Network configuration method and apparatus, computer device and storage medium
By obtaining the time correlation information of data packets from the business flow and using a neural network model to automatically configure the industrial PON network, the problems of high manpower consumption and high cost in the existing technology are solved, and efficient and accurate network configuration is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER
- Filing Date
- 2024-09-30
- Publication Date
- 2026-06-23
Smart Images
Figure CN119402353B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of network communication technology, specifically to a network configuration method, apparatus, computer equipment, and storage medium. Background Technology
[0002] In industrial PON (Passive Optical Network) application scenarios (e.g., during communication between PN (ProfiNet, Industrial Ethernet) slave stations and PN master stations), different industrial services have different communication requirements for the communication network. It is necessary to configure the network for the communication network corresponding to different industrial services in order to meet the communication quality requirements of different industrial services.
[0003] The existing method requires statistical analysis of the needs of various industrial services, completion of network configuration, and additional hardware (e.g., ET2000, FPGA, etc.) to determine the latency jitter of each industrial service. Based on the latency jitter, the network configuration is then adjusted, and so on, until the network configuration is properly adjusted. Due to the large variety and complexity of industrial services, the traditional network configuration method not only requires a lot of manpower but also incurs high costs due to the additional hardware. Summary of the Invention
[0004] Therefore, it is necessary to provide a network configuration method, apparatus, computer equipment, and storage medium that can effectively improve network configuration efficiency in response to the above-mentioned technical problems.
[0005] Firstly, this application provides a network configuration method, which includes:
[0006] Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow;
[0007] Based on time-related information, determine the target latency jitter information for the target service;
[0008] Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0009] In one embodiment, the time-related information includes packet transmission frequency and / or packet transmission interval duration.
[0010] In one embodiment, the target latency jitter information of the target service is determined based on time-related information, including:
[0011] Get the data packet reception time of a preset number of target services consecutively up to the current time.
[0012] Based on the reception time and time correlation information of each data packet, the target latency jitter information of the target service is determined.
[0013] In one embodiment, the target latency jitter information of the target service is determined based on the reception time and time correlation information of each data packet, including:
[0014] Based on the reception time and time correlation information of each data packet, determine the historical latency jitter information of the target service;
[0015] Based on the second neural network, and according to historical latency jitter information, the future latency jitter information of the target service in the future time period is predicted;
[0016] Use future latency jitter information as the target latency jitter information for the target service.
[0017] In one embodiment, the communication network corresponding to the target service is configured based on the target latency jitter information and time correlation information, including:
[0018] Based on time-related information, determine the expected latency accuracy of the target service;
[0019] Configure the communication network corresponding to the target service based on the expected latency accuracy and target latency jitter information.
[0020] In one embodiment, the communication network corresponding to the target service is configured based on the expected latency accuracy and the target latency jitter information, including:
[0021] Based on the expected latency accuracy and target latency jitter information, as well as the current network configuration information and network resource usage of the communication network corresponding to the target service, the target configuration information of the communication network is determined.
[0022] Configure the communication network based on the target configuration information.
[0023] In one embodiment, obtaining the time association information of the data packet corresponding to the target service at the current moment from the service flow includes:
[0024] The first neural network is used to obtain the time-related information of the data packets corresponding to the target business from the business flow.
