A business processing method, device, equipment and readable storage medium

Abstract

The present invention discloses a service processing method, device, equipment and readable storage medium, which relates to the field of communication technology, so as to provide a simple energy-saving strategy deployed and implemented from a global perspective. The method comprises: determining a first source SBS side edge device that can be in sleep mode from an SBS side edge device queue; determining a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device in a powered-on state; unloading the service of the first source SBS side edge device, and using the target SBS side edge device to process the service of the first source SBS side edge device. The embodiment of the present invention can provide a method for deploying base station energy saving from a global perspective and implementing a simple energy-saving strategy, thereby achieving the purpose of energy saving.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular to a service processing method, device, equipment and readable storage medium. Background Art

[0002] In order to meet the surging data traffic and data-intensive service needs, 5G base station deployment is about to usher in a large-scale development period. At the same time, the problems of high power consumption and high carbon emissions that come with it need to be solved urgently. Therefore, green communication networks will become an inevitable trend in the development of future wireless communication networks.

[0003] The industry has achieved a lot of research results on the energy consumption issue. At the base station communication level, on the one hand, energy consumption can be reduced by innovating hardware technology to produce new energy-saving base stations, using outdoor base stations, or replanning the construction of base station sites; on the other hand, different business scheduling strategies are proposed or applied to monitor network load or business traffic, and base station energy consumption devices are turned off when the business is under low load, so that the base station is in sleep mode. At the computing level, by considering the workload balance between the cloud and edge devices, different business strategies are used to schedule whether the business is processed in the cloud or on the edge device, so as to effectively utilize cloud resources while reducing the business burden of edge devices, so that the corresponding edge devices can be put into a dormant state to achieve energy saving.

[0004] In the existing energy-saving scheme, at the base station communication level, the triggering conditions for base station energy saving are limited to the base station's own monitoring and judgment of the load status of the cell to which it belongs. Operators cannot deploy base station energy-saving strategies from a global perspective of the network; at the computing level, the service scheduling process is relatively complicated. Therefore, it is necessary to propose a simple energy-saving strategy that deploys base station energy saving from a global perspective. Summary of the invention

[0005] The embodiments of the present invention provide a service processing method, apparatus, device and readable storage medium to provide a simple energy-saving strategy for deployment and implementation from a global perspective.

[0006] In a first aspect, an embodiment of the present invention provides a service processing method, which is applied to an SDN (Software Defined Network) controller, including:

[0007] Determine a first source SBS side edge device that can be in sleep mode from a SBS (Small Base Station) side edge device queue;

[0008] Determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state;

[0009] The service of the first source SBS side edge device is unloaded, and the service of the first source SBS side edge device is processed by using the target SBS side edge device.

[0010] The step of determining the first source SBS side edge device that can be in sleep mode from the micro base station SBS side edge device queue includes:

[0011] Calculating a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue;

[0012] Sorting the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate;

[0013] According to the sorting result, an SBS side edge device with a smaller service arrival rate is selected from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

[0014] The calculating of the first value includes:

[0015] Calculate the first parameter;

[0016] obtaining the first value using the first parameter;

[0017] The first parameter is calculated as follows:

[0018]

[0019] Among them, N * represents the first parameter, λ SDN_total is the sum of the service arrival rates of each SBS-side edge device in the SBS-side edge device queue, μ SDN_total is the sum of the service leaving rates of each SBS side edge device in the SBS side edge device queue, g is the second parameter, and is We can obtain Φ(g) and φ(g) represents the cumulative function and probability density function of the standard normal distribution, and ε represents the probability threshold;

[0020] The first value is calculated using the following formula:

[0021]

[0022] Among them, k SDN_off represents the first value, n krepresents the sum of the number of servers included in each SBS side edge device in the SBS side edge device queue, and K represents the number of SBS side edge devices in the SBS side edge device queue.

[0023] There are multiple first source SBS side edge devices; and determining a target SBS side edge device matching the first source SBS side edge device includes:

[0024] Sorting the plurality of first source SBS side edge devices according to the size of the service arrival rate;

[0025] For the kth first source SBS side edge device in the sorting result, select a first candidate SBS side edge device from the SBS side edge devices in the powered-on state;

[0026] Calculate the third parameter ρ k and the fourth parameter P k , the third parameter represents the queue delay threshold, and the fourth parameter represents the system stability;

[0027] If k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device of the kth first source SBS side edge device, and ε represents the probability threshold of service queuing waiting for processing.

[0028] Wherein, the method further comprises:

[0029] When the number of first source SBS side edge devices currently in sleep mode in the SBS side edge device queue is greater than the first value, determining second source SBS side edge devices in the SBS side edge device queue that can be in sleep mode except the first source SBS side edge device;

[0030] Put the second source SBS side edge device into sleep mode, transfer the first type of service flow of the second source SBS side edge device to the cloud for processing, and transfer the second type of service flow of the second source SBS side edge device to the MBS (Micro Base Station) side edge device for processing.

[0031] The determining of a second source SBS side edge device in the SBS side edge device queue that can be in a sleep mode except the first source SBS side edge device includes:

[0032] For at least one third source SBS side edge device in the SBS side edge device queue except the first source SBS side edge device, a first probability and a second probability are calculated; the first probability is the probability that the first type of service of the third source SBS side edge device is queued in the cloud queue, and the second probability is the probability that the second type of service of the third source SBS side edge device is queued in the MBS queue;

[0033] sorting the at least one third source SBS side edge device according to the first probability and the second probability of the at least one third source SBS side edge device;

[0034] For the mth value in the sorting result, determine whether the cloud stability requirement and the macro base station side edge device stability requirement are met if the third source SBS side edge device corresponding to the mth value is in sleep mode, 1≤m≤2×n, where n is the number of at least one third source SBS side edge device;

[0035] If the cloud stability requirements and the macro base station side edge device stability requirements are met, the third source SBS side edge device corresponding to the mth value is used as the second source SBS side edge device.

[0036] In a second aspect, an embodiment of the present invention provides a service processing device, which is applied to an SDN controller, including:

[0037] A first determining module, configured to determine a first source SBS side edge device that can be in a sleep mode from a SBS side edge device queue;

[0038] A second determination module is used to determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state;

[0039] The first processing module is configured to unload the service of the first source SBS side edge device and use the target SBS side edge device to process the service of the first source SBS side edge device.

[0040] Wherein, the first determining module includes:

[0041] A first calculation submodule, configured to calculate a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in a sleep mode in the SBS side edge device queue;

[0042] A first sorting submodule is used to sort the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate;

[0043] The first determination submodule is configured to select, according to the sorting result, an SBS side edge device with a smaller service arrival rate from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

[0044] Wherein, the first calculation submodule is used to calculate a first parameter; and obtain the first value using the first parameter;

[0045] The first parameter is calculated as follows:

[0046]

[0047] Among them, N * represents the first parameter, λ SDN_total is the sum of the service arrival rates of each SBS-side edge device in the SBS-side edge device queue, μ SDN_total is the sum of the service leaving rates of each SBS side edge device in the SBS side edge device queue, g is the second parameter, and is We can obtain Φ(g) and φ(g) represents the cumulative function and probability density function of the standard normal distribution, and ε represents the probability threshold;

[0048] The first value is calculated using the following formula:

[0049]

[0050] Among them, k SDN_off represents the first value, n k represents the sum of the number of servers included in each SBS side edge device in the SBS side edge device queue, and K represents the number of SBS side edge devices in the SBS side edge device queue.

