the time-series predicted traffic volumes of the remote station 13 for the time interval T_x may be DU_T_x(P), DU_T_x(P-1), DU_T_x(P-2), ..., DU_T_x(1) in order of most recent time (P is an integer equal to or greater than 2). The prediction unit 171 generates learning data for each remote station 13, with DU_T_x(p) as the correct output data and DU_T_x(p-1) to DU_T_x(p-q) as the input data, by sequentially subtracting 1 from the value of p (q is an integer equal to or greater than 1, for example, q=100). The prediction unit 171 uses the generated learning data to learn a traffic volume prediction model that represents the correspondence between input data and output data.
[0058] On the other hand, if the prediction unit 171 determines in step S122 that the allocated time interval T(i) is smaller than the time interval T_x (step S122: NO), it performs the process of step S126. The prediction unit 171 records the predicted traffic volume DU(i) of the remote station 13-m in a buffer in the prediction unit 171 corresponding to the remote station 13-m and the time interval T_x (step S126). The prediction unit 171 determines whether the predicted traffic volume for the time interval T_x has been recorded in the buffer corresponding to each remote station 13 and the time interval T_x (step S127). For example, assume that the allocated time interval T(i) is 250 us and the time interval T_x is 500 us. The prediction unit 171 determines whether the predicted traffic volume for T_x / T(i) = 2 has been recorded in the buffer corresponding to 500 us. If the prediction unit 171 determines that the predicted traffic volume for the time interval T_x has not been recorded in the buffer corresponding to the time interval T_x (step S127: NO), the prediction unit 171 performs the process from step S128.
[0059] When the prediction unit 171 determines that the predicted traffic volume for the time interval T_x for each remote station 13 has been recorded in the buffer corresponding to the time interval T_x (step S127: YES), it performs the processing of step S124. That is, the prediction unit 171 reads out the predicted traffic volume DU(i-T_x / T(i)+1) through the predicted traffic volume DU(i) from the buffer corresponding to the time interval T_x for each remote station 13, and sums them up to obtain DU_T_x(P). For example, suppose the allocated time interval T(i) is 250 us and the time interval T_x is 500 us. The prediction unit 171 sums the predicted traffic volume DU(i-1) and the predicted traffic volume DU(i) to calculate DU_500 us(P).
[0060] The prediction unit 171 stores time-series predicted traffic volumes DU_T_x(1) to DU_T_x(P-1) of each remote station 13 that were previously calculated for the time interval T_x. The prediction unit 171 adds a newly calculated predicted traffic volume DU_T_x(P) to these predicted traffic volumes DU_T_x(1) to DU_T_x(P-1) for each remote station 13 and stores the added volume (step S124). The prediction unit 171 performs the process of step S125 and learns a traffic volume prediction model using the time-series predicted traffic volumes for the time interval T_x.
[0061] After the process of step S125, or if the determination in step S127 is NO, the prediction unit 171 determines whether all of the K time intervals to be processed, T_1 to T_req, have been selected (step S128). If there is an unselected time interval (step S128: NO), the prediction unit 171 returns to step S121 and sets the newly selected time interval to T_x.
[0062] Then, if the prediction unit 171 determines that all K time intervals to be processed have been selected (step S128: YES), it stores a traffic volume prediction model corresponding to each of the K time intervals T_1 to T_req and a predicted time, which is the time from when input data is input to the traffic volume prediction model to when output data is output (step S129).
[0063] 7 is a flow diagram showing the future traffic volume prediction process of the prediction unit 171. Fig. 7 shows detailed processing in step S114 of Fig. 5. The prediction unit 171 determines whether it is possible to predict future traffic volume by time t(i+1), when the next period D(i) ends (step S131). Specifically, the prediction unit 171 determines whether the sum of the allocated time interval T(i) and the switching time Tc is longer than the prediction time of the traffic volume prediction model for the allocated time interval T(i).
[0064] If the allocation time interval T(i) + switching time Tc is longer than the predicted time (T(i) + Tc > predicted time), the prediction unit 171 determines that it is possible to predict future traffic volume by the end of the next period D(i) (step S131: YES). The prediction unit 171 inputs the p most recent time-series predicted traffic volumes DU(P) to DU(P-p+1) for the allocation time interval T(i) into the traffic volume prediction model created for each remote station 13. The prediction unit 171 calculates the future traffic volume DU(i+1) for each remote station 13 during the period D(i+1) from time t(i+1) to time t(i+2) (step S132). Note that t(i+2) = t(i+1) + T(i). The prediction unit 171 stores the calculated future traffic volume DU(i+1) for each remote station 13.
[0065] If the predicted time is equal to or greater than the allocation time T(i) + switching time Tc (T(i) + Tc ≦ predicted time), the prediction unit 171 determines that it is impossible to predict future traffic volume by the end of the next period D(i) (step S131: NO). The prediction unit 171 performs prediction from time t(i+1) to the time interval T_req (e.g., 5 ms) ahead, which satisfies the service request delay. For each remote station 13, the prediction unit 171 adds up the predicted traffic volumes of the time series for the allocation time interval T(i) in units of T_req / T(i) in descending order of time to calculate the predicted traffic volume of the time series for the time interval T_req. For each remote station 13, the prediction unit 171 inputs the predicted traffic volumes of the most recent q time series for the time interval T_req into the traffic volume prediction model created for the time interval T_req. As a result, the prediction unit 171 calculates the future traffic volume DUreq(i+1) of each remote station 13 during the period D(i+1) from time t(i+1) to time t(i+2) (step S133). Note that t(i+2) = t(i+1) + T_req. The prediction unit 171 sets the future traffic volume DUreq(i+1) to the future traffic volume DU(i+1) calculated in step S114 of FIG. 5.
[0066] FIG. 8 is a flow diagram showing the upper link traffic volume prediction process in the prediction unit 171. After the process of FIG. 5, the prediction unit 171 executes the upper link traffic volume prediction process shown in FIG. 8. The traffic volume of the upper link between the aggregation station 14-n and the transfer device 15 is the same as the traffic volume of the aggregation station 14-n. Therefore, first, the prediction unit 171 acquires bearer information that the switching instruction device 17 has received in advance from the aggregation station 14 (step S141). The bearer information is used as connection information that indicates the connection between the upper device and the lower device. The prediction unit 171 acquires the connection relationship between the remote station 13 and the aggregation station 14 from the bearer information.
[0067] The prediction unit 171 sums up the future traffic volumes DU(i+1) of the subordinate remote stations 13 calculated in step S114 of Fig. 5 for each central station 14 to calculate the future traffic volume L(i+1), which is the traffic volume of the upper link connected to the central station 14 during the period D(i+1) (step S142). Specifically, the prediction unit 171 calculates the following:
[0068] Future traffic volume L(i+1)=Σfuture traffic volume DU(i+1)×if(aggregate station-distributed station connection)
[0069] if (aggregate station-remote station connection) is a flag that takes the value 1 if the aggregate station 14 is designated as the connection destination of the remote station 13, and takes the value 0 if not. The prediction unit 171 outputs the period D(i+1) and the future traffic volume L(i+1) of each upper link to the switching threshold determination unit 172 and the switching determination unit 175 (step S143).
[0070] 9 is a flow diagram showing the switching threshold calculation process in the switching threshold determination unit 172. The process in FIG. 9 corresponds to the process in step S4 in FIG. 4. The prediction accuracy calculation unit 173 receives information on the period D(a) and the future traffic volume L(a) of each upper link from the prediction unit 171 (step S151). These correspond to the period D(i+1) and the future traffic volume L(i+1) of each upper link output by the prediction unit 171 in step S143 in FIG. 8.
[0071] Next, the prediction accuracy calculation unit 173 acquires the actual traffic volume of each remote station 13 during the period D(a) (step S152). For each central station 14, the prediction accuracy calculation unit 173 sums up the actual traffic volumes for the period D(a) acquired in step S152 for the remote stations 13 under its control, to calculate the actual traffic volume L'(a), which is the actual traffic volume of the upper link connected to the central station 14. Note that the prediction accuracy calculation unit 173 may receive the actual traffic volume L'(a) during the period D(a) from the central station 14.
[0072] The prediction accuracy calculation unit 173 acquires the link rate of each upper link. The prediction accuracy calculation unit 173 calculates the prediction accuracy for each upper link in the period D(a) (step S153). For example, the prediction accuracy calculation unit 173 calculates the following error rate as the prediction accuracy:
[0073] Error rate = | future traffic volume L(a) - actual traffic volume L'(a) | ÷ (actual traffic volume L'(a)) × 100
[0074] Alternatively, the prediction accuracy calculation unit 173 may calculate the following RMSE (Root Mean Squared Error) or MAE (Mean Absolute Error) used to evaluate prediction accuracy, where fi is the future traffic volume L(a) and yi is the actual traffic volume L'(a).
[0075]
[0076]
[0077] Next, the threshold calculation unit 174 calculates a switching threshold to be used after the period D(a) using the prediction accuracy calculated in step S153 (step S154). For example, when the threshold calculation unit 174 calculates the error rate in step S153, it calculates the switching threshold TH of the upper link as follows.
[0078] Switching threshold TH = link rate × (100 - error rate) ÷ 100 (3)
[0079] Alternatively, when the threshold calculation unit 174 calculates the RMSE or MAE in step S153, it converts the previously stored lookup table into an error rate.
[0080] 10 is a diagram showing an example of a lookup table. The lookup table is data that associates prediction accuracy with an error rate and a calculation formula for a switching threshold. The threshold calculation unit 174 reads out an error rate corresponding to the prediction accuracy from the lookup table. The threshold calculation unit 174 uses the read error rate to calculate the switching threshold TH for each upper link according to the above formula (3).
[0081] In FIG. 9, the threshold calculation unit 174 outputs the switching threshold TH of each upper link calculated in step S154 to the switching determination unit 175 (step S155).
[0082] The prediction accuracy is calculated using factors such as accuracy. However, it is uncertain whether this accuracy can actually be guaranteed. In this embodiment, traffic volume is predicted in advance, and then actual traffic flows. Therefore, as described above, the prediction accuracy is calculated using the difference between the actual traffic volume and the predicted traffic volume.
[0083] 11 is a flow diagram showing the switching determination process in the switching determination unit 175. The process in FIG. 11 corresponds to the process in step S8 in FIG. 4. The switching determination unit 175 performs the process in FIG. 11 for each upper link. The switching determination unit 175 receives information on the period D(b) and the future traffic volume L(b) of each aggregation station 14 from the prediction unit 171 (step S161). These correspond to the period D(i+1) and the future traffic volume L(i+1) of each aggregation station 14 output by the prediction unit 171 in step S143 in FIG. 8.
[0084] The switching determination unit 175 receives the switching threshold TH for each upper link output by the threshold calculation unit 174 in step S155 of Fig. 9 (step S162). The switching determination unit 175 calculates the predicted link usage rate of each upper link using the switching threshold TH according to the following equation (4) (step S163).
[0085] Predicted link utilization rate=future traffic volume L(b) / switching threshold TH (4)
[0086] Before substituting the future traffic volume L(b) into equation (4), the switching determination unit 175 converts it into the traffic volume per unit time equal to the link rate, for example by dividing the future traffic volume L(b) by the length of the period D(b). The switching determination unit 175 determines whether the calculated predicted link utilization rate exceeds 1 (step S164). If the switching determination unit 175 determines that the link utilization rate is equal to or less than 1, i.e., that the future traffic volume is equal to or less than the switching threshold, it terminates the processing of FIG. 11 because congestion is predicted not to occur. On the other hand, if the switching determination unit 175 determines that the predicted link utilization rate exceeds 1, i.e., that the future traffic volume will exceed the switching threshold, it determines that congestion is predicted to occur and therefore determines to perform route switching (step S165).
[0087] Fig. 12 is a flow diagram showing the switching determination process in the switching determination unit 175. When it is determined in step S165 of Fig. 11 that route switching is to be performed, the switching determination unit 175 starts the process of Fig. 12.
[0088] The switching determination unit 175 obtains from the prediction unit 171 the future traffic volume for period D(b) of each upper link, information on the distributed stations 13 subordinate to the aggregate station 14 connected to that upper link, and the future traffic volume DU(b) for period D(b) of that distributed station 13. The switching determination unit 175 determines to switch the connection destination of one or more distributed stations 13 subordinate to the aggregate station 14 using an upper link whose predicted link utilization rate exceeds 1 to another aggregate station 14. At this time, the switching determination unit 175 uses the future traffic volume DU(b) of each distributed station 13 to determine the switching destination aggregate station 14 of the distributed station 13 to be switched to, so that the future traffic volume of each upper link is equal to or less than the switching threshold TH for that upper link (step S171).
[0089] The switching determination unit 175 transmits to the source central station 14 a path addition instruction to add traffic from the remote station 13 to be switched (step S172). Furthermore, the switching determination unit 175 transmits to the source central station 14 a path deletion instruction to delete traffic from the remote station 13 to be switched (step S173). Furthermore, the switching determination unit 175 transmits to the transfer device 15 a path switching instruction to instruct the transfer device 15 to switch the communication path between the remote station 13 to be switched and the source central station 14 to the communication path between the remote station 13 to be switched and the target central station 14 (step S174).
[0090] As described above, the communication system 1 and the mobile communication system 10, which are examples of conventional communication systems, predict future traffic volume of the upper link for period D(a) and calculate the prediction accuracy based on the future traffic volume and the actual traffic volume. The communication system 1 and the mobile communication system 10 determine the switching threshold based on the link rate and prediction accuracy of the upper link. Then, the communication system 1 and the mobile communication system 10 predict the future traffic volume of the upper link for period D(b), which is a period after period D(a), and determine whether or not route switching is necessary based on the switching threshold and the future traffic volume.
[0091] However, in an actual communication environment where multiple flows coexist, predicting the future traffic volume of all flows at once results in low prediction accuracy. On the other hand, predicting the future traffic volume for each flow individually increases the computational load involved in the prediction, making it impossible to complete route switching before congestion actually occurs. Thus, in conventional communication systems, even if a decision to perform route switching is made based on predicted traffic volumes, congestion may not be prevented, resulting in communication delays.
[0092] In contrast, the communication system in each embodiment of the present invention described below has a configuration that can complete route switching before congestion occurs. Specifically, the communication system in each embodiment controls the amount of calculation required to predict future traffic volume so that it is within a range that allows route switching to be completed in advance. The communication system in each embodiment groups multiple flows to be predicted and predicts future traffic volume on a group-by-group basis, thereby reducing the amount of calculation. As a result, the communication system in each embodiment can suppress congestion and reduce communication delays while maintaining communication quality, even in a general communication environment where multiple flows coexist.
[0093] <First Embodiment> A communication system according to a first embodiment of the present invention will now be described. Note that the overall configuration of the communication system according to this embodiment is similar to the configuration of the conventional communication system 1 shown in the overall configuration diagram of Figure 1 described above, and therefore a description thereof will be omitted. Furthermore, the overall configuration of a mobile communication system in which the communication system according to this embodiment is applied to mobile communication is also similar to the configuration of the conventional mobile communication system 10 shown in the overall configuration diagram of Figure 2 described above, and therefore a description thereof will be omitted.
[0094] Furthermore, the block diagram showing the functional configuration of the switching instruction device of the communication system in the first embodiment is the same as the block diagram showing the functional configuration of the switching instruction device 17 of the conventional communication system 1 shown in FIG. 3 described above. Hereinafter, the switching instruction device in the first embodiment will be referred to as switching instruction device 17a. The switching instruction device 17a is, for example, an information processing device such as a general-purpose computer. The switching instruction device 17a in this embodiment and the conventional switching instruction device 17 described above differ in the configuration of the prediction unit. The configuration of the prediction unit 171a of the communication system in this embodiment will be described below.