[0025] Secondly, this application provides a network configuration apparatus, which includes:
[0026] The acquisition module is used to obtain the time association information of the data packets corresponding to the target service at the current moment from the business flow;
[0027] The determination module is used to determine the target latency jitter information of the target service based on time-related information;
[0028] The configuration module is used to configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0029] Thirdly, this application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0030] Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow;
[0031] Based on time-related information, determine the target latency jitter information for the target service;
[0032] Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0033] Fourthly, this application also provides a computer-readable storage medium on which a computer program is stored, and which, when executed by a processor, performs the following steps:
[0034] Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow;
[0035] Based on time-related information, determine the target latency jitter information for the target service;
[0036] Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0037] Fifthly, this application also provides a computer program product comprising a computer program that, when executed by a processor, performs the following steps:
[0038] Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow;
[0039] Based on time-related information, determine the target latency jitter information for the target service;
[0040] Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0041] The aforementioned network configuration method, apparatus, computer equipment, and storage medium obtain time association information of data packets corresponding to the target service at the current moment from the service flow. Based on the time association information, the target latency jitter information of the target service is determined. Based on the target latency jitter information and the time association information, the communication network corresponding to the target service is configured. This application obtains the time association information of data packets corresponding to the target service at the current moment from the service flow, automatically determines the target latency jitter information of the target service based on the time association information of the data packets corresponding to the target service at the current moment, and automatically configures the communication network corresponding to the target service based on the target latency jitter information and the time association information. This eliminates the need for manual intervention and additional hardware, effectively improving network configuration efficiency and accuracy while reducing network configuration costs. Attached Figure Description
[0042] Figure 1 This is an application environment diagram of a network configuration method provided in this embodiment;
[0043] Figure 2 This is a flowchart illustrating the first network configuration method provided in this embodiment;
[0044] Figure 3 This is a flowchart illustrating the process of determining the target latency jitter information of a target service in this embodiment.
[0045] Figure 4 This is a flowchart illustrating the process of configuring the communication network corresponding to the target service provided in this embodiment.
[0046] Figure 5 This is a flowchart illustrating the third network configuration method provided in this embodiment;
[0047] Figure 6 This is a structural block diagram of a network configuration device provided in this embodiment;
[0048] Figure 7 This is an internal structural diagram of the computer device provided in this embodiment. Detailed Implementation
[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0050] The network configuration method provided in this application embodiment can be applied to, for example, Figure 1The application environment shown is primarily used in environments where PN (ProfiNet, Industrial Ethernet) master stations and PN slave stations transmit service flows through optical communication networks. Specifically, it can be applied to OLT (Optical Line Terminal) devices. The OLT device obtains the time correlation information of the data packets corresponding to the target service at the current moment from the service flow. Based on the time correlation information, the OLT device determines the target latency jitter information of the target service. The OLT device then configures the communication network corresponding to the target service based on the target latency jitter information and the time correlation information.
[0051] In this context, "PN slave" typically refers to a "slave" in a Profinet network. Profinet is an industrial Ethernet standard used for data communication in industrial automation and control systems. A PN slave is a device connected to a Profinet network and existing as a slave device. These devices may be sensors, actuators, HMIs (Human Machine Interfaces), or other types of industrial automation equipment. They typically do not have the ability to initiate communication but rather respond to queries and commands from the master station.
[0052] A PN master station refers to the master station in a Profinet network, which is responsible for initiating communication requests, while slave stations respond to these requests and provide data or execute instructions.
[0053] OLT equipment is an abbreviation for "Optical Line Terminal". It is a type of equipment used for accessing networks in network communication, and plays an important role, especially in fiber optic communication networks.
[0054] In one embodiment, Figure 2 This is a flowchart illustrating a network configuration method provided in an embodiment of this application, applied to... Figure 1 Taking an OLT device as an example, this method includes the following steps:
[0055] S201, Obtain the time association information of the data packet corresponding to the target service at the current moment from the service flow.
[0056] In this context, "service flow" refers to the data flow between the PN master station and the PN slave station used for transmitting service data. "Target service" refers to the service that requires configuration within the network. "Time-related information" refers to information strongly correlated with time; in this application, time-related information includes packet transmission frequency and / or packet transmission interval duration. Packet transmission frequency refers to the frequency at which data packets of the target service are transmitted. Packet transmission interval duration refers to the time interval between the transmission times of two adjacent data packets.
[0057] As an optional implementation of this application, the time association information of the data packet corresponding to the target service at the current moment is obtained from the service flow using a data acquisition device.
[0058] Another optional implementation of this application involves obtaining the time association information of the data packets corresponding to each candidate service at the current moment from the service flow. Based on the service identifier of the target service, the time association information of the data packets corresponding to the target service is obtained from the time association information of the data packets corresponding to each candidate service. The service identifier can be the IP address, MAC address, or other unique identifier corresponding to the target service.