[0051] There are multiple first source SBS side edge devices; and the second determination module includes:

[0052] A first sorting submodule, used to sort the plurality of first source SBS side edge devices according to the size of the service arrival rate;

[0053] A first selection submodule, configured to select, for the kth first source SBS side edge device in the sorting result, a first candidate SBS side edge device from the SBS side edge devices in the powered-on state;

[0054] The first calculation submodule is used to calculate the third parameter ρ k and the fourth parameter P k , the third parameter represents the queue delay threshold, and the fourth parameter represents the system stability;

[0055] The first determination submodule is used if ρ k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device of the kth first source SBS side edge device, and ε represents the probability threshold of service queuing waiting for processing.

[0056] Wherein, the device further comprises:

[0057] A third determination module is used to determine a second source SBS side edge device in the SBS side edge device queue that can be in the sleep mode except the first source SBS side edge device when the number of the first source SBS side edge devices currently in the sleep mode in the SBS side edge device queue is greater than the first value;

[0058] The second processing module is used to put the second source SBS side edge device into sleep mode, transfer the first type of business flow of the second source SBS side edge device to the cloud for processing, and transfer the second type of business flow of the second source SBS side edge device to the macro base station MBS side edge device for processing.

[0059] Wherein, the third determination module includes:

[0060] A first calculation submodule is used to calculate a first probability and a second probability for at least one third source SBS side edge device in the SBS side edge device queue except the first source SBS side edge device; the first probability is the probability that the first type of service of the third source SBS side edge device is queued in the cloud queue, and the second probability is the probability that the second type of service of the third source SBS side edge device is queued in the MBS queue;

[0061] A first sorting submodule, configured to sort the at least one third source SBS side edge device according to the first probability and the second probability of the at least one third source SBS side edge device;

[0062] A first judgment submodule is used to judge, for the mth value in the sorting result, whether the cloud stability requirement and the macro base station side edge device stability requirement are met if the third source SBS side edge device corresponding to the mth value is in sleep mode, 1≤m≤2×n, and n is the number of at least one third source SBS side edge device;

[0063] The first determination submodule is used to use the third source SBS side edge device corresponding to the mth value as the second source SBS side edge device if the cloud stability requirement and the macro base station side edge device stability requirement are met.

[0064] In a third aspect, an embodiment of the present invention provides a service processing device, applied to an SDN controller, comprising: a processor and a transceiver;

[0065] The processor is used to determine a first source SBS side edge device that can be in sleep mode from an SBS side edge device queue; determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state; unload the service of the first source SBS side edge device, and use the target SBS side edge device to process the service of the first source SBS side edge device.

[0066] Wherein, the processor is further used for:

[0067] Calculating a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue;

[0068] Sorting the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate;

[0069] According to the sorting result, an SBS side edge device with a smaller service arrival rate is selected from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

[0070] Wherein, the processor is further used for:

[0071] Calculate the first parameter;

[0072] obtaining the first value using the first parameter;

[0073] The first parameter is calculated as follows:

[0074]

[0075] Among them, N * represents the first parameter, λ SDN_total is the sum of the service arrival rates of each SBS-side edge device in the SBS-side edge device queue, μ SDN_total is the sum of the service leaving rates of each SBS side edge device in the SBS side edge device queue, g is the second parameter, and is We can obtain Φ(g) and φ(g) represents the cumulative function and probability density function of the standard normal distribution, and ε represents the probability threshold;

[0076] The first value is calculated using the following formula:

[0077]

[0078] Among them, k SDN_off represents the first value, n k represents the sum of the number of servers included in each SBS side edge device in the SBS side edge device queue, and K represents the number of SBS side edge devices in the SBS side edge device queue.

[0079] There are multiple first source SBS side edge devices; wherein the processor is further used for:

[0080] Sorting the plurality of first source SBS side edge devices according to the size of the service arrival rate;

[0081] For the kth first source SBS side edge device in the sorting result, select a first candidate SBS side edge device from the SBS side edge devices in the powered-on state;

[0082] Calculate the third parameter ρ k and the fourth parameter P k , the third parameter represents the queue delay threshold, and the fourth parameter represents the system stability;

[0083] If k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device of the kth first source SBS side edge device, and ε represents the probability threshold of service queuing waiting for processing.

[0084] Wherein, the processor is further used for:

[0085] When the number of first source SBS side edge devices currently in the sleep mode in the SBS side edge device queue is greater than the first value, determining a second source SBS side edge device in the SBS side edge device queue that can be in the sleep mode except the first source SBS side edge device;

[0086] The second source SBS side edge device is put to sleep, and the first type of service flow of the second source SBS side edge device is transferred to the cloud for processing, and the second type of service flow of the second source SBS side edge device is transferred to the macro base station MBS side edge device for processing.

[0087] Wherein, the processor is further used for:

[0088] For at least one third source SBS side edge device in the SBS side edge device queue except the first source SBS side edge device, a first probability and a second probability are calculated; the first probability is the probability that the first type of service of the third source SBS side edge device is queued in the cloud queue, and the second probability is the probability that the second type of service of the third source SBS side edge device is queued in the MBS queue;

[0089] sorting the at least one third source SBS side edge device according to the first probability and the second probability of the at least one third source SBS side edge device;

[0090] For the mth value in the sorting result, determine whether the cloud stability requirement and the macro base station side edge device stability requirement are met if the third source SBS side edge device corresponding to the mth value is in sleep mode, 1≤m≤2×n, where n is the number of at least one third source SBS side edge device;

[0091] If the cloud stability requirements and the macro base station side edge device stability requirements are met, the third source SBS side edge device corresponding to the mth value is used as the second source SBS side edge device.

[0092] In a fourth aspect, an embodiment of the present invention further provides a communication device, comprising: a transceiver, a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method described in the first aspect above are implemented.

[0093] In a fifth aspect, an embodiment of the present invention further provides a readable storage medium, on which a program is stored, and when the program is executed by a processor, the steps in the method described in the first aspect above are implemented.