[0095] 13 is a block diagram showing the functional configuration of the prediction unit 171a of the communication system according to the first embodiment of the present invention. As shown in Fig. 13, the prediction unit 171a includes a flow classification unit 710, a flow information storage unit 720, a grouping prediction unit 730, and a total traffic calculation unit 740.
[0096] The flow classification unit 710 classifies flows input to the network 5 within a predetermined period (e.g., 1 millisecond or 1 second) based on traffic characteristics. Here, a flow is defined as a flow transmitted from a lower-level device 3 to a higher-level device 4 via the network 5.
[0097] In this example, flows with the same traffic pattern are defined as one flow. Flows with the same traffic pattern are, for example, flows with the same QoS. Even flows with the same lower-level device 3 and upper-level device 4 are defined as different flows if they have different traffic patterns (for example, different QoS).
[0098] Fig. 14 is a schematic diagram for explaining the definition of a flow, which is a prerequisite for the first embodiment of the present invention. Fig. 14 illustrates an example in which there are three terminals (UE) that are lower-level devices 3, and the thick circles represent the flows from each terminal. The flows from each terminal may include multiple flows with different traffic patterns (different QoS).
[0099] The thick cylinder in the top row shows two traffic pattern flows represented by thin cylinders with light hatching and thin cylinders with medium hatching, while the thick cylinder in the middle row shows three traffic pattern flows represented by thin cylinders with light hatching, thin cylinders with medium hatching, and thin cylinders with dark hatching, respectively. The thick cylinder in the bottom row shows only one traffic pattern flow represented by a thin cylinder with light hatching.
[0100] For example, a thin cylinder with a dark hatch represents video traffic with a frame rate of 60 fps (frames per second), a thin cylinder with a medium hatch represents the flow of video traffic with a frame rate of 30 fps, and a thin cylinder with a light hatch represents the flow of file transfer traffic via FTP (File Transfer Protocol), etc.
[0101] The prediction unit 171a in this embodiment assumes that flows with the same traffic pattern (with the same QoS) have the same flow characteristics (for example, periodicity, etc.) The prediction unit 171a classifies flows by traffic pattern and predicts future traffic volume.
[0102] The flow classification unit 710 classifies flows by flow type based on information defined in, for example, 5QI (5G QoS Identifier) or S-NSSAI (Sub Network Slice Selection Assist Information), etc. The flow classification unit 710 calculates the total number of terminals and traffic volume for each classified flow and stores them in a flow information table stored in the flow information storage unit 720.
[0103] The flow information storage unit 720 is configured to include a storage medium, for example, a semiconductor memory such as RAM (Random Access Memory), EEPROM (Electrically Erasable Programmable Read Only Memory) and ROM (Read Only Memory), a flash memory such as SSD (Solid State Drive), a magnetic disk such as HDD (Hard Disk Drive), an optical disk, or any combination of these storage media (not shown).
[0104] 15 is a diagram showing an example of the configuration of a flow information table in the first embodiment of the present invention. As shown in Fig. 15, for example, the flow information table is tabular data in which a flow ID (Identifier), a flow type, a traffic volume, the number of terminals, and the number of flows are associated with each other.
[0105] The flow ID is an identifier that identifies a classified flow. The flow type is a value that represents the flow characteristics. In the flow information table illustrated in FIG. 15, the value of the flow type is a 5QI value. The traffic volume is the total value of the traffic volume for each classified flow. In the flow information table illustrated in FIG. 15, the unit of traffic volume is kilobytes. The number of terminals is the total value of the number of terminals for each classified flow. In the flow information table illustrated in FIG. 15, the unit of traffic volume is units.
[0106] The grouping prediction unit 730 calculates the possible parallel number based on a predetermined allowable delay time (hereinafter referred to as "allowable delay") and the predicted time. The allowable delay is the delay time that is allowable in order to complete the prediction process before the timing when the route switching is required based on the prediction of future traffic volume. The predicted time here refers to the time required for the prediction process of future traffic volume. The possible parallel number here refers to the maximum number of prediction processes that can be executed in parallel for multiple flows and completed within the allowable delay range.
[0107] The grouping prediction unit 730 predicts future traffic volume by adjusting the number of prediction processes to be executed in parallel so that it is within the parallelizable number, thereby suppressing the amount of calculation so that the time required for the prediction process falls within the allowable delay range. The grouping prediction unit 730 outputs the value of the predicted future traffic volume to the total traffic calculation unit 740.
[0108] The following provides a more detailed explanation of the configuration of the grouping prediction unit 730. Fig. 16 is a block diagram showing the functional configuration of the grouping prediction unit 730 of the communication system according to the first embodiment of the present invention. As shown in Fig. 16, the grouping prediction unit 730 includes a parallelizable number calculation unit 731 and a traffic prediction unit 732.
[0109] The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) for each flow based on the flow ID. The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) based on, for example, information about 5QI or S-NSSAI stored in a storage medium (not shown) included in the prediction unit 171a. Note that the information about 5QI or S-NSSAI may be stored in the flow information storage unit 720. The storage medium (not shown) may include, for example, a storage medium such as RAM, semiconductor memory such as EEPROM and ROM, flash memory such as SSD, magnetic disk such as HDD, optical disk, or any combination of these storage media.
[0110] For example, the allowable delay value can be the "PDB (Packet Delay Budget)" value when using 5QI, or the "Max allowed end-to-end latency" value when using S-NSSAI.
[0111] In addition, in the case of a flow ID that is not related to the allowable delay, it is sufficient to predetermine, for example, an arbitrary allowable delay value to be used. For example, in the case of a flow ID that is not related to the allowable delay, it is sufficient to predetermine, for example, a value such as Delay_a = 10 [ms]. Alternatively, in the case of using S-NSSAI, it is sufficient to use a default value set according to the service. For example, in the case of using S-NSSAI, it is sufficient to use default values such as URLLC = 1 [ms], eMbb = 10 [ms], etc. In this case, it is assumed that the correspondence between the service and the allowable delay value is predetermined in a flow information table or the like.
[0112] The parallel number calculation unit 731 acquires information indicating the time required for prediction (Ti_pred) (hereinafter referred to as "predicted time") predicted by the traffic prediction unit 732. The parallel number calculation unit 731 calculates the parallel number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred), as shown in the following equation (5).
[0113] M=Delay_a / Ti_pred...(5)
[0114] For example, if the allowable delay is 100 milliseconds (i.e., Delay_a = 100 [ms]) and the predicted time is 5 milliseconds (i.e., Ti_pred = 5 [ms]), the possible parallel number is 20 (i.e., M = 20). Note that since the predicted time differs for each flow depending on the number of input data (traffic period), the predicted time (Ti_pred) may be set to the maximum predicted time or the average predicted time. The possible parallel number calculation unit 731 outputs the calculated value of the possible parallel number (M) to the traffic prediction unit 732.
[0115] The traffic prediction unit 732 obtains the value of the parallel number (M) output from the parallel number calculation unit 731. The traffic prediction unit 732 narrows down the number of flows so that it falls within the parallel number (M) and predicts future traffic volume (hereinafter also referred to as "predicted traffic volume"). In this embodiment, the traffic prediction unit 732 narrows down the number of flows to be subjected to prediction processing by randomly selecting M flows from all of the classified flows.
[0116] The number of selected flows may be any number up to M. However, since the accuracy of predicting future traffic volume decreases as the number of selected flows decreases, it is desirable that the number of selected flows be M, which is the maximum number of flows that can be predicted in parallel within the allowable time (i.e., the number that can be parallelized).
[0117] In this embodiment, the traffic prediction unit 732 is configured to randomly select M flows, but this configuration is not limiting. The traffic prediction unit 732 may be configured to select M flows according to any rule. A configuration for more efficiently narrowing down the number of flows will be described in another embodiment described later.
[0118] The traffic prediction unit 732 predicts future traffic volumes for the selected M flows and outputs the values of the future traffic volumes (predicted traffic volumes) predicted for each of the M flows to the total traffic calculation unit 740.
[0119] 13 , the total traffic calculation unit 740 acquires the value of the predicted traffic volume for each of the M flows predicted by the traffic prediction unit 732 of the grouping prediction unit 730. The total traffic calculation unit 740 adds up the acquired predicted traffic volumes to obtain the value of the total traffic volume (hereinafter referred to as the “total traffic volume”). The total traffic calculation unit 740 outputs the calculated value of the total traffic volume to the switching threshold determination unit 172.
[0120] The processing after the value of the total traffic volume is output from the total traffic calculation unit 740 of the prediction unit 171a to the switching threshold determination unit 172 (i.e., processing related to determining whether to perform route switching and processing related to controlling the implementation of route switching) is not described here because it is the same as the processing in the conventional communication system 1. In other words, the processing after the processing by the prediction unit 171a is the same as the processing related to the control of route switching by the switching threshold determination unit 172 and the switching determination unit 175 of the conventional communication system 1 described above with reference to Figures 9 to 12 and the like, and the processing related to route switching by the transfer device 15, and therefore not described here.
[0121] As described above, the switching instruction device 17a in the first embodiment of the present invention classifies each of the flows input from, for example, the lower-level device 3 during a predetermined period based on traffic pattern (e.g., QoS) characteristics based on information defined in, for example, 5QI or S-NSSAI. Based on the allowable delay and predicted time, the switching instruction device 17a calculates the maximum number of flows that can be subjected to prediction processing in parallel within the allowable delay range. The switching instruction device 17a randomly selects M flows from all of the classified flows input during the predetermined period and calculates future traffic volumes (predicted traffic volumes) for each of the selected M flows. The switching instruction device 17a adds up the predicted traffic volumes calculated for each selected flow and determines whether to perform path switching and controls its execution based on the total traffic volume.
[0122] In this way, the switching instruction device 17a in the first embodiment of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel to fall within a range of the possible parallel number that enables the prediction process to be completed within the allowable time for route switching prediction. This allows the switching instruction device 17a to ensure that the prediction process is completed before the timing when route switching is required (i.e., the timing when congestion occurs).
[0123] Therefore, the switching instruction device 17a can improve communication quality by controlling route switching in advance based on the predicted traffic volume, and can prevent congestion and reduce communication delays by controlling the prediction process to be completed within the allowed time. In this way, the switching instruction device 17a in the first embodiment of the present invention can reduce communication delays while satisfying communication quality even when multiple flows are mixed.
[0124] <Second Embodiment> A communication system according to a second embodiment of the present invention will now be described. Note that the overall configuration of the communication system according to this embodiment is similar to the configuration of the conventional communication system 1 shown in the overall configuration diagram of Figure 1 described above, and therefore a description thereof will be omitted. Furthermore, the overall configuration of a mobile communication system in which the communication system according to this embodiment is applied to mobile communication is similar to the configuration of the conventional mobile communication system 10 shown in the overall configuration diagram of Figure 2 described above, and therefore a description thereof will be omitted.
[0125] Furthermore, the block diagram showing the functional configuration of the switching instruction device of the communication system in the second embodiment is the same as the block diagram showing the functional configuration of the switching instruction device 17 of the conventional communication system 1 shown in FIG. 3 described above. Hereinafter, the switching instruction device in the second embodiment will be referred to as switching instruction device 17b. The switching instruction device 17b is, for example, an information processing device such as a general-purpose computer. The switching instruction device 17b of this embodiment and the conventional switching instruction device 17 described above have different configurations of their prediction units. The configuration of the prediction unit 171b of the communication system in this embodiment will be described below.
[0126] 17 is a block diagram showing the functional configuration of a prediction unit 171b of a communication system according to the second embodiment of the present invention. As shown in Fig. 17, the prediction unit 171b includes a flow classification unit 710, a flow information storage unit 720, a grouping prediction unit 730b, and a total traffic calculation unit 740.
[0127] As in the first embodiment described above, the flow classification unit 710 classifies flows input to the network 5 during a predetermined period based on traffic characteristics. The flow classification unit 710 classifies flows by flow type based on information defined in, for example, 5QI or S-NSSAI. The flow classification unit 710 calculates the total number of terminals and traffic volume for each classified flow and stores them in a flow information table stored in the flow information storage unit 720.
[0128] The grouping prediction unit 730b adjusts the number of prediction processes to be executed in parallel so that it is within the possible parallel number, thereby suppressing the amount of calculation so that the time required for the prediction process falls within the allowable delay range, and predicts future traffic volume. The grouping prediction unit 730b outputs the predicted future traffic volume value to the total traffic calculation unit 740.
[0129] As shown in FIG. 17, a grouping prediction unit 730b in the second embodiment has a configuration in which a traffic period calculation unit 733 is added to the grouping prediction unit 730 in the first embodiment described above.
[0130] The traffic period calculation unit 733 calculates the traffic period of each flow. The traffic period calculation unit 733 outputs the calculated traffic period value of each flow to the parallel number calculation unit 731b. The parallel number calculation unit 731b reflects the traffic period calculated by the traffic period calculation unit 733 in the predicted time. By reflecting the traffic period in the predicted time, the parallel number calculation unit 731b in the second embodiment can calculate the parallel number with higher accuracy than the parallel number calculation unit 731 in the first embodiment described above.
[0131] The traffic period calculation unit 733 identifies the traffic pattern of each flow based on, for example, 5QI or S-NSSAI. The traffic period calculation unit 733 calculates the traffic period for each flow based on the identified traffic pattern. Note that the traffic period calculation unit 733 may also calculate the traffic period for each flow based on spectral analysis of time-series traffic.
[0132] The configuration of the parallelizable number calculation unit 731b will be described in more detail below. Fig. 18 is a diagram for explaining the functional configuration of the parallelizable number calculation unit 731b of the communication system according to the second embodiment of the present invention.
[0133] In this embodiment, the parallel number calculation unit 731b calculates the predicted time (Ti_pred) based on the processing load. However, the present invention is not limited to this configuration, and the parallel number calculation unit 731b may be configured to calculate the predicted time (Ti_pred) based on the time required for past prediction processing by the traffic prediction unit 732. Alternatively, the parallel number calculation unit 731b may be configured to set the average value of the time required for past prediction processing by the traffic prediction unit 732 as the predicted time (Ti_pred). Alternatively, the parallel number calculation unit 731b may be configured to set a predetermined known value as the predicted time (Ti_pred).
[0134] The parallelizable number calculation unit 731b identifies the allowable delay (Delay_a) for each flow based on the flow ID. The parallelizable number calculation unit 731b identifies the allowable delay (Delay_a) based on, for example, information about 5QI or S-NSSAI stored in a storage medium (not shown) included in the prediction unit 171b. Note that the information about 5QI or S-NSSAI may be stored in the flow information storage unit 720.
[0135] For example, the allowable delay value can be the "PDB (Packet Delay Budget)" value when using 5QI, or the "Max allowed end-to-end latency" value when using S-NSSAI.
[0136] In the case of a flow ID that is not related to the allowable delay, for example, an arbitrary allowable delay value may be predetermined. Alternatively, in the case of using S-NSSAI, a default value set according to the service may be used. In this case, the correspondence between the service and the allowable delay value is assumed to be predetermined in a flow information table or the like.
[0137] The parallelizable number calculation unit 731b acquires the value of the traffic period (Ti_traffic) calculated by the traffic period calculation unit 733. The parallelizable number calculation unit 731b calculates a predicted time (Ti_pred) based on the traffic period (Ti_traffic) (number of input data) calculated by the traffic period calculation unit 733, the total processing load (Con_sum), and the processing load of the flow (Con), as shown in the following equation (6).
[0138] Ti_pred=Ti_traffic / Con_sum×Con…(6)
[0139] The parallelizable number calculation unit 731b calculates the parallelizable number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred), as shown in the following equation (7).
[0140] M=Delay_a / Ti_pred...(7)
[0141] The traffic prediction unit 732 calculates the number of parallel processes (M) and outputs the calculated number of parallel processes (M) to the traffic prediction unit 732.