[0059] Another optional implementation of this application involves obtaining the time-related information of data packets corresponding to the target service from the service flow using a first neural network. The first neural network employs, but is not limited to, a CNN (Convolutional Neural Network). Specifically, the OLT device captures data packets and related parameters (including packet length, transmission frequency, transmission interval, port, priority, IP, MAC, etc.) from the service flow. These parameters are then converted into corresponding communication tensors, which are input into the CNN neural network. The CNN network processes the temporal data of each data packet using a sliding window, dividing the temporal data into multiple fixed-length segments, each segment being equivalent to a pseudo-image. A one-dimensional convolutional layer slides the convolution kernel across the one-dimensional data (since the selected parameters corresponding to the data packets are related to the PLC's service, the service changes within a certain fixed period have a certain regularity), uncovering the temporal dependency between the relevant parameters of the data packets and the corresponding PLC period, thereby obtaining the time-related information of the data packets corresponding to the target service, i.e., parameter information with a strong temporal dependency.
[0060] S202, Based on time-related information, determine the target latency jitter information for the target service.
[0061] Among them, the target latency jitter information is the jitter information of the target service in terms of latency.
[0062] As an optional implementation of this application, time-related information is input into a value neural network model, and the neural network model determines the target latency jitter information of the target service based on the time-related information. The neural network model can be an LSTM neural network model.
[0063] Another optional implementation of this application is to determine the latency information between data packets of the target service based on the time association information, determine the latency change information based on the latency information between each data packet, and use the latency change information as the target latency jitter information of the target service.
[0064] S203, Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0065] Optionally, in this embodiment, configuration requirements can be determined based on time-related information, and configuration information can be determined based on the configuration requirements and target latency jitter information. Based on the configuration information, the communication network corresponding to the target service is configured.
[0066] The aforementioned network configuration method obtains the time association information of the data packets corresponding to the target service at the current moment from the service flow. Based on the time association information, it determines the target latency jitter information of the target service. Based on the target latency jitter information and the time association information, it configures the communication network corresponding to the target service. This application obtains the time association information of the data packets corresponding to the target service at the current moment from the service flow, and automatically determines the target latency jitter information of the target service based on the time association information of the data packets corresponding to the target service at the current moment. Based on the target latency jitter information and the time association information, it automatically configures the communication network corresponding to the target service. This requires no manual intervention and no additional hardware installation, effectively improving network configuration efficiency and accuracy while reducing network configuration costs.
[0067] In one embodiment, to more accurately determine the target latency jitter information of the target service, such as Figure 3 As shown, one optional implementation of S202 includes:
[0068] S301, obtain the data packet reception time of the data packets corresponding to the preset number of target services consecutively before the current time.
[0069] Here, "preset quantity" refers to a pre-set quantity, such as 9. Taking 9 as an example, obtaining the data packet reception time of the data packets corresponding to the preset quantity of target services before the current time means obtaining the data packet reception time of the data packets corresponding to the 9 consecutive target services before the current time.
[0070] Optionally, in this embodiment, when acquiring the data packets corresponding to the target service, the data packet reception time of each data packet is automatically recorded.
[0071] S302, determine the target latency jitter information of the target service based on the reception time and time correlation information of each data packet.
[0072] As an optional implementation of this application, the actual interval between adjacent data packets is determined based on the reception time of each data packet. Then, the actual packet transmission frequency is determined based on the actual packet interval. Finally, the target latency jitter information of the target service is determined based on the actual packet transmission frequency and the packet transmission frequency in the time-related information. Specifically, the ratio of the actual packet transmission frequency to the packet transmission frequency is used as the target latency jitter information of the target service.
[0073] Another optional implementation of this application is to determine the actual interval between adjacent data packets based on the reception time of each data packet, and to determine the target latency jitter information of the target service based on the actual interval between each data packet and the packet transmission interval in the time association information. For example, to determine the target latency jitter information between the first and second data packets, assume the actual interval between the first data packet (i.e., the difference between the reception time of the first data packet and the reception time of the previous data packet) is t1, the actual interval between the second data packet (i.e., the difference between the reception time of the second data packet and the reception time of the first data packet) is t2, the packet transmission interval is t, and the target latency jitter information between the first and second data packets is (t2-t) / (t1-t). This process continues until the target latency jitter information of a preset number of data packets corresponding to the target service is calculated. If the preset number is 9, then the target latency jitter information between each of the 9 data packets and the previous data packet needs to be calculated separately.