[0094] In the embodiment of the present invention, the SDN controller can determine the first source SBS side edge device that can be in sleep mode in the SBS side edge device queue, unload its service, and use the target SBS side edge device to process the service of the first source SBS side edge device. Therefore, through the solution of the embodiment of the present invention, the SBS side edge device can be put into sleep mode as much as possible from a global perspective, thereby minimizing energy consumption and achieving the purpose of energy saving and power saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] Figure 1 It is one of the structural diagrams of the business processing system provided by the embodiment of the present invention;

[0096] Figure 2 This is the second structural diagram of the business processing system provided by the embodiment of the present invention;

[0097] Figure 3This is the third structural diagram of the business processing system provided by the embodiment of the present invention;

[0098] Figure 4 It is an SBS service processing queue model provided by an embodiment of the present invention;

[0099] Figure 5 It is a cloud service processing queuing model provided by an embodiment of the present invention;

[0100] Figure 6 It is an SBS service processing model assisted by SDN provided by an embodiment of the present invention;

[0101] Figure 7 is a relationship curve between g and ε provided in an embodiment of the present invention;

[0102] Figure 8 This is one of the flow charts of the service processing method provided by the embodiment of the present invention;

[0103] Fig. 9 This is the second flowchart of the service processing method provided by the embodiment of the present invention;

[0104] Fig.10 is a schematic diagram of step 901 in the service processing method provided by an embodiment of the present invention;

[0105] Fig.11 is a schematic diagram of step 902 in the service processing method provided by an embodiment of the present invention;

[0106] Fig.12 is a schematic diagram of step 903 in the service processing method provided in an embodiment of the present invention;

[0107] Fig.13 It is one of the structural diagrams of the service processing device provided by the embodiment of the present invention;

[0108] Fig.14 This is the second structural diagram of the business processing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0109] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0110] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0111] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0112] See also Figure 1 , Figure 1 1 is a structural diagram of a service processing system provided by an embodiment of the present invention. An SDN controller 101 and at least one SBS side edge device 102 are provided.

[0113] Wherein, the SDN controller is used for:

[0114] Determining a first source SBS side edge device capable of being in sleep mode from the SBS side edge device queue;

[0115] Determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state;

[0116] The service of the first source SBS side edge device is unloaded, and the service of the first source SBS side edge device is processed by using the target SBS side edge device.

[0117] In the embodiment of the present invention, the SDN controller can determine the first source SBS side edge device that can be in sleep mode in the SBS side edge device queue, unload its service, and use the target SBS side edge device to process the service of the first source SBS side edge device. Therefore, through the solution of the embodiment of the present invention, the SBS side edge device can be put into sleep mode as much as possible from a global perspective, thereby minimizing energy consumption and achieving the purpose of energy saving and power saving.

[0118] Further, combined with Figure 2 The system of the embodiment of the present invention may further include: an MBS side edge device 103 and a cloud 104 .

[0119] The SDN controller 101 is also used for: when the number of first source SBS side edge devices currently in sleep mode in the SBS side edge device queue is greater than a first value, determining a second source SBS side edge device in the SBS side edge device queue that can be in sleep mode except the first source SBS side edge device; putting the second source SBS side edge device into sleep mode, and transferring the first type of service flow of the second source SBS side edge device to the cloud for processing, and transferring the second type of service flow of the second source SBS side edge device to the MBS side edge device for processing; the first value is used to represent the maximum value of the first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue;

[0120] MBS side edge device 103, configured to process the first type of service of the second source SBS side edge device;

[0121] The cloud 104 is used to process the second type of business of the second source SBS side edge device.

[0122] Among them, the first type of business may include non-computing business (such as voice calls), etc.; the second type of business may include computing business (such as VR, video surveillance, etc.).

[0123] Therefore, in the embodiment of the present invention, not only can the energy-saving strategy be deployed from a global perspective, but energy saving can also be performed from the perspectives of the communication layer and the computing layer, thereby further saving power consumption.

[0124] With the continuous advancement of 5G commercialization, the number of mobile smart devices in different application fields such as Internet of Vehicles, high-definition live broadcast, industrial control, and interactive games has exploded, and these mobile smart devices have put forward higher requirements on network capabilities. They not only require lower service latency, but also consume a large amount of computing resources, which undoubtedly brings a great burden to traditional networks with relatively limited resources. In view of this, the fog computing network system effectively solves the problem of insufficient computing and processing capabilities. In contrast, fog computing does not rely on remote servers in central locations, but uses distributed computing resources close to local devices, so that mobile terminals can process data and applications on local devices. The introduction of fog computing provides good technical and architectural support for the growing business needs.

[0125] In addition, energy consumption is considered to be one of the main challenges faced by communication network construction. The large-scale connection of 5G is bound to lead to higher energy consumption. The power consumption of a 5G single station is about 2.5 to 3.5 times that of a 4G single station. Doubled energy consumption means doubled electricity bills, which will greatly increase the operating pressure of operators. Therefore, 5G power consumption control is an issue that operators and equipment manufacturers need to solve urgently. At present, most studies on power consumption control only consider energy-saving strategies in a single communication system (macro base station, micro base station) or computing system (edge ​​device, cloud). Relatively limited research focuses on the joint service scheduling of communication and computing systems, and the deployment and implementation are difficult. At the same time, the introduction of new SDN technologies has provided new impetus for operators' transformation in business and ecology. SDN realizes end-to-end intelligent scheduling of network resources between different base station devices through collaborative orchestration, reshapes the coupling degree between network equipment and services, and realizes the intelligence and openness of the network.

[0126] Based on this, the embodiment of the present invention proposes an energy-saving method based on SDN-assisted fog computing network architecture. Figure 3 , Figure 3 Another system architecture diagram of an embodiment of the present invention is shown, Ψ = {1, 2, 3, ..., K} (K is an integer) is a set of SBS side edge devices for connecting mobile smart devices, and any SBS side edge device k∈Ψ can be controlled by the SDN controller to flexibly schedule and allocate services. The MBS side edge device is connected to K SBS side edge devices, and one side is connected to the cloud public network.

[0127] exist Figure 3 In the system shown, the transfer of business flows under the fog computing architecture can be divided into two categories:

[0128] Method 1: Transfer of service flows between SBSs based on SDN. Figure 3 The service flow transfer direction is shown by the dotted lines 31 and 32. The service in the source SBS side edge device is transferred to the destination SBS side edge device for processing through SDN. Since the source SBS side edge device is in an idle state, the source SBS side edge device can be put into sleep mode at this time.

[0129] Method 2: In order to ensure the service latency and stability of the edge devices on the SBS side, if the transfer of the service flow between the edge devices on the SBS side reaches the limit, the service flow belonging to a certain edge device on the SBS side can be transferred to the MBS. The services that need to be transferred can be divided into computing services and non-computing services. Among them, computing services (VR, video surveillance, etc.) are uploaded to the cloud through MBS to process the services. The direction of service flow transfer is shown by the dotted line 34 in 3; non-computing services (voice calls) are no longer transferred, and the services are directly processed in the edge devices on the MBS side. The direction of service flow transfer is shown by the dotted line 33 in the figure. At this time, the idle SBS can be put into sleep mode.

[0130] Among them, any SBS side edge device k∈Ψ can be modeled as an M / M / n queuing system with n servers. For the kth SBS side edge device, λ k , μ k 、n k They are service arrival rate, service departure rate, and number of servers respectively. Figure 4 The figure shows the SBS business processing queue model.