[0142] The traffic prediction unit 732 obtains the value of the parallel number (M) output from the parallel number calculation unit 731b. The traffic prediction unit 732 narrows down the number of flows so that it falls within the parallel number (M) and predicts future traffic volume (predicted traffic volume). In this embodiment, the traffic prediction unit 732 narrows down the number of flows to be subjected to prediction processing by randomly selecting M flows.
[0143] The number of selected flows may be any number equal to or less than M. However, since the accuracy of predicting future traffic volume decreases as the number of selected flows decreases, it is desirable that the number of selected flows be M, which is the maximum number of flows that can be predicted in parallel within the allowable time (i.e., the number that can be parallelized). In this embodiment, the traffic prediction unit 732 is configured to randomly select M flows, but this configuration is not limited to this. The traffic prediction unit 732 may also be configured to select M flows according to any rule. A configuration for more efficiently narrowing down the number of flows will be described in another embodiment described later.
[0144] The traffic prediction unit 732 predicts future traffic volumes for the selected M flows and outputs the values of the future traffic volumes (predicted traffic volumes) predicted for each of the M flows to the total traffic calculation unit 740.
[0145] 17 , the total traffic calculation unit 740 acquires the values of the predicted traffic volumes predicted by the traffic prediction unit 732 of the grouping prediction unit 730 b. The total traffic calculation unit 740 adds up the acquired predicted traffic volumes to obtain the value of the total traffic volume. The total traffic calculation unit 740 outputs the calculated value of the total traffic volume to the switching threshold determination unit 172.
[0146] The processing after the value of the total traffic volume is output from the total traffic calculation unit 740 of the prediction unit 171b to the switching threshold determination unit 172 (i.e., processing related to determining whether to perform route switching and processing related to controlling the implementation of route switching) is not described here because it is the same as the processing in the conventional communication system 1. In other words, the subsequent processing after the processing by the prediction unit 171b is the same as the processing related to the control of route switching by the switching threshold determination unit 172 and the switching determination unit 175 of the conventional communication system 1 described with reference to the above-mentioned Figures 9 to 12, and the processing related to route switching by the transfer device 15, and therefore not described here.
[0147] As described above, the switching instruction device 17b in the second embodiment of the present invention classifies each of the flows input from, for example, the lower-level device 3 during a predetermined period based on the characteristics of the traffic pattern (e.g., QoS) based on information defined in, for example, 5QI or S-NSSAI, etc. Based on the allowable delay and the predicted time, the switching instruction device 17b calculates the maximum number of flows that can be subjected to prediction processing in parallel within the allowable delay range.
[0148] Unlike the switching instruction device 17a in the first embodiment, the switching instruction device 17b in the second embodiment calculates the traffic period of each flow and reflects the calculated traffic period in the predicted time. This allows the switching instruction device 17b in the second embodiment to calculate the possible parallel number with higher accuracy than the switching instruction device 17a in the first embodiment.
[0149] The switching instruction device 17b randomly selects M flows from among the flows input during a predetermined period, calculates future traffic volumes (predicted traffic volumes) for each of the selected M flows, sums up the predicted traffic volumes calculated for each selected flow, and determines whether to perform route switching and controls its execution based on the total traffic volume.
[0150] In this way, the switching instruction device 17b in the second embodiment of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel to within a range of the possible parallel number that enables the prediction process to be completed within the allowable time for route switching prediction. This allows the switching instruction device 17b to ensure that the prediction process is completed before the timing when route switching is necessary (i.e., the timing when congestion occurs).
[0151] Therefore, the switching instruction device 17b can improve communication quality by controlling route switching in advance based on the predicted traffic volume, and can prevent congestion and reduce communication delays by controlling the prediction process to be completed within the allowed time. In this way, the switching instruction device 17b in the second embodiment of the present invention can reduce communication delays while satisfying communication quality even when multiple flows are mixed.
[0152] <Third Embodiment> A communication system according to a third embodiment of the present invention will now be described. Note that the overall configuration of the communication system according to this embodiment is similar to the configuration of the conventional communication system 1 shown in the overall configuration diagram of Fig. 1 described above, and therefore a description thereof will be omitted. Furthermore, the overall configuration of a mobile communication system in which the communication system according to this embodiment is applied to mobile communication is also similar to the configuration of the conventional mobile communication system 10 shown in the overall configuration diagram of Fig. 2 described above, and therefore a description thereof will be omitted.
[0153] Furthermore, the block diagram showing the functional configuration of the switching instruction device of the communication system in the third embodiment is the same as the block diagram showing the functional configuration of the switching instruction device 17 of the conventional communication system 1 shown in FIG. 3 described above. Hereinafter, the switching instruction device in the third embodiment will be referred to as switching instruction device 17c. The switching instruction device 17c is, for example, an information processing device such as a general-purpose computer. The switching instruction device 17c of this embodiment and the conventional switching instruction device 17 described above have different configurations of their prediction units. The configuration of the prediction unit 171c of the communication system in this embodiment will be described below.
[0154] 19 is a block diagram showing the functional configuration of a prediction unit 171c of a communication system according to the third embodiment of the present invention. As shown in FIG. 19, the prediction unit 171c includes a flow classification unit 710, a flow information storage unit 720, a grouping prediction unit 730c, and a total traffic calculation unit 740.
[0155] As in the first embodiment described above, the flow classification unit 710 classifies flows input to the network 5 during a predetermined period based on traffic characteristics. The flow classification unit 710 classifies flows by flow type based on information defined in, for example, 5QI or S-NSSAI. The flow classification unit 710 calculates the total number of terminals and traffic volume for each classified flow and stores them in a flow information table stored in the flow information storage unit 720.
[0156] The grouping prediction unit 730c adjusts the number of prediction processes to be executed in parallel so that it is within the possible parallel number, thereby suppressing the amount of calculation so that the time required for the prediction process falls within the allowable delay range, and predicts future traffic volume. The grouping prediction unit 730c outputs the predicted future traffic volume value to the total traffic calculation unit 740.
[0157] The configuration of the grouping prediction unit 730c will be described in more detail below. Fig. 20 is a block diagram showing the functional configuration of the grouping prediction unit 730c of the communication system according to the third embodiment of the present invention. As shown in Fig. 20, the grouping prediction unit 730c includes a parallelizable number calculation unit 731, a flow classification unit 734 based on parallel numbers, and a traffic prediction unit 732.
[0158] As shown in FIG. 20, a grouping prediction unit 730c in the third embodiment has a configuration in which a flow classification unit 734 based on the number of parallel processes is added to the grouping prediction unit 730 in the first embodiment.
[0159] The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) for each flow based on the flow ID. The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) based on, for example, information about 5QI or S-NSSAI stored in a storage medium (not shown) included in the prediction unit 171c. Note that the information about 5QI or S-NSSAI may be stored in the flow information storage unit 720.
[0160] For example, when 5QI is used, the value of "PDB" can be used as the allowable delay value, and when S-NSSAI is used, the value of "Max allowed end-to-end latency" can be used. Note that, in the case of a flow ID that is not related to the allowable delay, for example, an arbitrary allowable delay value can be determined in advance. Alternatively, when S-NSSAI is used, a specified value set according to the service can be used. Note that in this case, the correspondence between the service and the allowable delay value is assumed to be determined in advance in a flow information table or the like.
[0161] The parallel number calculation unit 731 obtains the value of the predicted time (Ti_pred) predicted by the traffic prediction unit 732. The parallel number calculation unit 731 calculates the parallel number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred), as shown in the following equation (8).
[0162] M=Delay_a / Ti_pred...(8)
[0163] The parallel number calculation unit 731 outputs the calculated value of the parallel number (M) to the flow classification unit 734.
[0164] The flow classification unit 734 based on the parallel number obtains the value of the possible parallel number (M) output from the possible parallel number calculation unit 731. The flow classification unit 734 based on the parallel number compares the obtained possible parallel number (M) with the actual number of flows.
[0165] When the number of flows is equal to or less than the parallel number (M), even if the process of predicting future traffic volume for all flows is executed in parallel, the prediction process will be completed within the allowable time. Therefore, when the number of flows is equal to or less than the parallel number (M), the flow classification unit 734 by parallel number does not need to perform the process of keeping the number of flows within the parallel number, and therefore does not perform the process of selecting only some of the flows from all the flows or the process of grouping multiple flows into one flow.
[0166] On the other hand, if the number of flows is greater than the number of parallelizable flows (M), executing the future traffic volume prediction process for all flows in parallel will prevent the prediction process from completing within the allowable time. This will cause congestion and communication delays. Therefore, if the number of flows is greater than the number of parallelizable flows (M), the flow classification unit 734 classifies the flows into groups so that the number of flows is equal to the number of parallelizable flows.
[0167] The grouping prediction unit 730 in the first embodiment and the grouping prediction unit 730b in the second embodiment described above were configured to select a portion of flows (i.e., the number of flows that can be processed in parallel (M)) from all of the flows classified by the flow classification unit 710 when the number of flows is greater than the number of flows that can be processed in parallel (M), and to perform prediction processing of future traffic volume only for the selected flows.
[0168] In contrast, when the number of flows is greater than the parallelizable number (M), the grouping prediction unit 730c in the third embodiment groups all of the flows classified by the flow classification unit 710 so that the number of flows is the same as the parallelizable number, and performs prediction processing for future traffic volume on a group-by-group basis. Therefore, the grouping prediction unit 730c in the third embodiment performs prediction processing for all of the flows classified by the flow classification unit 710, and is therefore considered to be able to predict future traffic volume with higher accuracy than the grouping prediction unit 730 in the first embodiment and the grouping prediction unit 730b in the second embodiment described above.
[0169] Any method can be used for the grouping (classification) of flows by the parallel number flow classification unit 734. The parallel number flow classification unit 734 sums the traffic volume values of flows classified into the same group to generate time-series traffic (hereinafter referred to as "time-series traffic"). The generated time-series traffic is regarded as one flow.
[0170] For example, if the actual number of flows is one more than the possible parallel number (M), the flow classification unit 734 randomly selects two flows from all the flows, sums the traffic volume values of the two selected flows, and generates one time-series traffic.
[0171] The flow classification unit 734 based on the number of parallel processes outputs the time-series traffic of the grouped flows and the value of the number of parallel processes (M) obtained from the number of parallel processes calculation unit 731 to the traffic prediction unit 732.
[0172] The traffic prediction unit 732 obtains the time-series traffic of the grouped flows and the value of the possible parallel number (M) output from the flow classification unit 734. The traffic prediction unit 732 predicts future traffic volume for each flow that has been adjusted by the flow classification unit 734 to be equal to the possible parallel number (M). The traffic prediction unit 732 outputs the values of the future traffic volumes (predicted traffic volumes) predicted for each of the M flows to the total traffic calculation unit 740.
[0173] 19 , the total traffic calculation unit 740 acquires the values of the predicted traffic volumes predicted by the traffic prediction unit 732 of the grouping prediction unit 730 c. The total traffic calculation unit 740 adds up the acquired predicted traffic volumes to obtain the value of the total traffic volume. The total traffic calculation unit 740 outputs the calculated value of the total traffic volume to the switching threshold determination unit 172.
[0174] The processing after the value of the total traffic volume is output from the total traffic calculation unit 740 of the prediction unit 171c to the switching threshold determination unit 172 (i.e., processing related to determining whether to perform route switching and processing related to controlling the implementation of route switching) is not described here because it is the same as the processing in the conventional communication system 1. In other words, the subsequent processing after the processing by the prediction unit 171c is the same as the processing related to the control of route switching by the switching threshold determination unit 172 and the switching determination unit 175 of the conventional communication system 1 described above with reference to Figures 9 to 12 and the like, and the processing related to route switching by the transfer device 15, and therefore not described here.
[0175] An example of the operation of the grouping prediction unit 730c will be described below. Fig. 21 is a flowchart showing the operation of the grouping prediction unit 730c in the communication system according to the third embodiment of the present invention. The operation of the grouping prediction unit 730c shown in the flowchart of Fig. 21 is started, for example, when information used by the parallelizable number calculation unit 731 (for example, information indicating a flow ID and traffic volume) is stored in the flow information storage unit 720.
[0176] The parallel number calculation unit 731 obtains information required for calculating future traffic volume (e.g., flow ID and information indicating traffic, etc.) from the flow information storage unit 720. The parallel number calculation unit 731 identifies the allowable delay (Delay_a) of each flow based on the flow ID. The parallel number calculation unit 731 obtains the value of the predicted time (Ti_pred) predicted by the traffic prediction unit 732. The parallel number calculation unit 731 calculates the parallel number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred). The predicted time (Ti_pred) may be the maximum predicted time or the average predicted time. The parallel number calculation unit 731 outputs the calculated value of the parallel number (M) to the flow classification unit 734 by parallel number.
[0177] The flow classification unit 734 based on the parallel number acquires the value of the possible parallel number (M) output from the possible parallel number calculation unit 731. The flow classification unit 734 based on the parallel number compares the acquired possible parallel number (M) with the actual number of flows (step S181).
[0178] If the number of flows is equal to or less than the number of parallel processes (M) (step S181, No), the flow classification unit 734 by parallel number does not need to perform any processing to reduce the number of flows to within the number of parallel processes, and therefore does not perform processing such as grouping multiple flows into one flow (step S184).
[0179] On the other hand, if the number of flows is greater than the number of parallel processes (M) (Yes in step S181), the flow classification unit 734 groups the flows so that the number of flows is equal to the number of parallel processes (step S182).
[0180] The flow classification unit 734 by parallel number adds up the values of the traffic volume of flows classified into the same group to generate time-series traffic (hereinafter referred to as "time-series traffic") (step S183). The generated time-series traffic is regarded as one flow. The flow classification unit 734 by parallel number outputs the time-series traffic of the grouped flows and the value of the parallel number (M) obtained from the parallel number calculation unit 731 to the traffic prediction unit 732.
[0181] This completes the operation of the grouping prediction unit 730c shown in the flowchart of FIG.
[0182] As described above, the switching instruction device 17c in the third embodiment of the present invention classifies each of the flows input from, for example, the lower-level device 3 during a predetermined period based on the characteristics of the traffic pattern (e.g., QoS) based on information defined in, for example, 5QI or S-NSSAI, etc. The switching instruction device 17c calculates the maximum number of flows that can be subjected to prediction processing in parallel within the range of the allowable delay based on the allowable delay and the predicted time.
[0183] If the number of classified flows is greater than the number of parallelizable flows, the switching instruction device 17c in the third embodiment groups the flows so that the number of flows is equal to the number of parallelizable flows, and calculates the future traffic volume for each group. The switching instruction device 17c adds up the predicted traffic volumes of the flows calculated for each group, and determines whether to perform path switching and controls its execution based on the calculated total traffic volume.
[0184] In this way, the switching instruction device 17c in the third embodiment of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel to fall within a range of the possible parallel number that enables the prediction process to be completed within the allowable time for route switching prediction. This allows the switching instruction device 17c to ensure that the prediction process is completed before the timing when route switching is necessary (i.e., the timing when congestion occurs).
[0185] Therefore, the switching instruction device 17c can improve communication quality by controlling route switching in advance based on the predicted traffic volume, and can prevent congestion and reduce communication delays by controlling the prediction process to be completed within the allowed time. In this way, the switching instruction device 17c in the third embodiment of the present invention can reduce communication delays while satisfying communication quality even when multiple flows are mixed.
[0186] <Fourth embodiment> A communication system according to a fourth embodiment of the present invention will now be described. Note that the overall configuration of the communication system according to this embodiment is similar to the configuration of the conventional communication system 1 shown in the overall configuration diagram of Fig. 1 described above, and therefore a description thereof will be omitted. Furthermore, the overall configuration of a mobile communication system in which the communication system according to this embodiment is applied to mobile communication is also similar to the configuration of the conventional mobile communication system 10 shown in the overall configuration diagram of Fig. 2 described above, and therefore a description thereof will be omitted.