[0074] Another optional implementation of this application embodiment is to determine the historical latency jitter information of the target service based on the reception time and time association information of each data packet. Based on the second neural network, the future latency jitter information of the target service in a future time period is predicted based on the historical latency jitter information. The future latency jitter information is used as the target latency jitter information of the target service. For example, the method of determining the historical latency jitter information of the target service can refer to the implementation method of determining the target latency jitter information in the above embodiments, and will not be repeated again. For example, an optional implementation method of predicting the future latency jitter information of the target service in a future time period based on the second neural network and historical latency jitter information is as follows: assuming that a preset number (e.g., 9) of the historical latency jitter information of the target service has been calculated as described in the above embodiments (each historical latency jitter information is the latency jitter information between the corresponding data packet and the previous data packet), the preset number (e.g., 9) of the historical latency jitter information of the target service can be input into the second neural network, and the second neural network can predict the future latency jitter information between the 10th data packet (i.e., the data packet at the current moment and the next data packet (i.e., the future data packet)). The second neural network can be an LSTM (Long Short-Term Memory) neural network.
[0075] In this embodiment, the data packet reception times of a preset number of target services preceding the current time are obtained. Based on the reception time and time correlation information of each data packet, the target latency jitter information of the target services can be determined more accurately.
[0076] In one embodiment, in order to more accurately configure the communication network corresponding to the target service, such as Figure 4 As shown, an optional implementation of S203 includes:
[0077] S401, based on time-related information, determine the expected latency accuracy of the target service.
[0078] Among them, the expected delay accuracy refers to the desired delay accuracy.
[0079] As an optional implementation of this application, the expected latency accuracy of the target service is determined based on a first latency list and the packet transmission frequency. The first latency list records the mapping relationship between packet transmission frequency and expected latency accuracy. Generally, the higher the packet transmission frequency, the higher the expected latency accuracy. To meet this requirement, it is typically configured that a higher packet transmission frequency corresponds to a higher expected latency accuracy.
[0080] Another optional implementation of this application involves determining the expected latency accuracy of the target service based on a second latency list and the packet transmission interval duration. The second latency list records the mapping relationship between the packet transmission interval duration and the expected latency accuracy.
[0081] S402, configure the communication network corresponding to the target service based on the expected latency accuracy and target latency jitter information.
[0082] Optionally, in this embodiment, the target configuration information of the communication network is determined based on the expected latency accuracy, target latency jitter information, and the current network configuration information and network resource usage of the communication network corresponding to the target service. The communication network is then configured based on the target configuration information. In this embodiment, the expected latency accuracy, target latency jitter information, and the current network configuration information and network resource usage of the communication network corresponding to the target service can be input into a configuration query tool. The configuration query tool then determines the target configuration information based on the above requirements. The configuration query tool can be existing network configuration software or a trained neural network model. Based on the above requirements (i.e., the expected latency accuracy and target latency jitter information, and the current network configuration information and network resource usage of the communication network corresponding to the target service), target configuration information more suitable for the current communication network can be determined.
[0083] In this embodiment, the expected latency accuracy of the target service is determined based on time correlation information. Based on the expected latency accuracy and target latency jitter information, the communication network corresponding to the target service is configured so that the configured communication network better meets the service transmission requirements of the target service in terms of latency and latency jitter, effectively reducing the adverse impact of latency jitter on the target service.
[0084] In one embodiment, such as Figure 5 As shown, another optional implementation of a network configuration method includes:
[0085] S501, using the first neural network, obtains the time-related information of the data packets corresponding to the target service from the service flow. This time-related information includes the packet transmission frequency and / or the packet transmission interval duration.