[0131] The utilization rate of the edge device at the kth SBS side ρ k It can be expressed as:

[0132]

[0133] The probability that a service needs to queue up for processing at the kth SBS-side edge device is:

[0134]

[0135] Among them, π i represents the steady-state probability that the i-th server is busy. The steady-state probability that there is no service in the k-th SBS can be expressed as:

[0136]

[0137] Therefore, the average queue delay of the k-th SBS side edge device is:

[0138]

[0139] Similar to the SBS side edge device, in the embodiment of the present invention, the cloud server under the fog computing network architecture is modeled as an M / M / d queuing system with d servers. Figure 5 Processing queuing models for cloud services.

[0140] The total service arrival rate λ in the cloud queuing model C for:

[0141]

[0142] Where K is the number of SBS devices, k SDN_off is the number of SBS-side edge devices that are in sleep mode due to service transfer between SBSs, is the proportion of computing services on the edge device at the i-th SBS side. Non-computing services can be directly transmitted via MBS without uploading to the cloud for processing. i The value is 0 or 1, indicating whether the ith SBS side edge device is in working state (xi=1) or in sleeping state (xi=0); i Indicates the service arrival rate of the edge device on the i-th SBS side.

[0143] The utilization rate of the cloud queuing system is:

[0144]

[0145] Where 0≤ρ c ≤1,λ c , μ c d c They are the service arrival rate, service departure rate, and number of servers of the cloud system.

[0146] Similar to the SBS queue system, the probability that a business needs to queue in the cloud queue system for processing is expressed as:

[0147]

[0148] Among them, π i represents the steady-state probability that the i-th server is busy, d = d c .

[0149] The steady-state probability that there is no business in the cloud system can be expressed as:

[0150]

[0151] Therefore, the average queue delay of services in the cloud system can be calculated as

[0152]

[0153] Assume that the power consumption of each SBS device is P SBS According to the system model, before the service flow is transferred, there are K SBSs in the system in the power-on mode. In the above-mentioned method, the service flow transfer can make k SDN_off SBS is in sleep mode, as described above, the second service flow transfer can make k N_cIf an SBS is in sleep mode, then energy saving can be achieved by transferring the business load of an SBS-side edge device to other adjacent devices and shutting down the SBS and related supporting edge devices in idle state. This method can save power consumption as follows:

[0154] P save =P SBS (k N_c +k SDN_off ) (10)

[0155] From the network model described above, we can see that there are two ways to transfer services in SBS. The first way is to transfer service flows between SBS-side edge devices based on SDN. The second way is to upload the computing service flows in the SBS-side edge devices to the cloud for processing through MBS. The modeling process of the two problems is described below.

[0156] (1) Problem modeling in method 1:

[0157] The total power consumption of the edge device on the SBS side is expressed as:

[0158]

[0159] Among them, P SBS Indicates the power consumed by each SBS side edge device; x k ∈{0, 1} indicates whether the SBS side edge device is in the power-on mode, x k The value is 0 for sleep mode and 1 for power-on mode.

[0160] In method 1, in order to ensure lower service delay and save energy in the entire system to the maximum extent, under the premise of maintaining the stability of the queuing system, the goal is to make the waiting probability of services in each SBS lower than a certain set threshold, so that as many SBS devices as possible are in sleep mode. In summary, the above problem can be described by P1:

[0161]

[0162]

[0163]

[0164]

[0165] Among them, the purpose of constraint A1 is to ensure that the service queuing probability of K SBS side edge devices is guaranteed to be below a certain threshold to ensure service delay. The purpose of constraint A2 is to ensure the stability of K SBS side edge devices. The purpose of constraint A3 is to indicate that the K SBS side edge devices are in power-on / sleep mode.

[0166] (2) Problem modeling in method 2:

[0167] The probability of business queuing for processing in the cloud system is expressed as:

[0168]

[0169] Among them, P(s i ) is the probability that the ith SBS-side edge device is in shutdown mode. Here, it is assumed that all SBS-side edge devices have the same probability of being in shutdown mode, that is, P(C|s i ) is the probability that the corresponding service needs to queue in the cloud queue when the i-th SBS-side edge device is in shutdown mode. The specific expression is as follows:

[0170]

[0171] in, is the utilization of the cloud system when the edge device on the i-th SBS side is in shutdown mode.

[0172] Correspondingly, when the i-th SBS-side edge device is in shutdown mode, the probability that the corresponding service needs to queue in the MBS queue is:

[0173]

[0174] Similar to the first method, this method uploads the computing services in the SBS to the cloud, so that the SBS processing the services is in sleep mode, thereby saving power consumption in the system to the maximum extent.

[0175] The problem can be described by P2:

[0176]

[0177] Subject to:A1:0≤ρ c ≤1,

[0178]

[0179]

[0180]

[0181] In this embodiment of the present invention, MBS is modeled as an M / M / dMBS queuing system, λ MBS , μ MBS d MBSThey are the service arrival rate, service departure rate, and number of servers on the MBS side. The purpose of constraints A1, A2, and A3 is to ensure the stability of the servers on the cloud side, MBS side, and SBS side, respectively, that is, to ensure that the utilization of the cloud side, MBS side, and SBS side systems is not greater than 1. The purpose of constraint A4 is to indicate that k servers are in power-on / sleep mode.

[0182] Since both P1 and P2 are binary integer nonlinear programming problems, the solution process is complicated. Therefore, in order to solve the above problems, an energy-saving algorithm based on SDN-assisted fog computing network architecture is proposed in the embodiment of the present invention. Based on SDN assistance, resources between all SBS servers can be shared. The SBS service processing model under SDN assistance proposed in the embodiment of the present invention is as follows: Figure 6 As shown in the figure, the queuing system of K edge devices can be modeled as an M / M / N queuing system. Through SDN, unified scheduling of network resources can be achieved. SBSs can cooperate with each other under the control of the SDN controller to process the services, thereby reducing the queuing delay of the services.

[0183] In the service queuing processing model assisted by SDN, the service arrival rate, service departure rate, and number of servers are μ SDN_total =μ k ,

[0184] Solve the power minimization problem P1, that is, solve the minimum number of servers that meet the above constraints (delay and stability constraints). According to the number of servers that can meet a queue probability less than ε, it can be obtained as:

[0185]

[0186] And g can be obtained by the equation:

[0187]

[0188] Among them, Φ(g) and φ(g) represent the cumulative function and probability density function of the standard normal distribution respectively. Through the above formula, the relationship curve between g and ε can be drawn, as shown in Figure 7 As shown. Therefore, by determining ε, g can be obtained accordingly.

[0189] Therefore, the maximum number of SBSs in sleep mode can be obtained as:

[0190]

[0191] Next, when solving the power minimization problem P2, we need to ensure that the queuing delay of the service is as small as possible, so we need to calculate the remaining KkSDN_off P(C|s i )、P(M|s i ) are arranged in ascending order, with priority given to P(C|s i )、P(M|s i ) small SBS queue to transfer services and ensure the stability of MBS and cloud systems after the services in SBS are transferred to MBS and cloud. Thus, the maximum number of SBSs in sleep mode that can be solved is k N_C .