[0187] Furthermore, the block diagram showing the functional configuration of the switching instruction device of the communication system in the fourth embodiment is the same as the block diagram showing the functional configuration of the switching instruction device 17 of the conventional communication system 1 shown in FIG. 3 described above. Hereinafter, the switching instruction device in the fourth embodiment will be referred to as switching instruction device 17d. The switching instruction device 17d is, for example, an information processing device such as a general-purpose computer. The switching instruction device 17d of this embodiment and the conventional switching instruction device 17 described above have different configurations of their prediction units. The configuration of the prediction unit 171d of the communication system in this embodiment will be described below.
[0188] 22 is a block diagram showing the functional configuration of a prediction unit 171d in a communication system according to the fourth embodiment of the present invention. As shown in FIG. 22, the prediction unit 171d includes a flow classification unit 710, a flow information storage unit 720, a grouping prediction unit 730d, and a total traffic calculation unit 740.
[0189] As in the first embodiment described above, the flow classification unit 710 classifies flows input to the network 5 during a predetermined period based on traffic characteristics. The flow classification unit 710 classifies flows by flow type based on information defined in, for example, 5QI or S-NSSAI. The flow classification unit 710 calculates the total number of terminals and traffic volume for each classified flow and stores them in a flow information table stored in the flow information storage unit 720.
[0190] The grouping prediction unit 730d adjusts the number of prediction processes to be executed in parallel so that it is within the possible parallel number, thereby suppressing the amount of calculation so that the time required for the prediction process falls within the allowable delay range, and predicts future traffic volume. The grouping prediction unit 730d outputs the predicted future traffic volume value to the total traffic calculation unit 740.
[0191] The configuration of the grouping prediction unit 730d will be described in more detail below. Fig. 23 is a block diagram showing the functional configuration of the grouping prediction unit 730d of the communication system according to the fourth embodiment of the present invention. As shown in Fig. 23, the grouping prediction unit 730d includes a traffic period calculation unit 733, a parallelizable number calculation unit 731, a flow classification unit 734 based on the parallel number, and a traffic prediction unit 732.
[0192] As shown in FIG. 23, the grouping prediction unit 730d in the fourth embodiment has a configuration in which a traffic period calculation unit 733 and a flow classification unit 734 based on the number of parallel processes are added to the grouping prediction unit 730 in the first embodiment described above.
[0193] The traffic period calculation unit 733 calculates the traffic period of each flow. The traffic period calculation unit 733 outputs the calculated traffic period value of each flow to the parallel number calculation unit 731d. The parallel number calculation unit 731d reflects the traffic period calculated by the traffic period calculation unit 733 in the predicted time. By reflecting the traffic period in the predicted time, the parallel number calculation unit 731d in the fourth embodiment can calculate the parallel number with higher accuracy than the parallel number calculation unit 731 in the first embodiment described above.
[0194] The traffic period calculation unit 733 identifies the traffic pattern of each flow based on, for example, 5QI or S-NSSAI. The traffic period calculation unit 733 calculates the traffic period for each flow based on the identified traffic pattern. Note that the traffic period calculation unit 733 may also calculate the traffic period for each flow based on spectral analysis of time-series traffic.
[0195] The parallelizable number calculation unit 731d identifies the allowable delay (Delay_a) for each flow based on the flow ID. The parallelizable number calculation unit 731d identifies the allowable delay (Delay_a) based on, for example, information related to 5QI or S-NSSAI stored in a storage medium (not shown) included in the prediction unit 171d. Note that the information related to 5QI or S-NSSAI may be stored in the flow information storage unit 720.
[0196] For example, when 5QI is used, the value of "PDB" can be used as the allowable delay value, and when S-NSSAI is used, the value of "Max allowed end-to-end latency" can be used. Note that, in the case of a flow ID that is not related to the allowable delay, for example, an arbitrary allowable delay value can be determined in advance. Alternatively, when S-NSSAI is used, a specified value set according to the service can be used. Note that in this case, the correspondence between the service and the allowable delay value is assumed to be determined in advance in a flow information table or the like.
[0197] The parallelizable number calculation unit 731d acquires the value of the traffic period (Ti_traffic) calculated by the traffic period calculation unit 733. The parallelizable number calculation unit 731d calculates a predicted time (Ti_pred) based on the traffic period (Ti_traffic) (number of input data) calculated by the traffic period calculation unit 733, the total processing load (Con_sum), and the processing load of the flow (Con), as shown in the following equation (9).
[0198] Ti_pred=Ti_traffic / Con_sum×Con…(9)
[0199] The parallelizable number calculation unit 731d calculates the parallelizable number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred), as shown in the following equation (10).
[0200] M=Delay_a / Ti_pred...(10)
[0201] The number of input data (traffic cycle) differs for each flow, and the predicted time differs depending on the number of input data, so the predicted time (Ti_pred) may be the maximum predicted time or the average predicted time. The parallel number calculation unit 731d outputs the calculated value of the parallel number (M) to the flow classification unit 734 by parallel number.
[0202] The flow classification unit 734 by parallel number acquires the value of the possible parallel number (M) output from the possible parallel number calculation unit 731d. The flow classification unit 734 by parallel number acquires the acquired possible parallel number (M) and compares it with the actual number of flows.
[0203] When the number of flows is equal to or less than the parallel number (M), even if the process of predicting future traffic volume for all flows is executed in parallel, the prediction process will be completed within the allowable time. Therefore, when the number of flows is equal to or less than the parallel number (M), the flow classification unit 734 by parallel number does not need to perform the process of keeping the number of flows within the parallel number, and therefore does not perform the process of selecting only some of the flows from all the flows or the process of grouping multiple flows into one flow.
[0204] On the other hand, if the number of flows is greater than the number of parallelizable flows (M), executing the future traffic volume prediction process for all flows in parallel will prevent the prediction process from completing within the allowable time. This will cause congestion and communication delays. Therefore, if the number of flows is greater than the number of parallelizable flows (M), the flow classification unit 734 classifies the flows into groups so that the number of flows is equal to the number of parallelizable flows.
[0205] The grouping prediction unit 730 in the first embodiment and the grouping prediction unit 730b in the second embodiment described above were configured to select a portion of flows (i.e., the number of flows that can be processed in parallel (M)) from all of the flows classified by the flow classification unit 710 when the number of flows is greater than the number of flows that can be processed in parallel (M), and to perform prediction processing of future traffic volume only for the selected flows.
[0206] In contrast, when the number of flows is greater than the parallelizable number (M), the grouping prediction unit 730d in the fourth embodiment groups all of the flows classified by the flow classification unit 710 so that the number of flows is the same as the parallelizable number, and performs prediction processing for future traffic volume on a group-by-group basis. Therefore, the grouping prediction unit 730d in the fourth embodiment performs prediction processing for all of the flows classified by the flow classification unit 710, and is therefore considered to be able to predict future traffic volume with higher accuracy than the grouping prediction unit 730 in the first embodiment and the grouping prediction unit 730b in the second embodiment described above.
[0207] Any method can be used for the grouping (classification) of flows by the parallel number-based flow classification unit 734. The parallel number-based flow classification unit 734 sums the traffic volume values of flows classified into the same group to generate time-series traffic. The generated time-series traffic is regarded as one flow.
[0208] For example, if the actual number of flows is one more than the possible parallel number (M), the flow classification unit 734 randomly selects two flows from all the flows, sums the traffic volume values of the two selected flows, and generates one time-series traffic.
[0209] The flow classification unit 734 based on the number of parallel processes outputs the time-series traffic of the grouped flows and the value of the number of parallel processes (M) obtained from the number of parallel processes calculation unit 731 to the traffic prediction unit 732.
[0210] The traffic prediction unit 732 obtains the time-series traffic of the grouped flows and the value of the possible parallel number (M) output from the flow classification unit 734. The traffic prediction unit 732 predicts future traffic volume for each flow that has been adjusted by the flow classification unit 734 to be equal to the possible parallel number (M). The traffic prediction unit 732 outputs the values of the future traffic volumes (predicted traffic volumes) predicted for each of the M flows to the total traffic calculation unit 740.
[0211] 22 , the total traffic calculation unit 740 acquires the values of the predicted traffic volumes predicted by the traffic prediction unit 732 of the grouping prediction unit 730c. The total traffic calculation unit 740 adds up the acquired predicted traffic volumes to obtain the value of the total traffic volume. The total traffic calculation unit 740 outputs the calculated value of the total traffic volume to the switching threshold determination unit 172.
[0212] The processing after the value of the total traffic volume is output from the total traffic calculation unit 740 of the prediction unit 171d to the switching threshold determination unit 172 (i.e., processing related to determining whether to perform route switching and processing related to controlling the implementation of route switching) is not described here because it is the same as the processing in the conventional communication system 1. In other words, the subsequent processing after the processing by the prediction unit 171d is the same as the processing related to the control of route switching by the switching threshold determination unit 172 and the switching determination unit 175 of the conventional communication system 1 described with reference to the above-mentioned Figures 9 to 12, and the processing related to route switching by the transfer device 15, and therefore not described here.
[0213] An example of the operation of the grouping prediction unit 730d will be described below. Fig. 24 is a flowchart showing the operation of the grouping prediction unit 730d in the communication system according to the fourth embodiment of the present invention. The operation of the grouping prediction unit 730d shown in the flowchart of Fig. 24 is started, for example, when information used by the traffic periodicity calculation unit 733 (e.g., information indicating the flow type) and information used by the possible parallel number calculation unit 731 (e.g., information indicating the traffic volume) are stored in the flow information storage unit 720.
[0214] The traffic period calculation unit 733 obtains information (e.g., flow type, etc.) required for calculating future traffic volume from the flow information storage unit 720. The traffic period calculation unit 733 identifies the traffic pattern of each flow based on, for example, 5QI or S-NSSAI. The traffic period calculation unit 733 calculates the traffic period for each flow based on the identified traffic pattern. The traffic period calculation unit 733 outputs the calculated value of the traffic period for each flow to the parallelizable number calculation unit 731d.
[0215] The parallelizable number calculation unit 731d acquires information required for calculating future traffic volume (e.g., information indicating traffic) from the flow information storage unit 720. The parallelizable number calculation unit 731d identifies the allowable delay (Delay_a) based on, for example, information related to 5QI or S-NSSAI stored in a storage medium (not shown) included in the prediction unit 171d.
[0216] The parallelizable number calculation unit 731d also acquires the value of the traffic cycle (Ti_traffic) for each flow calculated by the traffic cycle calculation unit 733. The parallelizable number calculation unit 731d calculates a predicted time (Ti_pred) based on the traffic cycle (Ti_traffic) (number of input data) calculated by the traffic cycle calculation unit 733, the total processing load (Con_sum), and the processing load (Con) of the flow.
[0217] The parallel number calculation unit 731d then calculates the parallel number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred). The parallel number calculation unit 731d outputs the calculated parallel number (M) to the parallel number-based flow classification unit 734.
[0218] The flow classification unit 734 based on the parallel number acquires the value of the possible parallel number (M) output from the possible parallel number calculation unit 731. The flow classification unit 734 based on the parallel number compares the acquired possible parallel number (M) with the actual number of flows (step S191).
[0219] If the number of flows is equal to or less than the number of parallel processes (M) (step S191, No), the flow classification unit 734 by parallel number does not need to perform any processing to reduce the number of flows to within the number of parallel processes, and therefore does not perform processing such as grouping multiple flows into one flow (step S195).
[0220] On the other hand, if the number of flows is greater than the possible parallel number (M) (step S191: Yes), the flow classification unit 734 classifies the flows into groups so that the number of flows is equal to the possible parallel number. Specifically, the flow classification unit 734 classifies the flows into groups so that the number of input data is small (i.e., the traffic cycle is short) in order to group the flows in a way that reduces the amount of calculation required for predicting future traffic volume.
[0221] First, the flow classification unit 734 calculates the greatest common divisor of the values of the number of pieces of input data (traffic cycles) for each flow. Next, the flow classification unit 734 calculates the least common multiple that satisfies the calculated greatest common divisor (step S192).
[0222] Next, since the process of step S192 alone may not be enough to reduce the number of flows to within the possible number of parallel connections, the flow classification unit 734 calculates a set of least common multiples from the plurality of least common multiples calculated above to reduce the number of flows to within the possible number of parallel connections (step S193). The flow classification unit 734 classifies the flows into groups, with each set of least common multiples of the calculated number of input data (traffic cycles) forming one group. The operations of steps S192 to S193 performed by the flow classification unit 734 by the number of parallel connections will be described in more detail later with specific examples.
[0223] The flow classification unit 734 by parallel number adds up the values of the traffic volume of flows classified into the same group to generate time-series traffic (step S194). The generated time-series traffic is regarded as one flow. The flow classification unit 734 by parallel number outputs the time-series traffic of the grouped flows and the value of the parallel number (M) obtained from the parallel number calculation unit 731 to the traffic prediction unit 732.
[0224] This completes the operation of the grouping prediction unit 730d shown in the flowchart of FIG.
[0225] The processing of steps S192 to S193 in the flowchart shown in Fig. 24 will be described in detail below, using specific numerical values. Fig. 25 is a flowchart showing the operation of the grouping prediction unit 730d of the communication system according to the fourth embodiment of the present invention.
[0226] The flow classification unit 734 by parallel number identifies flows with a relatively large amount of calculation in the prediction process of future traffic volume based on the traffic period and the parallel number for each flow, and groups the flows so that the traffic period is minimized according to the parallel number.The flow classification unit 734 by parallel number then sums the predicted traffic volume for each group to generate time-series traffic for each group, and outputs the generated time-series traffic to the traffic prediction unit 732.
[0227] If the number of flows is greater than the number of parallel processes (M) (Yes in step S191), the flow classification unit 734 classifies the flows into groups so that the number of flows is equal to the number of parallel processes. Specifically, the flow classification unit 734 first calculates the greatest common divisor of the number of input data (traffic cycle) values for each flow. Next, the flow classification unit 734 lists the least common multiple that satisfies the calculated greatest common divisor (step S192).
[0228] Here, as an example, the number of flows is assumed to be seven, and the number of flows that can be processed in parallel is assumed to be three (M=3). Furthermore, the traffic periods (number of input data items) of these seven flows are assumed to be 8, 11, 18, 25, 32, 48, and 56, respectively.
[0229] The flow classification unit 734 based on the number of parallel flows first performs prime factorization on the value of the traffic cycle of each flow as follows (step S192a).
[0230] 8 = 2 3 11 = 11 18 = 2 x 3 2 25 = 5 2 32 = 2 5 48 = 2 4 ×3 56 = 2 3 x7
[0231] The flow classification unit 734 by parallel number calculates the greatest common divisor of the traffic period values of the flows based on the result of the prime factorization. The greatest common divisor calculated by the flow classification unit 734 by parallel number is, for example, as follows:
[0232] Greatest common factor: 16 (32, 48), 8 (8, 56 = 8 x 7, 32, 48), 6 (18 = 6 x 3, 48), none (25, 11)
[0233] The flow classification unit 734 by parallel number calculates and lists the least common multiples of the traffic periods in descending order of the greatest common divisors among the calculated greatest common divisors (step S192b). The least common multiples listed by the flow classification unit 734 by parallel number are, for example, as follows:
[0234] Least common multiple: 96 (32, 48), 56 (8, 56 = 8 x 7), 18 (18 = 6 x 3), 25, 11
[0235] Simply performing the processing of step S192 above may not reduce the number of flows to within the number that can be parallelized. In the above specific example, if the least common multiple listed is used as the traffic period of each of the grouped flows, the least common multiple listed is five, so at this point the number of flows has been narrowed down from the initial seven to five. However, at this point the number of flows is still greater than the number that can be parallelized (three).