[0086] S502, obtain the data packet reception time of the data packets corresponding to the preset number of target services consecutively before the current time.
[0087] S503 determines the historical latency jitter information of the target service based on the reception time and time correlation information of each data packet.
[0088] S504, based on the second neural network, predicts the future latency jitter information of the target service in the future time period according to historical latency jitter information.
[0089] S505 uses future latency jitter information as the target latency jitter information for the target service.
[0090] S506, based on time-related information, determines the expected latency accuracy of the target service.
[0091] S507, based on the expected latency accuracy and target latency jitter information, as well as the current network configuration information and network resource usage of the communication network corresponding to the target service, determine the target configuration information of the communication network.
[0092] S508 configures the communication network based on target configuration information.
[0093] In this embodiment, the time association information of the data packets corresponding to the target service at the current moment is obtained from the service flow. Based on the time association information, the target latency jitter information of the target service is determined. Based on the target latency jitter information and the time association information, the communication network corresponding to the target service is configured. This application obtains the time association information of the data packets corresponding to the target service at the current moment from the service flow, and automatically determines the target latency jitter information of the target service based on the time association information of the data packets corresponding to the target service at the current moment. Based on the target latency jitter information and the time association information, the communication network corresponding to the target service is automatically configured without manual intervention or additional hardware installation, effectively improving network configuration efficiency and accuracy while reducing network configuration costs.
[0094] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0095] Based on the same inventive concept, this application also provides a network configuration apparatus for implementing the network configuration method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more network configuration apparatus embodiments provided below can be found in the limitations of the network configuration method described above, and will not be repeated here.
[0096] In one embodiment, by Figure 6 A structural block diagram of a network configuration apparatus in one embodiment is shown. Figure 6 As shown, a network configuration device 1 is provided, which includes: an acquisition module 10, a determination module 20, and a configuration module 30, wherein:
[0097] The acquisition module 10 is used to obtain the time association information of the data packet corresponding to the target service at the current moment from the service flow;
[0098] The determination module 20 is used to determine the target latency jitter information of the target service based on time-related information;
[0099] Configuration module 30 is used to configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0100] In one embodiment, the time-related information includes packet transmission frequency and / or packet transmission interval duration.
[0101] In one embodiment, the above Figure 6 The determining module 20 is also specifically used for:
[0102] Get the data packet reception time of a preset number of target services consecutively up to the current time.
[0103] Based on the reception time and time correlation information of each data packet, the target latency jitter information of the target service is determined.
[0104] In one embodiment, the above Figure 6 The determining module 20 is also specifically used for:
[0105] Based on the reception time and time correlation information of each data packet, determine the historical latency jitter information of the target service;
[0106] Based on the second neural network, and according to historical latency jitter information, the future latency jitter information of the target service in the future time period is predicted;
[0107] Use future latency jitter information as the target latency jitter information for the target service.
[0108] In one embodiment, the above Figure 6 The configuration module 30 is also specifically used for:
[0109] Based on time-related information, determine the expected latency accuracy of the target service;
[0110] Configure the communication network corresponding to the target service based on the expected latency accuracy and target latency jitter information.
[0111] In one embodiment, the above Figure 6The configuration module 30 is also specifically used for:
[0112] Based on the expected latency accuracy and target latency jitter information, as well as the current network configuration information and network resource usage of the communication network corresponding to the target service, the target configuration information of the communication network is determined.
[0113] Configure the communication network based on the target configuration information.
[0114] In one embodiment, the above Figure 6 The acquisition module 10 is also specifically used for:
[0115] The first neural network is used to obtain the time-related information of the data packets corresponding to the target business from the business flow.
[0116] Each module in the aforementioned network configuration device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.
[0117] In one embodiment, a computer device is provided, which may be a platform-side device, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores business flow-related information. The network interface communicates with external user devices via a network connection. When the computer program is executed by the processor, it implements a network configuration method.
[0118] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specifically, the computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0119] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0120] Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow;
[0121] Based on time-related information, determine the target latency jitter information for the target service;
[0122] Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0123] In one embodiment, when the processor executes the computer program, it also performs the following steps: the time-related information includes the packet sending frequency and / or the packet sending interval duration.