[0192] Finally, the total number of SBSs that can be in sleep mode under the two traffic flow transfer modes can be calculated, which is k SDN_off +k N_c .

[0193] Based on the above principles, see Figure 8 , Figure 8 is a flow chart of a service processing method provided by an embodiment of the present invention, which is applied to an SDN controller, such as Figure 8 As shown, the following steps are included:

[0194] Step 801: Determine a first source SBS side edge device that can be in sleep mode from a SBS side edge device queue.

[0195] Specifically, in this step, a first value is calculated, and the first value is used to represent the maximum value of the first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue. Then, the SBS side edge devices in the SBS side edge device queue are sorted according to the size of the service arrival rate. Finally, according to the sorting result, the SBS side edge device with a smaller service arrival rate is selected from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

[0196] For example, the SBS side edge devices in the SBS side edge device queue are sorted from small to large according to the service arrival rate, and a corresponding number of SBS side edge devices are selected from the sorting result according to the first value as the first source SBS side edge devices.

[0197] The first value can be calculated using formula (19). Accordingly, in this step, the first parameter is calculated, and the first value is obtained using the first parameter. The first parameter is obtained using formula (17).

[0198] Step 802: Determine a target SBS-side edge device that matches the first source SBS-side edge device, wherein the target SBS-side edge device is determined to be an SBS-side edge device that is in a powered-on state.

[0199] In an embodiment of the present invention, the first source SBS side edge device is multiple, such as more than 2. Then, in this step, the multiple first source SBS side edge devices are sorted according to the size of the service arrival rate. For the kth first source SBS side edge device in the sorting result, a first candidate SBS side edge device is selected from the SBS side edge devices that are in the powered-on state. Calculate the third parameter ρ k and the fourth parameter P k , the third parameter represents the queue delay threshold, and the fourth parameter represents the system stability. k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device of the kth first source SBS side edge device, and ε represents the probability threshold of service queuing waiting for processing.

[0200] For example, the plurality of first source SBS side edge devices are sorted in ascending order of service arrival rate. Starting from the first source SBS side edge device with the smallest service arrival rate, it is adapted to any one of the SBS side edge devices in the power-on state (i.e., the first candidate SBS side edge device) in the above manner. If ρ is calculated at this time k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device. Otherwise, other SBS side edge devices in the power-on state may be selected for adaptation. The third parameter ρ k and the fourth parameter P k It can be calculated by referring to the above formula (1) and formula (2) respectively.

[0201] Step 803: Unload the service of the first source SBS side edge device, and use the target SBS side edge device to process the service of the first source SBS side edge device.

[0202] In the embodiment of the present invention, the SDN controller can determine the first source SBS side edge device that can be in sleep mode in the SBS side edge device queue, unload its service, and use the target SBS side edge device to process the service of the first source SBS side edge device. Therefore, through the solution of the embodiment of the present invention, the SBS side edge device can be put into sleep mode as much as possible from a global perspective, thereby minimizing energy consumption and achieving the purpose of energy saving and power saving.

[0203] In order to further save power, based on the above embodiment, when the number of first source SBS side edge devices currently in sleep mode in the SBS side edge device queue is greater than the first value, a second source SBS side edge device in the SBS side edge device queue that can be in sleep mode other than the first source SBS side edge device is determined. Afterwards, the second source SBS side edge device can be put into sleep mode, and the first type of service flow of the second source SBS side edge device is transferred to the cloud for processing, and the second type of service flow of the second source SBS side edge device is transferred to the macro base station MBS side edge device for processing.

[0204] Specifically, when determining the second source SBS side edge device in the SBS side edge device queue that can be in the sleep mode except the first source SBS side edge device, the following steps may be included:

[0205] (1) For at least one third source SBS side edge device in the SBS side edge device queue except the first source SBS side edge device, a first probability and a second probability are calculated; the first probability is the probability that the first type of service of the third source SBS side edge device is queued in the cloud queue, and the second probability is the probability that the second type of service of the third source SBS side edge device is queued in the MBS queue.

[0206] The calculation method of the first probability and the second probability can refer to the above formulas (14) and (15).

[0207] (2) Sort the at least one third source SBS side edge device according to the first probability and the second probability of the at least one third source SBS side edge device.

[0208] Assuming there are three third-source SBS side edge devices (A, B, C), then the first probability and the second probability are combined to rank the three third-source SBS side edge devices. Since there are two ranking parameters (three third-source SBS side edge devices correspond to 6 values), each third-source SBS side edge device may be ranked twice, that is, it is possible to form an rank result of A, B, C, B, C, A.

[0209] (3) For the mth value in the sorting result, determine whether the cloud stability requirements and the macro base station side edge device stability requirements are met if the third source SBS side edge device corresponding to the mth value is in sleep mode, 1≤m≤2×n, n is the number of at least one third source SBS side edge device.

[0210] (4) If the cloud stability requirement and the macro base station side edge device stability requirement are met, the third source SBS side edge device corresponding to the mth value is used as the second source SBS side edge device.

[0211] The implementation scheme of the embodiment of the present invention is described in detail below.

[0212] See also Fig. 9 , Fig. 9 is a flow chart of a service processing method provided by an embodiment of the present invention, such as Fig. 9 As shown, the following steps are included:

[0213] Step 901, calculate the first number of SBS side edge devices that can be in sleep mode when the service flow is transferred between SBS side edge devices. Rearrange the SBS side edge devices in the system that are powered on in order from small to large according to the service load, and unload the services of the selected SBS side edge devices in turn, so that the corresponding SBS side edge devices enter the sleep mode. The number of SBS side edge devices with unloaded services is the first number.

[0214] It is known that the service arrival rates of the edge devices on the SBS side are λ1, λ2, ..., λ K , service leaving rate μ, number of servers d, service queue waiting probability threshold ε; MBS side service arrival rate λ MBS , service leaving rate μ MBS , Number of MBS-side servers d MBS , cloud-side service arrival rate λ c , service leaving rate μ c 、Number of cloud servers c ; SBS quantity K.

[0215] Defining λ depature is the service arrival rate set of the service flow transferred from the source SBS side edge device to another SBS side edge device. Since in the initial state of the system, all SBS side edge devices in the system are in the power-on state, the initialization λ depature An empty collection.

[0216] According to the above formulas (17) and (19), the number of servers N that satisfy the queue probability less than ε is calculated respectively. * , the number of SBS-side edge devices that can be in sleep mode when traffic is transferred between SBSs SDN_off . Since the edge devices on the SBS side are all powered on in the original state, there are: x k =1,

[0217] K SDN_off The services waiting to be processed in the edge devices on the SBS side in sleep mode are placed in depature In the collection, use the following for loop to implement it.