[0236] In this case, the flow classification unit 734 by parallel number calculates a set of least common multiples from the plurality of least common multiples listed above that will keep the number of flows within the number of parallelizable flows. The flow classification unit 734 by parallel number classifies the flows into groups, with each set of least common multiples of the calculated numbers of input data (traffic periods) being one group.
[0237] For example, in order to make the number of flows equal to the number of parallelizable flows (three), the flow classification unit 734 multiplies the relatively smallest of the least common multiples listed above to calculate a set of minimum numbers (step S193). The set of least common multiples calculated by the flow classification unit 734 by the number of parallelizable flows is, for example, as follows:
[0238] 288 (32, 48, 18), 56 (8, 56), 275
[0239] The traffic volume values of flows classified into the same group are summed up to generate time-series traffic. The flow classification unit 734 by parallel number groups flows according to the traffic period (number of input data), and generates time-series traffic by summing up the traffic volumes of flows belonging to the same group (step S194). The generated time-series traffic is regarded as one flow. For example, the time-series traffic generated by the flow classification unit 734 by parallel number is as follows:
[0240] Traffic_pred1=Traffic_32+Traffic_48+Traffic_18 Traffic_pred2=Traffic_8+Traffic_56 Traffic_pred3=Traffic_25+Traffic_11
[0241] For example, the predicted traffic volume (Traffic_pred1) of the first grouped flow is the sum of the traffic volume of the flow with a traffic period of 32, the traffic volume of the flow with a traffic period of 48, and the traffic volume of the flow with a traffic period of 18, as described above.
[0242] The flow classification unit 734 based on the number of parallel processes outputs the time-series traffic of the grouped flows and the value of the number of parallel processes (M) obtained from the number of parallel processes calculation unit 731 to the traffic prediction unit 732.
[0243] As described above, the switching instruction device 17d in the fourth embodiment of the present invention classifies each of the flows input from, for example, the lower-level device 3 during a predetermined period based on the characteristics of the traffic pattern (e.g., QoS) based on information defined in, for example, 5QI or S-NSSAI, etc. Based on the allowable delay and the predicted time, the switching instruction device 17d calculates the parallelizable number, which is the maximum number of flows that can be subjected to prediction processing in parallel within the allowable delay range.
[0244] Unlike the switching instruction device 17a in the first embodiment and the switching instruction device 17c in the third embodiment, the switching instruction device 17d in the fourth embodiment calculates the traffic period of each flow and reflects the calculated traffic period in the predicted time. This allows the switching instruction device 17d in the fourth embodiment to calculate the possible parallel number with higher accuracy than the switching instruction device 17a in the first embodiment and the switching instruction device 17c in the third embodiment.
[0245] If the number of classified flows is greater than the number of parallelizable flows, the switching instruction device 17d in the fourth embodiment groups the flows so that the number of flows is equal to the number of parallelizable flows, and calculates the future traffic volume for each group. The switching instruction device 17d adds up the predicted traffic volumes of the flows calculated for each group, and determines whether to perform path switching and controls its execution based on the calculated total traffic volume.
[0246] In this way, the switching instruction device 17d in the fourth embodiment of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel to fall within a range of the possible parallel number that enables the prediction process to be completed within the allowable time for route switching prediction. This allows the switching instruction device 17d to ensure that the prediction process is completed before the timing when route switching is necessary (i.e., the timing when congestion occurs).
[0247] Therefore, the switching instruction device 17d can improve communication quality by controlling route switching in advance based on the predicted traffic volume, and can prevent congestion and reduce communication delays by controlling the prediction process to be completed within the allowed time. In this way, the switching instruction device 17d in the fourth embodiment of the present invention can reduce communication delays while satisfying communication quality even when multiple flows are mixed.
[0248] <Fifth Embodiment> A communication system according to a fifth embodiment of the present invention will now be described. Note that the overall configuration of the communication system according to this embodiment is similar to the configuration of the conventional communication system 1 shown in the overall configuration diagram of Fig. 1 described above, and therefore a description thereof will be omitted. Furthermore, the overall configuration of a mobile communication system in which the communication system according to this embodiment is applied to mobile communication is also similar to the configuration of the conventional mobile communication system 10 shown in the overall configuration diagram of Fig. 2 described above, and therefore a description thereof will be omitted.
[0249] Furthermore, the block diagram showing the functional configuration of the switching instruction device of the communication system in the fifth embodiment is the same as the block diagram showing the functional configuration of the switching instruction device 17 of the conventional communication system 1 shown in FIG. 3 described above. Hereinafter, the switching instruction device in the fifth embodiment will be referred to as switching instruction device 17e. The switching instruction device 17e is, for example, an information processing device such as a general-purpose computer. The switching instruction device 17e of this embodiment and the conventional switching instruction device 17 described above have different configurations of their prediction units. The configuration of the prediction unit 17e of the communication system in this embodiment will be described below.
[0250] 26 is a block diagram showing the functional configuration of a prediction unit 171e of a communication system according to the fifth embodiment of the present invention. As shown in Fig. 26, the prediction unit 171e includes a flow classification unit 710, a flow information storage unit 720, a grouping prediction unit 730e, and a total traffic calculation unit 740.
[0251] As in the first embodiment described above, the flow classification unit 710 classifies flows input to the network 5 during a predetermined period based on traffic characteristics. The flow classification unit 710 classifies flows by flow type based on information defined in, for example, 5QI or S-NSSAI. The flow classification unit 710 calculates the total number of terminals and traffic volume for each classified flow and stores them in a flow information table stored in the flow information storage unit 720.
[0252] The grouping prediction unit 730e predicts future traffic volume by adjusting the number of prediction processes to be executed in parallel so that it is within the possible parallel number, thereby suppressing the amount of calculation so that the time required for the prediction process falls within the allowable delay range. The grouping prediction unit 730e outputs the predicted value of future traffic volume to the total traffic calculation unit 740.
[0253] The configuration of the grouping prediction unit 730e will be described in more detail below. Fig. 27 is a block diagram showing the functional configuration of the grouping prediction unit 730e of the communication system according to the fifth embodiment of the present invention. As shown in Fig. 27, the grouping prediction unit 730e includes a parallelizable number calculation unit 731, a flow classification unit 734 based on parallel numbers, and a traffic prediction unit 732.
[0254] As shown in Fig. 27, the grouping prediction unit 730e in the fifth embodiment has a configuration in which the parallel number-based flow classification unit 734 in the grouping prediction unit 730c in the third embodiment shown in Fig. 20 has been replaced with a parallel number-based flow classification unit 734e. However, the configuration is not limited to this, and for example, the grouping prediction unit 730e in the fifth embodiment may have a configuration in which the parallel number-based flow classification unit 734 in the grouping prediction unit 730d in the fourth embodiment shown in Fig. 23 has been replaced with a parallel number-based flow classification unit 734e.
[0255] The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) for each flow based on the flow ID. The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) based on, for example, information about 5QI or S-NSSAI stored in a storage medium (not shown) included in the prediction unit 171e. Note that the information about 5QI or S-NSSAI may be stored in the flow information storage unit 720.
[0256] For example, when 5QI is used, the value of "PDB" can be used as the allowable delay value, and when S-NSSAI is used, the value of "Max allowed end-to-end latency" can be used. Note that, in the case of a flow ID that is not related to the allowable delay, for example, an arbitrary allowable delay value can be determined in advance. Alternatively, when S-NSSAI is used, a specified value set according to the service can be used. Note that in this case, the correspondence between the service and the allowable delay value is assumed to be determined in advance in a flow information table or the like.
[0257] The parallel number calculation unit 731 obtains the value of the predicted time (Ti_pred) predicted by the traffic prediction unit 732. The parallel number calculation unit 731 calculates the parallel number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred), as shown in the following equation (11).
[0258] M=Delay_a / Ti_pred...(11)
[0259] Since the predicted time differs for each flow depending on the number of input data (traffic cycle), the predicted time (Ti_pred) may be the maximum predicted time or the average predicted time. The parallel number calculation unit 731 outputs the calculated value of the parallel number (M) to the flow classification unit 734e.
[0260] The flow classification unit 734e based on the parallel number obtains the value of the possible parallel number (M) output from the possible parallel number calculation unit 731. The flow classification unit 734e based on the parallel number compares the obtained possible parallel number (M) with the actual number of flows.
[0261] When the number of flows is equal to or less than the parallel number (M), even if the process of predicting future traffic volume for all flows is executed in parallel, the prediction process will be completed within the allowable time. Therefore, when the number of flows is equal to or less than the parallel number (M), the flow classification unit 734e by parallel number does not need to perform the process of reducing the number of flows to within the parallel number, and therefore does not perform the process of selecting only some of the flows from all the flows or the process of grouping multiple flows into one flow.
[0262] On the other hand, if the number of flows is greater than the number of parallel connections (M), executing the future traffic volume prediction process for all flows in parallel will prevent the prediction process from completing within the allowable time. This will cause congestion and communication delays. Therefore, if the number of flows is greater than the number of parallel connections (M), the flow classification unit 734e classifies the flows into groups so that the number of flows is equal to the number of parallel connections.
[0263] The grouping prediction unit 730 in the first embodiment and the grouping prediction unit 730b in the second embodiment described above were configured to select a portion of flows (i.e., the number of flows that can be processed in parallel (M)) from all of the flows classified by the flow classification unit 710 when the number of flows is greater than the number of flows that can be processed in parallel (M), and to perform prediction processing of future traffic volume only for the selected flows.
[0264] Furthermore, when the number of flows is greater than the number of flows that can be parallelized (M), the grouping prediction unit 730c in the third embodiment and the grouping prediction unit 730d in the fourth embodiment are configured to group all flows classified by the flow classification unit 710 so that the number of flows is equal to the number of flows that can be parallelized, and to perform prediction processing of future traffic volume on a group-by-group basis.
[0265] In contrast, when the number of flows is greater than the number of parallelizable flows (M), the grouping prediction unit 730e in the fifth embodiment lists the traffic volume for each flow for all flows classified by the flow classification unit 710. The grouping prediction unit 730e then selects flows equal in number to the number of parallelizable flows (M) in descending order of traffic volume, and performs prediction processing of future traffic volumes only for the selected flows.
[0266] If the number of flows is greater than the maximum number of parallel connections (M), the flow classification unit 734e by parallel number lists the traffic volume for each flow for all flows classified by the flow classification unit 710. Then, the flow classification unit 734e by parallel number selects flows in descending order of traffic volume, the number of which is equal to the maximum number of parallel connections (M).
[0267] The traffic prediction unit 732 performs a process of predicting future traffic volumes only for flows selected by the flow classification unit 734e based on parallelism. For flows not selected by the flow classification unit 734e based on parallelism, the traffic prediction unit 732 does not perform a process of predicting future traffic volumes, and instead regards the current traffic volume as the future traffic volume (predicted traffic volume). However, this configuration is not limited to this. For flows not selected by the flow classification unit 734e based on parallelism, the traffic volume for the immediately preceding period may be regarded as the future traffic volume (predicted traffic volume) (for example, when the current traffic volume cannot be obtained in time).
[0268] In this embodiment, flows not selected by the parallel flow classification unit 734e are flows with relatively small traffic volumes, and therefore can be said to be flows with a relatively small impact on the prediction of future overall traffic volumes. In other words, the grouping prediction unit 730c in this embodiment is configured to prioritize flows that will have a greater impact on the prediction of future overall traffic volumes as the targets of prediction processing.
[0269] The traffic volume listed for each flow by the parallel flow classification unit 734e may be, for example, the current traffic volume, the average traffic volume within a specified period, or the maximum traffic volume within a specified period.
[0270] The flow classification unit 734e by parallel number adds up the values of the traffic volume of flows classified into the same group to generate time-series traffic. The generated time-series traffic is regarded as one flow. The flow classification unit 734 by parallel number outputs the time-series traffic of the grouped flows and the value of the parallel number (M) obtained from the parallel number calculation unit 731 to the traffic prediction unit 732.
[0271] The traffic prediction unit 732 obtains the time-series traffic of the grouped flows output from the flow classification unit 734e by the parallel number, and the value of the possible parallel number (M). The traffic prediction unit 732 predicts future traffic volume for each flow that has been adjusted by the flow classification unit 734 by the parallel number so that the number is equal to the possible parallel number (M). The traffic prediction unit 732 outputs the values of the future traffic volume (predicted traffic volume) predicted for each of the M flows to the total traffic calculation unit 740.
[0272] 26 , the total traffic calculation unit 740 acquires the values of the predicted traffic volumes predicted by the traffic prediction unit 732 of the grouping prediction unit 730 e. The total traffic calculation unit 740 adds up the acquired predicted traffic volumes to obtain the value of the total traffic volume. The total traffic calculation unit 740 outputs the calculated value of the total traffic volume to the switching threshold determination unit 172.
[0273] The processing after the value of the total traffic volume is output from the total traffic calculation unit 740 of the prediction unit 171e to the switching threshold determination unit 172 (i.e., processing related to determining whether to perform route switching and processing related to controlling the implementation of route switching) is not described here because it is the same as the processing in the conventional communication system 1. In other words, the subsequent processing after the processing by the prediction unit 171e is the same as the processing related to the control of route switching by the switching threshold determination unit 172 and the switching determination unit 175 of the conventional communication system 1 described with reference to the above-mentioned Figures 9 to 12, and the processing related to route switching by the transfer device 15, and therefore not described here.
[0274] An example of the operation of the grouping prediction unit 730e will be described below. Fig. 28 is a flowchart showing the operation of the grouping prediction unit 730e in the communication system according to the fifth embodiment of the present invention. The operation of the grouping prediction unit 730e shown in the flowchart of Fig. 28 is started, for example, when information used by the parallelizable number calculation unit 731 (for example, information indicating a flow ID and traffic volume) is stored in the flow information storage unit 720.
[0275] The parallel number calculation unit 731 obtains information required for calculating future traffic volume (e.g., flow ID and information indicating traffic, etc.) from the flow information storage unit 720. The parallel number calculation unit 731 identifies the allowable delay (Delay_a) of each flow based on the flow ID. The parallel number calculation unit 731 obtains the value of the predicted time (Ti_pred) predicted by the traffic prediction unit 732. The parallel number calculation unit 731 calculates the parallel number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred). The predicted time (Ti_pred) may be the maximum predicted time or the average predicted time. The parallel number calculation unit 731 outputs the calculated value of the parallel number (M) to the flow classification unit 734e based on the parallel number.
[0276] The flow classification unit 734e based on the parallel number obtains the value of the possible parallel number (M) output from the possible parallel number calculation unit 731. The flow classification unit 734 based on the parallel number compares the obtained possible parallel number (M) with the actual number of flows (step S201).
[0277] If the number of flows is equal to or less than the number of parallel processes (M) (step S201, No), the flow classification unit 734e by parallel number does not need to perform any processing to reduce the number of flows to within the number of parallel processes, and therefore does not perform any processing such as grouping multiple flows into one flow (step S204).
[0278] On the other hand, if the number of flows is greater than the number of parallel processes (M) (Yes in step S201), the flow classification unit 734e groups the flows so that the number of flows is equal to the number of parallel processes. If the number of flows is greater than the number of parallel processes (M), the grouping prediction unit 730e lists the traffic volume for each flow for all flows classified by the flow classification unit 710 (step S202).
[0279] Here, as an example, the number of flows is assumed to be three, and the number of flows that can be processed in parallel is assumed to be two (M=2). Furthermore, the traffic volumes of these three flows are assumed to be as follows, as shown in FIG.