[0124] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the target latency jitter information of the target service based on time-related information, including:
[0125] Get the data packet reception time of a preset number of target services consecutively up to the current time.
[0126] Based on the reception time and time correlation information of each data packet, the target latency jitter information of the target service is determined.
[0127] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the target latency jitter information of the target service based on the reception time and time correlation information of each data packet, including:
[0128] Based on the reception time and time correlation information of each data packet, determine the historical latency jitter information of the target service;
[0129] Based on the second neural network, and according to historical latency jitter information, the future latency jitter information of the target service in the future time period is predicted;
[0130] Use future latency jitter information as the target latency jitter information for the target service.
[0131] In one embodiment, when the processor executes the computer program, it further performs the following steps: configuring the communication network corresponding to the target service based on the target latency jitter information and time correlation information, including:
[0132] Based on time-related information, determine the expected latency accuracy of the target service;
[0133] Configure the communication network corresponding to the target service based on the expected latency accuracy and target latency jitter information.
[0134] In one embodiment, when the processor executes the computer program, it further performs the following steps: configuring the communication network corresponding to the target service based on the expected latency accuracy and the target latency jitter information, including:
[0135] Based on the expected latency accuracy and target latency jitter information, as well as the current network configuration information and network resource usage of the communication network corresponding to the target service, the target configuration information of the communication network is determined.
[0136] Configure the communication network based on the target configuration information.
[0137] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining time-related information of the data packets corresponding to the target service at the current moment from the service flow, including:
[0138] The first neural network is used to obtain the time-related information of the data packets corresponding to the target business from the business flow.
[0139] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps:
[0140] Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow;
[0141] Based on time-related information, determine the target latency jitter information for the target service;
[0142] Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0143] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the time-related information includes the packet sending frequency and / or the packet sending interval duration.
[0144] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the target latency jitter information of the target service based on time-related information, including:
[0145] Get the data packet reception time of a preset number of target services consecutively up to the current time.
[0146] Based on the reception time and time correlation information of each data packet, the target latency jitter information of the target service is determined.
[0147] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the target latency jitter information of the target service based on the reception time and time correlation information of each data packet, including:
[0148] Based on the reception time and time correlation information of each data packet, determine the historical latency jitter information of the target service;
[0149] Based on the second neural network, and according to historical latency jitter information, the future latency jitter information of the target service in the future time period is predicted;
[0150] Use future latency jitter information as the target latency jitter information for the target service.
[0151] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: configuring the communication network corresponding to the target service based on the target latency jitter information and time correlation information, including:
[0152] Based on time-related information, determine the expected latency accuracy of the target service;
[0153] Configure the communication network corresponding to the target service based on the expected latency accuracy and target latency jitter information.
[0154] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: configuring the communication network corresponding to the target service based on the expected latency accuracy and the target latency jitter information, including:
[0155] Based on the expected latency accuracy and target latency jitter information, as well as the current network configuration information and network resource usage of the communication network corresponding to the target service, the target configuration information of the communication network is determined.
[0156] Configure the communication network based on the target configuration information.
[0157] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining time-related information of the data packets corresponding to the target service at the current moment from the service flow, including:
[0158] The first neural network is used to obtain the time-related information of the data packets corresponding to the target business from the business flow.
[0159] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:
[0160] Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow;
[0161] Based on time-related information, determine the target latency jitter information for the target service;
[0162] Configure the communication network corresponding to the target service based on the target latency jitter information and time correlation information.
[0163] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the time-related information includes the packet sending frequency and / or the packet sending interval duration.
[0164] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the target latency jitter information of the target service based on time-related information, including:
[0165] Get the data packet reception time of a preset number of target services consecutively up to the current time.
[0166] Based on the reception time and time correlation information of each data packet, the target latency jitter information of the target service is determined.