[0218] Initialize k=1;

[0219] for k≤k SDN_off

[0220] Find the minimum service arrival rate λ from K SBS-side edge devices min , The corresponding SBS index is k;

[0221] Set the SBS side edge device state corresponding to the minimum service arrival rate to sleep mode, x k =0;

[0222] λ min Remove from the service arrival rate set, Ψ = Ψ - {k};

[0223] λ depature =λ depature +{λ min};

[0224] k = k + 1;

[0225] end for;

[0226] In the above process, when the service flow is transferred between the edge devices on the SBS side, the number of SBSs that can be in sleep mode is calculated. SDN_off First, k is initialized to 1, and when k is less than the number of SBSs that can be in sleep mode k SDN_of f, combined Fig.10 , execute the following strategy:

[0227] (1) Find the minimum service arrival rate λ from K SBS-side edge devices min , The corresponding SBS index is k;

[0228] (2) The SBS side edge device state corresponding to the minimum service arrival rate is set to sleep mode, that is, xk is set to 0;

[0229] (3) min Remove from the service-to-service arrival rate set, Ψ = Ψ - {k} and λ depature The empty set marked as unloaded traffic, with each cycle, there will be a new minimum traffic rate λ min Add to the set; when k is greater than k SDN_off When the above strategy is stopped.

[0230] At this time, the SBS-side edge devices in the system that are in sleep state have been arranged in ascending order according to the service load. depatureIt is the set of service arrival rates corresponding to all SBS-side edge devices in sleep mode.

[0231] Step 902: adapt the unloaded service to other SBS-side edge devices in the system that are in the powered-on state. Under the conditions of satisfying the queue queuing delay and system stability, adapt the unloaded service to the service processing queue of the corresponding SBS-side edge device in the powered-on state through SDN, and the adapted SBS-side edge device processes the unloaded service.

[0232] In this step, the services in the SBS side edge device in the dormant state are rearranged in ascending order according to the service arrival rate values. depature The unloaded services in the set are adapted to other SBS side edge devices in the open state, and these unloaded services are processed under the conditions of satisfying the queue delay and system stability. This step is implemented using the following for loop.

[0233] Initialize k=1;

[0234]

[0235] Defining λ q ∈λ depature ;

[0236] &P k <ε

[0237] λ k =λ q +λ k ;

[0238] λ q From λ depature Remove from the set, λ depature =λ depature -{λ q};

[0239] else

[0240] k = k + 1;

[0241] end if

[0242] end for;

[0243] In the above process, combined with Fig.11 , the offloading service needs to be compatible with other SBS-side edge devices in the open state. depature When the unloaded business in the collection is not empty, that is, λ depatureThe minimum value of the service arrival rate in the SBS is adapted to the SBS side edge device with the minimum service arrival rate in operation. The adaptation condition is to meet the queue delay And the system stability P k If the condition is met, the adapted service is processed by the SBS with the smallest service arrival rate. The service arrival rate of the SBS with the smallest service arrival rate is: the sum of the arrival rate of the unloaded service and the original service arrival rate that the SBS with the smallest service arrival rate should process, that is, λ k =λ q +λ k If the above queue delay and system stability requirements are not met, other SBS-side edge devices that are powered on need to be selected to process the offloaded service. depature All the unloading services in the process will be adapted to the SBS side edge devices that are in the powered-on state.

[0244] Step 903: The service flow is transferred from the SBS side edge device to the MBS, wherein computing services are uploaded to the cloud for processing, and non-computing services are processed and transmitted in the MBS. Under the condition that the stability of the MBS and cloud queue systems is met, it is determined that the SBS side edge device corresponding to the service flow can be placed in sleep mode.

[0245] In order to ensure the service delay and the stability of the edge devices on the SBS side, the transfer of service flows between SBSs reaches the limit, that is, the number of SBSs in sleep mode is k. SDN_off In order to further save system power consumption, the transfer mode of the service flow is changed to the second mode in the above network model. The specific steps are as follows.

[0246] Through the for loop, the queue probability of the service in the SBS in the cloud queue is calculated if the SBS is in sleep mode.

[0247] Initialize i=1

[0248] for i≤Kk SDN_off

[0249] According to equations (14) and (15), the probability of a service queuing in the cloud queue P(C|s i ), the probability that the service needs to queue in the MBS queue P(M|s i );

[0250] i=i+1;

[0251] end for;

[0252] According to P(C|s i) and P(M|s i ) are rearranged in ascending order by the Ψ obtained in the previous step; under the condition that the stability of the MBS and cloud queue system is satisfied, it is determined whether the corresponding SBS can be put into sleep mode, and the number k of SBSs in sleep mode under this method is calculated. N_c .

[0253] Initialize j = 1; x k =1, k N_c =0;

[0254] for j≤Kk SDN_off

[0255]

[0256] x t =0; k N_c =k N_c +1;

[0257] else

[0258] x t =1

[0259] else if;

[0260] end for;

[0261] Combination Fig.12 , initialize i=1, if i≤Kk SDN_off According to formulas (14) and (15), the probability of a service queuing in the cloud queue P(C|s i ), the probability that the service needs to queue in the MBS queue P(M|s i ). Otherwise, according to P(C|s i ) and P(M|s i ) are rearranged in ascending order by the Ψ obtained in the previous step. Initialize j = 1. If j ≤ Kk SDN_off , then judge as well as Is it true? If true, the corresponding SBS side edge device is put into sleep mode and the count value is increased by 1. If not true, the next judgment can be made, or the process ends.

[0262] It can be seen from the above description that in the embodiment of the present invention, there are two ways to transmit services: mode one is to transfer services between SBSs, and mode two is to transfer services from SBSs to MBSs, wherein computing services need to be uploaded to the cloud for processing, and the remaining non-computing services are processed in the MBS. In this way, the SBS micro base station can be put into sleep mode as much as possible, thereby minimizing energy consumption and achieving the purpose of energy saving and power saving. In addition, the embodiment of the present invention not only considers the transmission between service flows at the communication layer, but also considers that computing services at the computing layer need to be uploaded to the cloud for processing. Therefore, the embodiment of the present invention is suitable for energy saving at both the communication layer and the computing layer.

[0263] In the embodiment of the present invention, based on SDN, the queuing system of multiple edge devices is regarded as an M / M / N queuing system, in which the SDN controller can uniformly schedule network resources. The SBSs can cooperate with each other under the control of the SDN controller to process services. Therefore, the method can deploy strategies from a global network perspective and enhance the accuracy and reliability of energy-saving operations performed by the base station itself based on its own energy-saving strategy.

[0264] The embodiment of the present invention also provides a service processing device, which is applied to an SDN controller. Fig.13 , Fig.13 Since the principle of solving the problem by the service processing device is similar to that of the service processing method in the embodiment of the present invention, the implementation of the service processing device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0265] like Fig.13 As shown, the service processing device 1300 includes:

[0266] The first determination module 1301 is used to determine a first source SBS side edge device that can be in sleep mode from the SBS side edge device queue; the second determination module 1302 is used to determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in the power-on state; the first processing module 1303 is used to unload the service of the first source SBS side edge device, and use the target SBS side edge device to process the service of the first source SBS side edge device.