[0280] Flow 1: [200, 200, 0, 0] Flow 2: [1000, 0, 0, 1000] Flow 5: [500, 500, 1000, 1000]
[0281] The flow classification unit 734e by parallel number selects the same number of flows as the possible parallel number (M) in descending order of traffic volume (step S203). Here, the flow classification unit 734e by parallel number selects the same number of flows as the possible parallel number (M) in descending order of maximum traffic volume within a predetermined period. As shown in FIG. 28 , the maximum traffic volume of flow 1 is 200, and the maximum traffic volumes of flows 2 and 5 are 1000, so the flow classification unit 734e by parallel number selects two flows, flow 2 and flow 5. The flow classification unit 734e by parallel number outputs information indicating the selected flows and the time-series traffic of each flow to the traffic prediction unit 732.
[0282] The traffic prediction unit 732 acquires information indicating the selected flows output from the flow classification unit 734 by parallel number and the time-series traffic of each flow. The traffic prediction unit 732 performs a prediction process of future traffic volume only for flows selected by the flow classification unit 734e by parallel number. Note that for flows not selected by the flow classification unit 734e by parallel number, the traffic prediction process is not performed, and the current traffic volume is regarded as the future traffic volume (predicted traffic volume). The traffic prediction unit 732 outputs the values of the future traffic volumes (predicted traffic volumes) predicted for each of the M flows to the total traffic calculation unit 740.
[0283] This completes the operation of the grouping prediction unit 730e shown in the flowchart of FIG.
[0284] As described above, the switching instruction device 17e in the fifth embodiment of the present invention classifies each of the flows input from, for example, the lower-level device 3 during a predetermined period based on the characteristics of the traffic pattern (for example, QoS) based on information defined in, for example, 5QI or S-NSSAI, etc. The switching instruction device 17c calculates the maximum number of flows that can be subjected to prediction processing in parallel within the range of the allowable delay based on the allowable delay and the predicted time.
[0285] If the number of classified flows is greater than the number of possible parallel flows, the switching instruction device 17e in the fifth embodiment selects a number of flows equal to the number of possible parallel flows (M) in descending order of traffic volume. The switching instruction device 17e performs a process of predicting future traffic volumes only for the selected flows. Flows not selected by the flow classification unit 734e based on the number of parallel flows have relatively low traffic volumes, and therefore can be said to have a relatively small impact on the prediction of the overall future traffic volume. In other words, the switching instruction device 17e in the fifth embodiment is configured to prioritize flows that have a greater impact on the prediction of the overall future traffic volume as the target of the prediction process.
[0286] Furthermore, the switching instruction device 17e in the fifth embodiment does not perform a process of predicting future traffic volume for non-selected flows, but regards the current traffic volume as the future traffic volume (predicted traffic volume).The switching instruction device 17e then adds up the predicted traffic volumes of the selected flow and the non-selected flow, and determines whether to perform route switching and controls its execution based on the calculated total traffic volume.
[0287] In this way, the switching instruction device 17e in the fifth embodiment of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel to fall within a range of the possible parallel number that enables the prediction process to be completed within the allowable time for route switching prediction. This allows the switching instruction device 17e to ensure that the prediction process is completed before the timing when route switching is required (i.e., the timing when congestion occurs).
[0288] Therefore, the switching instruction device 17e can improve communication quality by controlling route switching in advance based on the predicted traffic volume, and can prevent congestion and reduce communication delays by controlling the prediction process to be completed within the allowed time. In this way, the switching instruction device 17e in the fifth embodiment of the present invention can reduce communication delays while satisfying communication quality even when multiple flows are mixed.
[0289] <Sixth Embodiment> A communication system according to a sixth embodiment of the present invention will now be described. Note that the overall configuration of the communication system according to this embodiment is similar to the configuration of the conventional communication system 1 shown in the overall configuration diagram of Fig. 1 described above, and therefore a description thereof will be omitted. Furthermore, the overall configuration of a mobile communication system in which the communication system according to this embodiment is applied to mobile communication is also similar to the configuration of the conventional mobile communication system 10 shown in the overall configuration diagram of Fig. 2 described above, and therefore a description thereof will be omitted.
[0290] Furthermore, the block diagram showing the functional configuration of the switching instruction device of the communication system in the sixth embodiment is the same as the block diagram showing the functional configuration of the switching instruction device 17 of the conventional communication system 1 shown in FIG. 3 described above. Hereinafter, the switching instruction device in the sixth embodiment will be referred to as switching instruction device 17f. The switching instruction device 17f is, for example, an information processing device such as a general-purpose computer. The switching instruction device 17f of this embodiment and the conventional switching instruction device 17 described above have different configurations of their prediction units. The configuration of the prediction unit 171f of the communication system in this embodiment will be described below.
[0291] 29 is a block diagram showing the functional configuration of a prediction unit 171f of a communication system according to the sixth embodiment of the present invention. As shown in Fig. 29, the prediction unit 171f includes a flow classification unit 710, a flow information storage unit 720, a grouping prediction unit 730f, and a total traffic calculation unit 740.
[0292] As in the first embodiment described above, the flow classification unit 710 classifies flows input to the network 5 during a predetermined period based on traffic characteristics. The flow classification unit 710 classifies flows by flow type based on information defined in, for example, 5QI or S-NSSAI. The flow classification unit 710 calculates the total number of terminals and traffic volume for each classified flow and stores them in a flow information table stored in the flow information storage unit 720.
[0293] The grouping prediction unit 730f adjusts the number of prediction processes to be executed in parallel so that it is within the possible parallel number, thereby suppressing the amount of calculation so that the time required for the prediction process falls within the allowable delay range, and predicts future traffic volume. The grouping prediction unit 730e outputs the predicted value of future traffic volume to the total traffic calculation unit 740.
[0294] The configuration of the grouping prediction unit 730f will be described in more detail below. The grouping prediction units in the first to fifth embodiments described above are configured to calculate the possible parallel number based on the allowable delay and the predicted time, so that the predicted time falls within the allowable delay range. In contrast, the grouping prediction unit 730f in the sixth embodiment described below is configured to calculate the possible parallel number so that the calculation load in the prediction process falls within the range of the available resource amount.
[0295] 30 is a block diagram showing the functional configuration of a grouping prediction unit 730f of a communication system according to the sixth embodiment of the present invention. As shown in Fig. 30, the grouping prediction unit 730f includes a parallelizable number calculation unit 731f and a traffic prediction unit 732f.
[0296] 30 , the grouping prediction unit 730f in the sixth embodiment has a configuration in which the parallelizable number calculation unit 731 is replaced with a parallelizable number calculation unit 731f in the grouping prediction unit 730 in the first embodiment shown in FIG. 16 described above. However, the present invention is not limited to this configuration, and it is also possible to use a configuration in which the parallelizable number calculation unit in each of the above-described embodiments is replaced with the parallelizable number calculation unit 731f in the sixth embodiment described below. That is, in the first to fifth embodiments described above, instead of a configuration in which a parallelizable number is calculated so that the predicted time falls within the allowable delay range, a configuration in which a parallelizable number is calculated so that the calculation load in the prediction process falls within the range of the available resource amount can be used.
[0297] The parallelizable number calculation unit 731f acquires the value of the resource amount (Re) from, for example, a controller of a higher-level device, etc. Alternatively, the value of the resource amount (Re) is assumed to be known.
[0298] The parallelizable number calculation unit 731f acquires information indicating the calculation load per prediction (Lo_pred) (hereinafter simply referred to as "calculation load") measured by the traffic prediction unit 732f. The parallelizable number calculation unit 731f calculates the parallelizable number (M) based on the current resource amount (Re_pred) and the past calculation load (Lo_pred), as shown in the following formula (12).
[0299] M=Re_pred / Lo_pred…(12)
[0300] Alternatively, the parallel number calculation unit 731f may calculate the parallel number (M) based on the past total calculation load (Lo_old) measured by the traffic prediction unit 732f and the past parallel number (M_old), as shown in the following equation (13):
[0301] M=Re_pred / Lo_old×M_old…(13)
[0302] The traffic prediction unit 732f obtains the value of the parallel number (M) output from the parallel number calculation unit 731f. The traffic prediction unit 732f narrows down the number of flows so that it falls within the parallel number (M) and predicts future traffic volume (predicted traffic volume). In this embodiment, the traffic prediction unit 732f narrows down the number of flows to be subjected to prediction processing, for example, by randomly selecting M flows from all of the classified flows.
[0303] The number of selected flows may be any number up to M. However, since the accuracy of predicting future traffic volume decreases as the number of selected flows decreases, it is desirable that the number of selected flows be M, which is the maximum number of flows that can be predicted in parallel within the allowable time (i.e., the number that can be parallelized).
[0304] In this embodiment, the traffic prediction unit 732 is configured to randomly select M flows, but the present invention is not limited to this configuration. The traffic prediction unit 732 may be configured to select M flows according to any rule.
[0305] The traffic prediction unit 732f predicts future traffic volumes for the selected M flows. The traffic prediction unit 732 outputs the values of the future traffic volumes (predicted traffic volumes) predicted for each of the M flows to the total traffic calculation unit 740.
[0306] 29 , the total traffic calculation unit 740 acquires the value of the predicted traffic volume for each of the M flows predicted by the traffic prediction unit 732f of the grouping prediction unit 730f. The total traffic calculation unit 740 adds up the acquired predicted traffic volumes to obtain the value of the total traffic volume. The total traffic calculation unit 740 outputs the calculated value of the total traffic volume to the switching threshold determination unit 172.
[0307] The processing after the value of the total traffic volume is output from the total traffic calculation unit 740 of the prediction unit 171f to the switching threshold determination unit 172 (i.e., processing related to determining whether to perform route switching and processing related to controlling the implementation of route switching) is not described here because it is the same as the processing in the conventional communication system 1. In other words, the subsequent processing after the processing by the prediction unit 171f is the same as the processing related to the control of route switching by the switching threshold determination unit 172 and the switching determination unit 175 of the conventional communication system 1 described with reference to the above-mentioned Figures 9 to 12, and the processing related to route switching by the transfer device 15, and therefore not described here.
[0308] As described above, the switching instruction device 17f in the sixth embodiment of the present invention classifies each of the flows input from, for example, a lower-level device 3 during a predetermined period based on traffic pattern (e.g., QoS) characteristics based on information defined in, for example, 5QI or S-NSSAI. Based on the amount of resources available for processing in the prediction process and the computational load, the switching instruction device 17f calculates the maximum number of flows that can be processed in parallel under a computational load within the range of the amount of resources available for processing. The switching instruction device 17f randomly selects M flows from all of the classified flows input during the predetermined period and calculates future traffic volumes (predicted traffic volumes) for each of the selected M flows. The switching instruction device 17f adds up the predicted traffic volumes calculated for each selected flow and determines whether to perform path switching and controls its execution based on the total traffic volume.
[0309] In this way, the switching instruction device 17f in the sixth embodiment of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel so that the calculation load in the prediction process falls within the range of the amount of resources that can be processed. This allows the switching instruction device 17f to ensure that the prediction process is completed before the timing when route switching is necessary (i.e., the timing when congestion occurs).
[0310] Therefore, the switching instruction device 17f can improve communication quality by controlling route switching in advance based on the predicted traffic volume, and can prevent congestion and reduce communication delays by controlling the calculation load in the prediction process to fall within the range of the amount of resources that can be processed. In this way, the switching instruction device 17f in the sixth embodiment of the present invention can reduce communication delays while satisfying communication quality even when multiple flows are mixed.
[0311] <Seventh Embodiment> A communication system according to a seventh embodiment of the present invention will now be described. Note that the overall configuration of the communication system according to this embodiment is similar to the configuration of the conventional communication system 1 shown in the overall configuration diagram of Fig. 1 described above, and therefore a description thereof will be omitted. Furthermore, the overall configuration of a mobile communication system in which the communication system according to this embodiment is applied to mobile communication is similar to the configuration of the conventional mobile communication system 10 shown in the overall configuration diagram of Fig. 2 described above, and therefore a description thereof will be omitted.
[0312] Furthermore, the block diagram showing the functional configuration of the switching instruction device of the communication system according to the seventh embodiment is the same as the block diagram showing the functional configuration of the switching instruction device 17 of the conventional communication system 1 shown in FIG. 3 described above. Hereinafter, the switching instruction device of the seventh embodiment will be referred to as a switching instruction device 17g. The switching instruction device 17g is, for example, an information processing device such as a general-purpose computer. The switching instruction device 17g of this embodiment and the conventional switching instruction device 17 described above differ in the configurations of the prediction unit, switching threshold determination unit, and switching determination unit. Below, the configurations of the prediction unit 171g, switching threshold determination unit 172g, and switching determination unit 175g of the communication system according to this embodiment will be described.
[0313] [Functional Configuration of Prediction Unit] Fig. 31 is a block diagram showing the functional configuration of a prediction unit 171g of a communication system according to the seventh embodiment of the present invention. As shown in Fig. 31, the prediction unit 171g includes a flow classification unit 710, a flow information storage unit 720, and a grouping prediction unit 730.
[0314] The flow classification unit 710 classifies flows input to the network 5 within a predetermined period (for example, 1 millisecond or 1 second) based on traffic characteristics. The flow classification unit 710 classifies flows by flow type based on information defined in, for example, 5QI or S-NSSAI. The flow classification unit 710 calculates the number of terminals and the total traffic volume for each classified flow, and stores them in a flow information table stored in the flow information storage unit 720.
[0315] The grouping prediction unit 730 calculates the possible parallel number based on a predetermined allowable delay and a prediction time. The grouping prediction unit 730 adjusts the number of prediction processes to be executed in parallel so that it is within the possible parallel number, thereby predicting future traffic volume while limiting the amount of calculation so that the time required for the prediction process falls within the allowable delay range. The grouping prediction unit 730 outputs the value of the predicted future traffic volume to the switching threshold determination unit 172g, which will be described later.
[0316] The prediction unit in the first to sixth embodiments described above includes a total traffic calculation unit 740, and the traffic prediction unit is configured to output the value of predicted future traffic volume to the total traffic calculation unit 740. The total traffic calculation unit 740 is configured to acquire the value of predicted traffic volume for each of the possible parallel flows from the traffic prediction unit, add them up, and output the value of the total traffic volume to the switching threshold determination unit.
[0317] In contrast to this, in the seventh embodiment, the prediction unit 171f does not include the total traffic calculation unit 740, and instead, a switching threshold determination unit 172g (described later) includes a total traffic calculation unit 740g.
[0318] The switching instruction devices of the first to sixth embodiments described above and the switching instruction device of the seventh embodiment have different path switching methods. Specifically, the switching instruction devices of the first to sixth embodiments described above are configured to perform path switching for each lower-level device 3 based on the predicted traffic volume, but the switching instruction device of the seventh embodiment is configured to perform path switching for each flow based on the predicted traffic volume.
[0319] As shown in FIG. 31 , the grouping prediction unit 730 includes a parallelizable number calculation unit 731 and a traffic prediction unit 732 .
[0320] The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) for each flow based on the flow ID. The parallelizable number calculation unit 731 identifies the allowable delay (Delay_a) based on, for example, information related to 5QI or S-NSSAI stored in a storage medium (not shown) included in the prediction unit 171g. For example, when 5QI is used, the value of "PDB" can be used as the allowable delay value, and when S-NSSAI is used, the value of "Max allowed end-to-end latency" can be used.
[0321] In the case of a flow ID that is not related to the allowable delay, for example, an arbitrary allowable delay value may be predetermined. Alternatively, in the case of using S-NSSAI, a default value set according to the service may be used. In this case, the correspondence between the service and the allowable delay value is assumed to be predetermined in a flow information table or the like.
[0322] The parallel number calculation unit 731 acquires information indicating the predicted time (Ti_pred) predicted by the traffic prediction unit 732. The parallel number calculation unit 731 calculates the parallel number (M) based on the allowable delay (Delay_a) and the predicted time (Ti_pred). The parallel number calculation unit 731 outputs the calculated value of the parallel number (M) to the traffic prediction unit 732.