[0167] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the target latency jitter information of the target service based on the reception time and time correlation information of each data packet, including:
[0168] Based on the reception time and time correlation information of each data packet, determine the historical latency jitter information of the target service;
[0169] Based on the second neural network, and according to historical latency jitter information, the future latency jitter information of the target service in the future time period is predicted;
[0170] Use future latency jitter information as the target latency jitter information for the target service.
[0171] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: configuring the communication network corresponding to the target service based on the target latency jitter information and time correlation information, including:
[0172] Based on time-related information, determine the expected latency accuracy of the target service;
[0173] Configure the communication network corresponding to the target service based on the expected latency accuracy and target latency jitter information.
[0174] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: configuring the communication network corresponding to the target service based on the expected latency accuracy and the target latency jitter information, including:
[0175] Based on the expected latency accuracy and target latency jitter information, as well as the current network configuration information and network resource usage of the communication network corresponding to the target service, the target configuration information of the communication network is determined.
[0176] Configure the communication network based on the target configuration information.
[0177] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining time-related information of the data packets corresponding to the target service at the current moment from the service flow, including:
[0178] The first neural network is used to obtain the time-related information of the data packets corresponding to the target business from the business flow.
[0179] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0180] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should all be considered to be within the scope of this specification.
[0181] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A network configuration method, characterized in that, The method includes: Obtain the time association information of the data packets corresponding to the target service at the current moment from the service flow; wherein, the time association information includes the packet transmission frequency; The system obtains the data packet reception time of a preset number of data packets corresponding to the target service consecutively before the current time; determines the actual interval between adjacent data packets based on the reception time of each data packet; determines the actual packet transmission frequency of the data packets corresponding to the target service based on the actual interval between the data packets corresponding to the target service; determines the historical latency jitter information of the target service based on the actual packet transmission frequency and the data packet transmission frequency in the time association information; predicts the future latency jitter information of the target service in a future time period based on the historical latency jitter information using a second neural network; and uses the future latency jitter information as the target latency jitter information of the target service. Configure the communication network corresponding to the target service based on the target latency jitter information and the time correlation information.
2. The method according to claim 1, characterized in that, The time-related information also includes the packet sending interval duration.
3. The method according to claim 1, characterized in that, The step of determining the historical latency jitter information of the target service based on the actual packet transmission frequency and the data packet transmission frequency in the time-related information includes: The ratio of the actual packet transmission frequency to the packet transmission frequency in the time-related information is used as the target latency jitter information for the target service.
4. The method according to claim 1, characterized in that, The step of configuring the communication network corresponding to the target service based on the target latency jitter information and the time correlation information includes: Based on the time correlation information, determine the expected latency accuracy of the target service; Configure the communication network corresponding to the target service based on the expected latency accuracy and the target latency jitter information.
5. The method according to claim 4, characterized in that, The step of configuring the communication network corresponding to the target service based on the expected latency accuracy and the target latency jitter information includes: Based on the expected latency accuracy and the target latency jitter information, as well as the current network configuration information and network resource usage of the communication network corresponding to the target service, the target configuration information of the communication network is determined. The communication network is configured based on the target configuration information.
6. The method according to claim 1, characterized in that, The step of obtaining the time association information of the data packet corresponding to the target service at the current moment from the service flow includes: The first neural network is used to obtain the time-related information of the data packets corresponding to the target business from the business flow.
7. A network configuration device, characterized in that, The device includes: The acquisition module is used to acquire time association information of the data packets corresponding to the target service at the current moment from the service flow; wherein, the time association information includes the packet transmission frequency; The determination module is used to obtain the data packet reception time of a preset number of data packets corresponding to the target service before the current time; determine the actual interval duration between adjacent data packets based on the reception time of each data packet; determine the actual packet transmission frequency of the data packets corresponding to the target service based on the actual interval duration of the data packets corresponding to the target service; determine the historical latency jitter information of the target service based on the actual packet transmission frequency and the data packet transmission frequency in the time association information; predict the future latency jitter information of the target service in a future time period based on the historical latency jitter information using a second neural network; and use the future latency jitter information as the target latency jitter information of the target service. The configuration module is used to configure the communication network corresponding to the target service based on the target latency jitter information and the time association information.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.