[0267] Wherein, the first determining module includes:

[0268] A first calculation submodule, configured to calculate a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in a sleep mode in the SBS side edge device queue;

[0269] A first sorting submodule is used to sort the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate;

[0270] The first determination submodule is configured to select, according to the sorting result, an SBS side edge device with a smaller service arrival rate from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

[0271] Wherein, the first calculation submodule is used to calculate a first parameter; and obtain the first value using the first parameter;

[0272] The first parameter is calculated as follows:

[0273]

[0274] Among them, N * represents the first parameter, λ SDN_total is the sum of the service arrival rates of each SBS-side edge device in the SBS-side edge device queue, μ SDN_total is the sum of the service leaving rates of each SBS side edge device in the SBS side edge device queue, g is the second parameter, and is We can obtain Φ(g) and φ(g) represents the cumulative function and probability density function of the standard normal distribution, and ε represents the probability threshold;

[0275] The first value is calculated using the following formula:

[0276]

[0277] Among them, k SDN_off represents the first value, n k represents the sum of the number of servers included in each SBS side edge device in the SBS side edge device queue, and K represents the number of SBS side edge devices in the SBS side edge device queue.

[0278] There are multiple first source SBS side edge devices; and the second determination module includes:

[0279] A first sorting submodule, used to sort the plurality of first source SBS side edge devices according to the size of the service arrival rate;

[0280] A first selection submodule, configured to select, for the kth first source SBS side edge device in the sorting result, a first candidate SBS side edge device from the SBS side edge devices in the powered-on state;

[0281] The first calculation submodule is used to calculate the third parameter ρ k and the fourth parameter P k , the third parameter represents the queue delay threshold, and the fourth parameter represents the system stability;

[0282] The first determination submodule is used if ρ k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device of the kth first source SBS side edge device, and ε represents the probability threshold of service queuing waiting for processing.

[0283] Wherein, the device further comprises:

[0284] A third determination module is used to determine a second source SBS side edge device in the SBS side edge device queue that can be in the sleep mode except the first source SBS side edge device when the number of the first source SBS side edge devices currently in the sleep mode in the SBS side edge device queue is greater than the first value;

[0285] The second processing module is used to put the second source SBS side edge device into sleep mode, transfer the first type of business flow of the second source SBS side edge device to the cloud for processing, and transfer the second type of business flow of the second source SBS side edge device to the macro base station MBS side edge device for processing.

[0286] Wherein, the third determination module includes:

[0287] A first calculation submodule is used to calculate a first probability and a second probability for at least one third source SBS side edge device in the SBS side edge device queue except the first source SBS side edge device; the first probability is the probability that the first type of service of the third source SBS side edge device is queued in the cloud queue, and the second probability is the probability that the second type of service of the third source SBS side edge device is queued in the MBS queue;

[0288] A first sorting submodule, configured to sort the at least one third source SBS side edge device according to the first probability and the second probability of the at least one third source SBS side edge device;

[0289] A first judgment submodule is used to judge, for the mth value in the sorting result, whether the cloud stability requirement and the macro base station side edge device stability requirement are met if the third source SBS side edge device corresponding to the mth value is in sleep mode, 1≤m≤2×n, and n is the number of at least one third source SBS side edge device;

[0290] The first determination submodule is used to use the third source SBS side edge device corresponding to the mth value as the second source SBS side edge device if the cloud stability requirement and the macro base station side edge device stability requirement are met.

[0291] The device provided in the embodiment of the present invention can execute the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0292] The embodiment of the present invention also provides a service processing device, which is applied to an SDN controller. Fig.14 , Fig.14 Since the principle of solving the problem by the service processing device is similar to that of the service processing method in the embodiment of the present invention, the implementation of the service processing device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0293] like Fig.14 As shown, the terminal device 1400 includes: a processor 1401 and a transceiver 1402 .

[0294] The processor is used to determine a first source SBS side edge device that can be in sleep mode from an SBS side edge device queue; determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state; unload the service of the first source SBS side edge device, and use the target SBS side edge device to process the service of the first source SBS side edge device.

[0295] Wherein, the processor is further used for:

[0296] Calculating a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue;

[0297] Sorting the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate;

[0298] According to the sorting result, an SBS side edge device with a smaller service arrival rate is selected from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

[0299] Wherein, the processor is further used for:

[0300] Calculate the first parameter;

[0301] obtaining the first value using the first parameter;

[0302] The first parameter is calculated as follows:

[0303]

[0304] Among them, N * represents the first parameter, λ SDN_total is the sum of the service arrival rates of each SBS-side edge device in the SBS-side edge device queue, μ SDN_total is the sum of the service leaving rates of each SBS side edge device in the SBS side edge device queue, g is the second parameter, and is We can obtain Φ(g) and φ(g) represents the cumulative function and probability density function of the standard normal distribution, and ε represents the probability threshold;

[0305] The first value is calculated using the following formula:

[0306]

[0307] Among them, k SDN_off represents the first value, n k represents the sum of the number of servers included in each SBS side edge device in the SBS side edge device queue, and K represents the number of SBS side edge devices in the SBS side edge device queue.

[0308] There are multiple first source SBS side edge devices; wherein the processor is further used for:

[0309] Sorting the plurality of first source SBS side edge devices according to the size of the service arrival rate;

[0310] For the kth first source SBS side edge device in the sorting result, select a first candidate SBS side edge device from the SBS side edge devices in the powered-on state;

[0311] Calculate the third parameter ρ k and the fourth parameter P k , the third parameter represents the queue delay threshold, and the fourth parameter represents the system stability;

[0312] If k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device of the kth first source SBS side edge device, and ε represents the probability threshold of service queuing waiting for processing.

[0313] Wherein, the processor is further used for:

[0314] When the number of first source SBS side edge devices currently in sleep mode in the SBS side edge device queue is greater than the first value, determining second source SBS side edge devices in the SBS side edge device queue that can be in sleep mode except the first source SBS side edge device;

[0315] The second source SBS side edge device is put to sleep, and the first type of service flow of the second source SBS side edge device is transferred to the cloud for processing, and the second type of service flow of the second source SBS side edge device is transferred to the macro base station MBS side edge device for processing.

[0316] Wherein, the processor is further used for:

[0317] For at least one third source SBS side edge device in the SBS side edge device queue except the first source SBS side edge device, a first probability and a second probability are calculated; the first probability is the probability that the first type of service of the third source SBS side edge device is queued in the cloud queue, and the second probability is the probability that the second type of service of the third source SBS side edge device is queued in the MBS queue;

[0318] sorting the at least one third source SBS side edge device according to the first probability and the second probability of the at least one third source SBS side edge device;

[0319] For the mth value in the sorting result, determine whether the cloud stability requirement and the macro base station side edge device stability requirement are met if the third source SBS side edge device corresponding to the mth value is in sleep mode, 1≤m≤2×n, where n is the number of at least one third source SBS side edge device;

[0320] If the cloud stability requirements and the macro base station side edge device stability requirements are met, the third source SBS side edge device corresponding to the mth value is used as the second source SBS side edge device.