[0323] The traffic prediction unit 732 obtains the value of the parallelizable number (M) output from the parallelizable number calculation unit 731. The traffic prediction unit 732 narrows down the number of flows so that it falls within the parallelizable number (M) and predicts future traffic volume (predicted traffic volume). In this embodiment, the traffic prediction unit 732 narrows down the number of flows to be subjected to prediction processing by randomly selecting M flows from all classified flows. Note that, in this embodiment, the traffic prediction unit 732 is configured to randomly select M flows, but the present invention is not limited to this configuration. The traffic prediction unit 732 may also be configured to select M flows according to any rule.
[0324] The traffic prediction unit 732 predicts future traffic volumes for the selected M flows and outputs the values of the future traffic volumes (predicted traffic volumes) predicted for each of the M flows to the switching threshold determination unit 172g, which will be described later.
[0325] [Configuration of Switching Threshold Determination Unit and Switching Determination Unit] The following describes the configurations of the switching threshold determination unit 172g and the switching determination unit 175g of the switching instruction device 17g in the seventh embodiment. Figure 32 is a block diagram showing the functional configurations of the switching threshold determination unit 172g and the switching determination unit 175g of the switching instruction device 17g in the seventh embodiment of the present invention.
[0326] As shown in FIG. 32, the switching threshold value determination unit 172 g includes a total traffic calculation unit 740 g , a prediction accuracy calculation unit 173 , and a threshold value calculation unit 174 .
[0327] The total traffic calculation unit 740g acquires the value of the predicted traffic volume predicted by the traffic prediction unit 732 of the grouping prediction unit 730. The total traffic calculation unit 740g calculates the total traffic volume of actual traffic per lower-level device 3 (hereinafter referred to as the "total actual traffic volume") and the total traffic volume per lower-level device 3 (hereinafter also referred to as the "total predicted traffic volume"). The total traffic calculation unit 740g outputs the calculated values of the total actual traffic volume and the total predicted traffic volume to the prediction accuracy calculation unit 173.
[0328] The prediction accuracy calculation unit 173 acquires the value of the total actual traffic volume and the value of the total predicted traffic volume output from the total traffic calculation unit 740g. The prediction accuracy calculation unit 173 calculates the prediction accuracy for each upper link based on the future traffic volume predicted in the past by the prediction unit 171 and the total actual traffic volume. The prediction accuracy calculation unit 173 outputs information indicating the calculated prediction accuracy to the threshold calculation unit 174.
[0329] The threshold calculation unit 174 acquires the information indicating the prediction accuracy output from the prediction accuracy calculation unit 173. The threshold calculation unit 174 calculates a switching threshold for each upper link based on the link rate and the prediction accuracy. The threshold calculation unit 174 outputs the switching threshold for each upper link to the switching determination unit 175g.
[0330] As shown in FIG. 32, the switching determination unit 175 g includes a link usage rate calculation unit 176 and a switching flow calculation unit 177 .
[0331] The link utilization calculation unit 176 obtains the switching threshold for each upper link output from the threshold calculation unit 174. The link utilization calculation unit 176 also obtains the value of the total predicted traffic volume from the total traffic calculation unit 740g. The link utilization calculation unit 176 calculates the predicted link utilization for each upper link based on the value of the total predicted traffic volume and the switching threshold. The link utilization calculation unit 176 outputs the calculated link utilization value to the switching flow calculation unit 177.
[0332] The switching flow calculation unit 177 acquires the link utilization value output from the link utilization calculation unit 176. When there is an upper link for which it is determined that congestion will occur due to a high predicted link utilization rate, the switching flow calculation unit 177 determines to perform route switching, and identifies route switching that will result in a traffic volume that will not cause congestion, starting with the flow with the lowest priority. When it determines to perform route switching, the switching flow calculation unit 177 instructs each device (e.g., the lower device 3, the upper device 4, and the transfer device 15) to switch the identified route.
[0333] An example of the operation of the switching flow calculation unit 177 will be described in more detail below with a specific example. Fig. 33 is a flowchart showing the operation of the switching flow calculation unit 177 of the switching determination unit 175g according to the seventh embodiment of the present invention.
[0334] The switching flow calculation unit 177 obtains the predicted traffic volume and sorts the predicted traffic volumes for each flow. The switching flow calculation unit 177 sorts the flows in ascending order of priority (step S211).
[0335] In addition, the switching flow calculation unit 177 calculates the congestion amount (or the free space if the value is negative) for each lower-level device 3 based on the link usage rate of each lower-level device 3 and the switching threshold, as shown in the following equation (14) (step S212).
[0336] X_conv = (link utilization rate - 1) × switching threshold (14)
[0337] Hereinafter, X_conv that is a positive value will be represented as "X_conv1", and X_conv that is a negative value will be represented as "X_conv2".
[0338] The switching flow calculation unit 177 identifies the lower-level device 3 with the largest congestion amount value and the lower-level device 3 with the smallest congestion amount value (i.e., the largest available capacity value). Based on the largest congestion amount value and the largest available capacity value, the switching flow calculation unit 177 calculates the maximum traffic volume at which path switching is effective (step S213).
[0339] For example, if the congestion level of the first lower-level device 3 is the highest and the congestion level of the second lower-level device 3 is the lowest (i.e., the available capacity is the highest), the maximum traffic volume at which path switching is effective is expressed by the following equation (15).
[0340] X=X_conv1−X_conv2…(15)
[0341] The switching flow calculation unit 177 determines whether the path switching is effective by switching paths in order from the lowest priority flow (Step S214).
[0342] If it is determined that the route switching is effective (X>Xi) (Yes in step S214), the switching flow calculation unit 177 instructs the link utilization calculation unit 176 to recalculate the link utilization (Link).
[0343] Link = Link-xi / switching threshold (16)
[0344] The switching flow calculation unit 177 changes the lower-level device 3 to which the switched predicted traffic belongs (Step S215).
[0345] On the other hand, if it is determined that the path switching is ineffective (X≦Xi) (No in step S214), the switching flow calculation unit 177 compares the flow with the next highest priority (step S217). Note that in this embodiment, the comparison is performed in order from the lowest priority flow, but the present invention is not limited to this configuration. For example, the comparison may be performed in order from the highest traffic volume flow.
[0346] When performing path switching for each flow, the switching flow calculation unit 177 notifies the transfer device 15 (switching device) of the DSCP of the flow for which path switching is to be performed, since there is a correspondence between the DSCP (Differentiated Services Code Point) and 5QI.
[0347] After determining whether to perform route switching, the switching flow calculation unit 177 again determines whether congestion has occurred based on the new link utilization rates. If all link utilization rates are not 1 (i.e., if the link utilization rates are greater than 1), the switching flow calculation unit 177 ends the process.
[0348] This completes the operation of the switching flow calculation unit 177 shown in the flowchart of FIG.
[0349] As described above, the switching instruction device 17g in the seventh embodiment of the present invention classifies each of the flows input from, for example, a lower-level device 3 during a predetermined period based on traffic pattern (e.g., QoS) characteristics based on information defined in, for example, 5QI or S-NSSAI. The switching instruction device 17g calculates the maximum number of flows that can be subjected to parallel processing within the allowable delay range based on the allowable delay and the predicted time. The switching instruction device 17g randomly selects M flows from all of the classified flows input during the predetermined period and calculates future traffic volumes (predicted traffic volumes) for each of the selected M flows. Furthermore, while the switching instruction devices in the first to sixth embodiments were configured to perform path switching for each lower-level device 3 based on the predicted traffic volume, the switching instruction device in the seventh embodiment performs path switching for each flow based on the predicted traffic volume.
[0350] In this way, the switching instruction device 17g in the seventh embodiment of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel to fall within a range of the possible parallel number that enables the prediction process to be completed within the allowable time for route switching prediction. This allows the switching instruction device 17g to ensure that the prediction process is completed before the timing when route switching is necessary (i.e., the timing when congestion occurs).
[0351] Therefore, the switching instruction device 17g can improve communication quality by controlling route switching in advance based on the predicted traffic volume, and can prevent congestion and reduce communication delays by controlling the prediction process to be completed within the allowed time. In this way, the switching instruction device 17g in the seventh embodiment of the present invention can reduce communication delays while satisfying communication quality even when multiple flows are mixed.
[0352] The basic configuration common to the switching instruction devices in the above-described embodiments will be summarized and explained below. Fig. 34 is a diagram showing the basic processing flow of the switching instruction device in each embodiment of the present invention.
[0353] First, the flow classification unit classifies flows input to the network 5 within a predetermined period (e.g., 1 millisecond or 1 second) based on traffic characteristics (step S01). The traffic characteristics include, for example, QoS, traffic pattern, or traffic period. Here, the number of flows classified and grouped by the flow classification unit is assumed to be N. In the following description, a "flow" refers to a flow after classification by the flow classification unit, i.e., a flow in which flows with the same traffic characteristics are grouped together.
[0354] Next, the parallel number calculation unit calculates the parallel number (step S02). Here, the parallel number calculated by the parallel number calculation unit is assumed to be M. The parallel number is the maximum number of predicted processes that can be completed within the allowable delay range when predicting future traffic volumes for multiple flows in parallel. The parallel number calculation unit calculates the parallel number based on the allowable delay and the predicted time. Alternatively, the parallel number calculation unit calculates the parallel number based on the amount of resources and the calculation load. For example, in the first embodiment described above, the parallel number calculation unit calculates the parallel number using the former method, while in the sixth embodiment described above, the parallel number calculation unit calculates the parallel number using the latter method.
[0355] Next, if the number of flows (N) is greater than the parallelizable number (M), the traffic prediction unit 732 adjusts the number of flows to be subjected to the prediction process of future traffic volume so that it is at most the parallelizable number (M) (step S03). This is because if the prediction process is performed in parallel for a number of flows that exceeds the parallelizable number, it may not be possible to complete the prediction process before the prediction target period arrives, which may cause congestion and communication delays.
[0356] If the number of flows (N) is already within the parallelizable number (M), there is no need to adjust the number of flows to be subjected to prediction processing, because even if prediction processing is performed in parallel for all (i.e., N) flows classified by the flow classification unit, all prediction processing can be completed before the target prediction period arrives.
[0357] One method for adjusting the number of flows for which the traffic prediction unit 732 performs prediction processing on future traffic volumes so that it reaches at most the parallelizable number (M) is to select at most the parallelizable number (M) of flows from all (i.e., N) flows classified by the flow classification unit, and perform prediction processing on only the selected flows. For example, in the first and second embodiments described above, the traffic prediction unit 732 adjusts the number of flows for which prediction processing is performed using this method. In this case, prediction processing is not performed on flows that were not selected, so for example, past traffic volumes are treated as future traffic volumes.
[0358] One method for adjusting the number of flows for which the traffic prediction unit 732 performs prediction processing on future traffic volumes so that the number of flows reaches the maximum possible parallel number (M) is to group all of the flows (i.e., N flows) classified by the flow classification unit as many times as necessary, adjust the number of groups so that the number of groups reaches the maximum possible parallel number (M), and perform prediction processing on a group-by-group basis. For example, in the third and fourth embodiments described above, the traffic prediction unit 732 adjusts the number of flows for which prediction processing is performed in this manner.
[0359] Next, when the number of flows is adjusted by selecting only the maximum number of flows (M) that can be parallelized from all (i.e., N) flows, the traffic prediction unit 732 performs a prediction process for future traffic volume only for the selected flows. On the other hand, when the number of groups to be predicted is adjusted by grouping all (i.e., N) flows as many times as necessary, the traffic prediction unit 732 performs a prediction process for future traffic volume for each group (step S04).
[0360] Next, the total traffic calculation unit calculates the total traffic volume by adding up the future traffic volumes obtained by the prediction process by the traffic prediction unit (step 05). At this time, if the number of flows has been adjusted by selecting only the maximum number of flows that can be parallelized (M) from all (i.e., N) flows, the total traffic calculation unit performs the above-mentioned addition process by regarding, for example, the past traffic volume as the future traffic volume for the flows that have not been selected.
[0361] Next, the prediction accuracy calculation unit of the switching threshold determination unit acquires the value of the total traffic volume calculated by the total traffic calculation unit. The prediction accuracy calculation unit calculates prediction accuracy for each link based on the total traffic volume calculated in the past (e.g., period (t-1)) and the actual traffic volume at the present (e.g., period (t)). The threshold calculation unit of the switching threshold determination unit determines a switching threshold for each link such that the lower the prediction accuracy, the lower the ratio of the switching threshold to the link's transmission capacity (e.g., link rate) (step S06).
[0362] Next, the switching determination unit determines in advance whether congestion will occur for each link based on the value of the total traffic volume and the switching threshold (step S07).
[0363] Next, if congestion is predicted, the switching determination unit determines to perform route switching for load balancing. For example, the switching determination unit determines to perform route switching from a link where congestion is predicted to occur to a link with a low link utilization rate. The switching determination unit instructs a transfer device or the like that will perform the route switching to perform the process for route switching (step S08).
[0364] The above is the basic process flow common to the switching instruction devices in the above-described embodiments.
[0365] An example of the timing of execution of the flow grouping process (classification process) by the flow classification unit 734 based on the number of parallel processes in the third embodiment and the flow classification unit 734 based on the number of parallel processes in the fourth embodiment will be described below.
[0366] 35 is a diagram illustrating the execution timing of the grouping process by the flow classification unit based on the number of parallel flows in each embodiment of the present invention. In the example shown in FIG. 35, there are two flows before grouping, namely, flow 1, which requires 5 milliseconds for prediction (prediction time), and flow 2, which also requires 5 milliseconds for prediction. Note that the number of flows changes over time.
[0367] In addition, the delay time (allowable delay) allowed for the prediction process of future traffic volume (predicted traffic volume) in each period is set to be within 8 milliseconds for each flow.
[0368] The example shown in Figure 35 shows how the prediction process for each flow is repeated at the interval of time (t0)-time (t-1). For example, as shown in Figure 35, at the timing of time (t-1), the prediction process for the future traffic volume for flow 1 and the prediction process for the future traffic volume for flow 2 are started simultaneously. Subsequently, similarly at the timing of time (t), the prediction process for the future traffic volume for flow 1 and the prediction process for the future traffic volume for flow 2 are started again simultaneously.
[0369] As described above, the time required for prediction (prediction time) for both Flow 1 and Flow 2 is 5 milliseconds, but as shown in FIG. 35, the prediction process started at time (t-1) is not completed by time (t0). Therefore, the interval between time (t0) and time (t-1) is less than 5 milliseconds. Therefore, in this case, the result of the prediction process started at time (t-1) is used in the flow grouping process that starts at time (t1), which is the start timing of the next period.
[0370] In the flow grouping process starting at time (t1), the number of parallel processes is first calculated. Here, assume that parallel prediction processing for flow 1, which has a predicted time of 5 milliseconds, and flow 2, which also has a predicted time of 5 milliseconds, requires a total of 10 (= 5 + 5) milliseconds. In this case, the number of parallel processes can be calculated by dividing the total predicted time by the allowed time. Since the allowed time is 8 milliseconds as described above, the number can be calculated to be within 1.6 (= 10 / 8) (i.e., 1).
[0371] Next, based on the calculated number of flows that can be run in parallel, a determination is made as to whether grouping is necessary. In the example shown in Fig. 35, the number of flows that can be run in parallel is one, and therefore it is determined that grouping is necessary. Then, flow 1 and flow 2 are grouped into one group (group 1).
[0372] Thereafter, prediction processing is performed based on the time-series traffic obtained by adding up the traffic of flows 1 and 2 belonging to group 1. Because the traffic is added up, the prediction time for future traffic volume for group 1 is 5 milliseconds. Therefore, the prediction time is within the allowable delay of 8 milliseconds, making it possible to complete the prediction processing within the allowable delay range.