[0321] The device provided in the embodiment of the present invention can execute the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0322] An embodiment of the present invention further provides a communication device, comprising: a transceiver, a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor implements the steps in the service processing method described above when executing the program.

[0323] The embodiment of the present invention also provides a readable storage medium, on which a program is stored. When the program is executed by a processor, each process of the above-mentioned business processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disk, hard disk, magnetic tape, magneto-optical disk (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid state drive (SSD)), etc.

[0324] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0325] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD), and includes a number of instructions for a terminal (which can be a mobile phone, computer, server, air conditioner, or network equipment, etc.) to execute the methods described in each embodiment of the present invention.

[0326] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A service processing method, applied to a software defined network (SDN) controller, characterized in that: include: Determine a first source SBS side edge device that can be in sleep mode from the micro base station SBS side edge device queue; Determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state; Unloading the service of the first source SBS side edge device, and using the target SBS side edge device to process the service of the first source SBS side edge device; The step of determining the first source SBS side edge device that can be in sleep mode from the micro base station SBS side edge device queue includes: Calculating a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue; Sorting the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate; According to the sorting result, an SBS side edge device with a smaller service arrival rate is selected from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

2. The method according to claim 1, characterized in that The calculating the first value comprises: Calculate the first parameter; obtaining the first value using the first parameter; The first parameter is calculated as follows: Among them, N * represents the first parameter, λ SDN_total is the sum of the service arrival rates of each SBS-side edge device in the SBS-side edge device queue, μ SDN_total is the sum of the service leaving rates of each SBS side edge device in the SBS side edge device queue, g is the second parameter, and is Find, Φ(g) and φ(g) represents the cumulative function and probability density function of the standard normal distribution, and ε represents the probability threshold; The first value is calculated using the following formula: Among them, k SDN_off represents the first value, n k represents the sum of the number of servers included in each SBS side edge device in the SBS side edge device queue, and K represents the number of SBS side edge devices in the SBS side edge device queue.

3. The method according to claim 1, characterized in that There are multiple first source SBS side edge devices; determining a target SBS side edge device matching the first source SBS side edge device includes: Sorting the plurality of first source SBS side edge devices according to the size of the service arrival rate; For the kth first source SBS side edge device in the sorting result, select a first candidate SBS side edge device from the SBS side edge devices in the powered-on state; Calculate the third parameter ρ k and the fourth parameter P k , the third parameter represents the queue delay threshold, and the fourth parameter represents the system stability; If k <1 and P k <ε, the first candidate SBS side edge device is used as the target SBS side edge device of the kth first source SBS side edge device, and ε represents the probability threshold of service queuing waiting for processing.

4. The method according to claim 1, characterized in that The method further comprises: When the number of first source SBS side edge devices currently in sleep mode in the SBS side edge device queue is greater than the first value, determining second source SBS side edge devices in the SBS side edge device queue that can be in sleep mode except the first source SBS side edge device; The second source SBS side edge device is put to sleep, and the first type of service flow of the second source SBS side edge device is transferred to the cloud for processing, and the second type of service flow of the second source SBS side edge device is transferred to the macro base station MBS side edge device for processing.

5. The method according to claim 4, characterized in that The determining a second source SBS side edge device in the SBS side edge device queue that can be in a sleep mode except the first source SBS side edge device includes: For at least one third source SBS side edge device in the SBS side edge device queue except the first source SBS side edge device, a first probability and a second probability are calculated; the first probability is the probability that the first type of service of the third source SBS side edge device is queued in the cloud queue, and the second probability is the probability that the second type of service of the third source SBS side edge device is queued in the MBS queue; sorting the at least one third source SBS side edge device according to the first probability and the second probability of the at least one third source SBS side edge device; For the mth value in the sorting result, determine whether the cloud stability requirement and the macro base station side edge device stability requirement are met if the third source SBS side edge device corresponding to the mth value is in sleep mode, 1≤m≤2×n, where n is the number of at least one third source SBS side edge device; If the cloud stability requirements and the macro base station side edge device stability requirements are met, the third source SBS side edge device corresponding to the mth value is used as the second source SBS side edge device.

6. A service processing device, applied to an SDN controller, characterized in that: include: A first determining module, configured to determine a first source SBS side edge device that can be in a sleep mode from a SBS side edge device queue; A second determination module is used to determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state; A first processing module, configured to unload the service of the first source SBS side edge device, and use the target SBS side edge device to process the service of the first source SBS side edge device; Wherein, the first determining module includes: A first calculation submodule, configured to calculate a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in a sleep mode in the SBS side edge device queue; A first sorting submodule is used to sort the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate; The first determination submodule is configured to select, according to the sorting result, an SBS side edge device with a smaller service arrival rate from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

7. A service processing device, applied to an SDN controller, characterized in that: include: processors and transceivers; The processor is used to determine a first source SBS side edge device that can be in a sleep mode from the SBS side edge device queue; Determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state; unload the service of the first source SBS side edge device, and use the target SBS side edge device to process the service of the first source SBS side edge device; Wherein, the processor is further used for: Calculating a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue; Sorting the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate; According to the sorting result, an SBS side edge device with a smaller service arrival rate is selected from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

8. A business processing system, characterized in that: include: SDN controller, at least one SBS-side edge device; Wherein, the SDN controller is used for: Determining a first source SBS side edge device capable of being in sleep mode from the SBS side edge device queue; Determine a target SBS side edge device that matches the first source SBS side edge device, wherein the target SBS side edge device is determined to be an SBS side edge device that is in a powered-on state; Unloading the service of the first source SBS side edge device, and using the target SBS side edge device to process the service of the first source SBS side edge device; Wherein, the SDN controller is also used for: Calculating a first value, where the first value is used to represent a maximum value of first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue; Sorting the SBS side edge devices in the SBS side edge device queue according to the size of the service arrival rate; According to the sorting result, an SBS side edge device with a smaller service arrival rate is selected from the SBS side edge device queue as the first source SBS side edge device, wherein the number of the first source SBS side edge devices is the first value.

9. The system according to claim 8, characterized in that Also included: MBS-side edge devices, cloud; The SDN controller is also used for: when the number of first source SBS side edge devices currently in sleep mode in the SBS side edge device queue is greater than a first value, determining a second source SBS side edge device in the SBS side edge device queue that can be in sleep mode except the first source SBS side edge device; putting the second source SBS side edge device into sleep mode, and transferring the first type of service flow of the second source SBS side edge device to the cloud for processing, and transferring the second type of service flow of the second source SBS side edge device to the MBS side edge device for processing; the first value is used to represent the maximum value of the first source SBS side edge devices that can be in sleep mode in the SBS side edge device queue; MBS side edge device, used for processing the first type of service of the second source SBS side edge device; The cloud end is used to process the second type of business of the second source SBS side edge device.

10. A communication device, comprising: A transceiver, a memory, a processor and a program stored in the memory and executable on the processor; wherein the processor is used to read the program in the memory to implement the steps in the service processing method as described in any one of claims 1 to 5.

11. A readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps in the business processing method according to any one of claims 1 to 5 are implemented.

Images