[0373] Thereafter, based on the future traffic volume predicted for the time-series traffic in units of groups, it is determined whether congestion will occur, and route switching is performed as necessary.
[0374] Another example of the execution timing of the flow grouping process (classification process) by the flow classification unit 734 based on the number of parallel processes in the third embodiment and the flow classification unit 734 based on the number of parallel processes in the fourth embodiment will be described below.
[0375] Figure 36 is a diagram illustrating the execution timing of the grouping process by the flow classification unit based on the number of parallel processes in each embodiment of the present invention. In the example shown in Figure 36, the number of flows before grouping is three. However, unlike the example shown in Figure 35 above, flow 1 and flow 2 have already been grouped, and there are grouped flow 1 and flow 2, which require a prediction time of 4 milliseconds (prediction time), and flow 3, which also requires a prediction time of 45 milliseconds. Note that the number of flows changes over time as needed.
[0376] Furthermore, the delay time (allowable delay) allowed for the prediction process of future traffic volume (predicted traffic volume) in each period is set to within 5 milliseconds for each flow.
[0377] The example shown in Figure 36 shows how the prediction process for each flow is repeated at the interval of time (t0)-time (t-1). For example, as shown in Figure 36, at the timing of time (t-1), the prediction process for the future traffic volume for flows 1+2 and the prediction process for the future traffic volume for flow 3 are started simultaneously. Subsequently, similarly at the timing of time (t), the prediction process for the future traffic volume for flows 1+2 and the prediction process for the future traffic volume for flow 3 are started simultaneously again.
[0378] As mentioned above, the time required for prediction (prediction time) for both Flow 1+2 and Flow 3 is 4 milliseconds, but as shown in FIG. 36, the prediction process started at time (t-1) is not completed by time (t0). Therefore, the interval between time (t0) and time (t-1) is less than 4 milliseconds. Therefore, in this case, the result of the prediction process started at time (t-1) is used in the flow grouping process that starts at time (t1), which is the start timing of the next period.
[0379] In the flow grouping process starting at time (t1), the number of parallel processes is first calculated. Here, if prediction processing is performed in parallel on flow 1+2, which has a predicted time of 4 milliseconds, and flow 3, which also has a predicted time of 4 milliseconds, a total of 8 (=4+4) milliseconds will be required. In this case, the number of parallel processes can be calculated by dividing the total predicted time by the allowed time. Since the allowed time is 5 milliseconds as mentioned above, the number can be calculated to be within 1.25 (=5 / 4) (i.e., 1).
[0380] Next, based on the calculated number of parallel processes, a determination is made as to whether grouping is necessary. In the example shown in Figure 36, if the flows already grouped are considered to be one flow, it is determined that grouping is necessary because there are two flows and the number of parallel processes that can be executed is one. Then, flows 1+2 and flow 3 are grouped into one group (group 1).
[0381] Thereafter, prediction processing is performed based on the time-series traffic obtained by adding together the traffic of flows 1+2 and 3 belonging to group 1. Because the traffic is added together, the prediction time for future traffic volume for group 1 is 4 milliseconds. Therefore, the prediction time is within the allowable delay of 5 milliseconds, making it possible to complete the prediction processing within the allowable delay range.
[0382] Thereafter, based on the future traffic volume predicted for the time-series traffic in units of groups, it is determined whether congestion will occur, and route switching is performed as necessary.
[0383] The first to third embodiments are described assuming the use of traffic captured from the lower-level device 3. In each of the above-described embodiments, the network 5 may be any network such as a mobile fronthaul (MFH), a mobile midhaul (MMH), or a mobile backhaul (MBH).
[0384] In each of the above-described embodiments, the switching instruction device may be configured to acquire traffic information from a controller (not shown) of the lower-level device 3 instead of acquiring traffic information from the lower-level device 3 .
[0385] In each of the above-described embodiments, the switching instruction device may be configured to use scheduling information in the wireless section (e.g., BSR (Buffer Status Report), TBS (Transport Block Size), etc.) instead of using a traffic volume value when determining whether to perform path switching. In this case, the network 5 is, for example, an MMH or MBH. The source from which the scheduling information is obtained is, for example, a DU, a DU controller, a CU, or a CU controller.
[0386] In the above-described embodiments, the case of upstream communication has been described as an example, but the present invention is not limited to this, and a similar configuration can be applied to downstream communication as well.
[0387] In the above-described embodiments, a configuration assuming a 5G mobile network is described, but the present invention is not limited to this. A similar configuration can be applied to other wireless networks such as Wi-Fi (registered trademark). In this case, the source from which traffic information is obtained is, for example, a Wi-Fi (registered trademark) access point. Furthermore, the network 5 is, for example, a network between a Wi-Fi (registered trademark) controller and a Wi-Fi (registered trademark) access point.
[0388] As described above, the switching instruction device in each of the above-described embodiments of the present invention narrows down the number of flows for which traffic volume predictions are performed in parallel. This allows the switching instruction device to ensure that the prediction process is completed before the timing at which route switching is necessary (i.e., the timing at which congestion occurs). Therefore, the switching instruction device can improve communication quality by controlling route switching in advance based on the predicted traffic volume, while preventing congestion and reducing communication delays by controlling the prediction process to be completed within an allowable time. In this way, the switching instruction device in each of the above-described embodiments of the present invention can reduce communication delays while maintaining communication quality, even when multiple flows are mixed.
[0389] According to the above-described embodiment, the prediction device includes a flow classifying unit, a parallelizable number calculating unit, a traffic predicting unit, and a total traffic calculating unit. For example, the prediction device corresponds to the prediction units 71a to 71g in the embodiment, the flow classifying unit corresponds to the flow classifying unit 710 in the embodiment, the parallelizable number calculating unit corresponds to the parallelizable number calculating units 731, 731b, 731d, and 731f in the embodiment, the traffic predicting unit corresponds to the traffic predicting units 732 and 732f in the embodiment, and the total traffic calculating unit corresponds to the total traffic calculating units 740 and 740g in the embodiment.
[0390] The flow classification unit classifies communication traffic input during a predetermined period into multiple flows based on the characteristics of the communication traffic. For example, the communication traffic characteristics are flow types based on information defined in 5QI or S-NSSAI in the embodiment. The parallelization number calculation unit calculates a parallelization number, which is the maximum number of prediction processes that can be completed before the second period begins when prediction processes for predicting traffic volumes for a second period after the first period are performed in parallel for each flow based on the traffic volume for each flow during the first period and predetermined conditions. For example, the traffic volume for the second period is the predicted traffic volume in the embodiment. If the number of flows classified by the flow classification unit is greater than the parallelization number, the traffic prediction unit performs prediction processes for flows within the parallelization number. The total traffic calculation unit calculates the total traffic volume for the second period based on the results of the prediction process by the traffic prediction unit. For example, the total value of the traffic volume for the second period is the total traffic volume in the embodiment.
[0391] In the prediction device, the predetermined condition may be a condition based on an allowable time, which is a processing time allowed for the prediction process, and a predicted time, which is a time required for the prediction process. In this case, the parallel number calculation unit calculates the parallel number by determining whether the predicted time falls within the allowable time.
[0392] In addition, in the above prediction device, if the number of flows classified by the flow classification unit is greater than the number that can be processed in parallel, the traffic prediction unit may add up the traffic volume of multiple flows and treat the multiple flows as one flow, thereby keeping the number of prediction processes to within the number that can be processed in parallel.
[0393] In addition, in the above prediction device, when the above traffic prediction unit regards multiple flows as one flow, it may select multiple flows to add up the traffic volume so that the maximum value of the traffic period of each of the flows to be predicted is small.
[0394] In addition, in the above prediction device, if the number of flows classified by the flow classification unit is greater than the number that can be parallelized, the traffic prediction unit may select flows from the multiple flows in order of the largest maximum past traffic volume, thereby ensuring that the number of prediction processes to be performed is within the number that can be parallelized.
[0395] In the prediction device, the predetermined condition may be a condition based on the amount of resources available for processing in the prediction process and the calculation load generated by the prediction process. In this case, the parallel number calculation unit calculates the parallel number by determining whether the calculation load fits within the amount of resources.
[0396] Furthermore, according to the above-described embodiment, the communication control device includes a flow classifying unit, a parallelizable number calculating unit, a traffic predicting unit, a total traffic calculating unit, a switching determination unit, and a switching instruction unit. For example, the prediction device corresponds to the prediction units 71a to 71g in the embodiment, the flow classifying unit corresponds to the flow classifying unit 710 in the embodiment, the parallelizable number calculating unit corresponds to the parallelizable number calculating units 731, 731b, 731d, and 731f in the embodiment, the traffic predicting unit corresponds to the traffic predicting units 732 and 732f in the embodiment, the total traffic calculating unit corresponds to the total traffic calculating units 740 and 740g in the embodiment, the switching determination unit corresponds to the switching determination units 175 and 175g in the embodiment, and the switching instruction unit corresponds to the switching instruction devices 17a to 17g in the embodiment.
[0397] The flow classification unit classifies communication traffic input during a predetermined period into multiple flows based on the characteristics of the communication traffic. For example, the communication traffic characteristics are flow types based on information defined in 5QI or S-NSSAI in the embodiment. The parallelization number calculation unit calculates a parallelization number, which is the maximum number of prediction processes that can be completed before the second period begins when prediction processes for predicting traffic volumes for a second period after the first period are performed in parallel for each flow based on the traffic volume for each flow during the first period and predetermined conditions. For example, the traffic volume for the second period is the predicted traffic volume in the embodiment. If the number of flows classified by the flow classification unit is greater than the parallelization number, the traffic prediction unit performs prediction processes for flows within the parallelization number. The total traffic calculation unit calculates the total traffic volume for the second period based on the results of the prediction process by the traffic prediction unit. For example, the total value of the traffic volume for the second period is the total traffic volume in the embodiment. The switching determination unit predicts whether congestion will occur in the second period based on the total traffic volume, and determines whether switching of the communication path is necessary based on the prediction result. When the switching determination unit determines that switching of the communication path is necessary, the switching instruction unit issues a switching instruction to a switching device that executes switching of the communication path. For example, the switching device is the transfer device 15 in the embodiment.
[0398] Part or all of the configuration of the switching instruction device in the above-described embodiment may be implemented by a computer. In this case, a program for implementing this function may be recorded on a computer-readable recording medium, and the program may be loaded into a computer system and executed. Note that the term "computer system" as used herein includes hardware such as an OS and peripheral devices. Furthermore, "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into computer systems. Furthermore, "computer-readable recording medium" may also include media that dynamically store programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or telephone lines, or media that store programs for a fixed period of time, such as volatile memory within the computer system that serves as the server or client. The program may be designed to implement part of the above-described functions, or may be capable of implementing the above-described functions in combination with programs already stored in the computer system, or may be implemented using a programmable logic device such as an FPGA (Field Programmable Gate Array).
[0399] Although an embodiment of the present invention has been described above in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and includes designs within the scope that do not deviate from the gist of the present invention.
[0400] 1...communication system, 3...lower-level device, 4...higher-level device, 5...network, 7...switching instruction device, 10...mobile communication system, 11...terminal station, 12...antenna station, 13...remote station, 14...aggregate station, 15...transfer device, 16...resource allocation device, 17, 17a to 17g...switching instruction device, 20...higher-level network, 71...prediction unit, 72...switching threshold determination unit, 73...prediction accuracy calculation unit, 74...threshold calculation unit, 75...switching judgment unit, 171, 171a to 171g...prediction unit, 172, 172g...switching threshold determination unit determination unit, 173... prediction accuracy calculation unit, 174... threshold calculation unit, 175, 175g... switching determination unit, 176... link utilization rate calculation unit, 177... switching flow calculation unit, 710... flow classification unit, 720... flow information storage unit, 730, 730b to 730f... grouping prediction unit, 731, 731b, 731d, 731f... parallelizable number calculation unit, 732, 732f... traffic prediction unit, 733... traffic period calculation unit, 734, 734e... flow classification unit, 740, 740g... total traffic calculation unit
Claims
1. A prediction device comprising: a flow classification unit that classifies communication traffic input during a specified period into a plurality of flows based on characteristics of the communication traffic; a parallel number calculation unit that calculates a parallel number, which is the maximum number of prediction processes that can be completed before the second period begins, when a prediction process that predicts the traffic volume for a second period after the first period is performed in parallel for each flow based on the traffic volume for each flow in a first period and specified conditions; a traffic prediction unit that performs the prediction process on a number of flows within the parallel number when the number of flows classified by the flow classification unit is greater than the parallel number; and a total traffic calculation unit that calculates a total of the traffic volume for the second period based on the result of the prediction process by the traffic prediction unit.
2. The prediction device according to claim 1, wherein the predetermined condition is a condition based on an allowable time, which is the processing time allowed for the prediction process, and a predicted time, which is the time required for the prediction process, and the possible parallel number calculation unit calculates the possible parallel number by determining whether the predicted time falls within the allowable time.
3. The prediction device according to claim 2, wherein, when the number of flows classified by the flow classification unit is greater than the possible parallel number, the traffic prediction unit adds up the traffic volumes of the multiple flows and regards the multiple flows as one flow, thereby keeping the number of prediction processes to be performed within the possible parallel number.
4. The prediction device according to claim 3, wherein, when the traffic prediction unit regards the multiple flows as one flow, it selects the multiple flows whose traffic volumes are to be added together so that the maximum value of the traffic period of each of the flows for which the prediction process is performed is small.
5. The prediction device according to claim 2, wherein, when the number of flows classified by the flow classification unit is greater than the possible parallel number, the traffic prediction unit keeps the number of prediction processes to be performed within the possible parallel number by selecting, from among the multiple flows, the flows having the largest maximum past traffic volume.
6. The prediction device described in claim 1, wherein the specified condition is a condition based on an amount of resources that can be processed in the prediction process and a calculation load generated in the prediction process, and the parallel number calculation unit calculates the parallel number by determining whether the calculation load is within the amount of resources.
7. A communication control device comprising: a flow classification unit that classifies communication traffic input during a specified period into a plurality of flows based on characteristics of the communication traffic; a parallel number calculation unit that calculates a parallel number, which is the maximum number of prediction processes that can be completed before the second period begins when a prediction process for predicting the traffic volume for a second period after the first period is performed in parallel for each flow based on the traffic volume for each flow during a first period and specified conditions; a traffic prediction unit that, when the number of the flows classified by the flow classification unit is greater than the parallel number, performs the prediction process for a number of the flows within the parallel number; a total traffic calculation unit that calculates a total of the traffic volume for the second period based on a result of the prediction process by the traffic prediction unit; a switching determination unit that predicts whether congestion will occur during the second period based on the total value of the traffic volume and determines whether or not a communication path needs to be switched based on the prediction result; and a switching instruction unit that issues a switching instruction to a switching device that executes the switching of the communication path when it is determined by the switching determination unit that the communication path needs to be switched.
8. A prediction method executed by a computer, comprising: a flow classification step of classifying communication traffic input during a specified period into a plurality of flows based on characteristics of the communication traffic; a parallel number calculation step of calculating a parallel number which is the maximum number of prediction processes that can be completed before the second period begins when a prediction process for predicting the traffic volume in a second period after the first period is performed in parallel for each flow based on the traffic volume for each flow in a first period and specified conditions; a traffic prediction step of performing the prediction process on a number of the flows not exceeding the parallel number when the number of the flows classified by the flow classification step is greater than the parallel number; and a total traffic calculation step of calculating a total of the traffic volume in the second period based on a result of the prediction process in the traffic prediction step.
Citation Information
Patent Citations
Communication traffic predicting device, communication traffic predicting method, and program
JP2014087031A
Control device, communication system, and radio control method
JP2018011244A
Transmission system, switching control device, switching control method, and program
WO2023058089A1
