Network traffic steering method and related devices
Patent Information
- Application Number
- CN202310215831.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2022-11-25
- Filing Date
- 2023-03-07
- Publication Date
- 2026-10-09
- Estimated Expiration
- 2043-03-07
AI Technical Summary
在新型电力通信网中，新能源发电站的发电量直接影响着电力通信网业务的重要度，发电量的波动性直接导致了电力通信网业务重要度的波动性，这对电力通信网的流量疏导算法提出了新的挑战
[0038]As can be seen from the above, the network traffic diversion method and related equipment provided in this application predict the power generation of power generation nodes based on a pre-built power generation prediction model; based on the predicted power generation, the importance and link risk of the service to be transmitted are predicted; based on the importance and link risk, the link cost is calculated; and in response to congestion during transmission of the service to be transmitted, diversion is performed on the service based on the link cost. This embodiment of the application predicts power generation using a preset prediction model, predicts the importance and link risk of each service based on the power generation, dynamically adjusts the link weight, and diverts traffic based on the importance of the service when it is blocked. This effectively reduces the blocking rate, average importance of blocked services, and variance of link risk in the new power optical communication network, thereby improving the reliability of the power optical communication network.
Smart Images
Figure CN116485192B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing technology, and in particular to a network traffic diversion method and related equipment. Background Technology
[0002] To reduce energy consumption and achieve carbon neutrality, the power system is gradually shifting from traditional thermal power generation to renewable energy generation. However, renewable energy generation methods such as wind and solar power have unique temporal and spatial characteristics, which makes the power generation efficiency of renewable energy generation nodes more volatile and random.
[0003] Power optical communication networks are dedicated communication networks used to connect power equipment. The stable operation of the services they carry is crucial; congestion in these networks can directly impact regional power supply. In new power communication networks, the power generation of renewable energy plants directly affects the importance of network services. Fluctuations in power generation directly lead to fluctuations in service importance, posing new challenges to traffic routing algorithms. Previous resource allocation and traffic routing algorithms for power optical communication networks only considered fixed service importance and optical network constraints, neglecting the random and fluctuating characteristics of renewable energy power networks, which result in highly dynamic service importance in new power communication networks. This can lead to problems such as high-importance services clustering on local links and an inability to balance topology risks. Summary of the Invention
[0004] In view of this, the purpose of this application is to propose a network traffic diversion method and related equipment.
[0005] To achieve the above objectives, this application provides a network traffic diversion method, comprising:
[0006] Based on a pre-built power generation prediction model, the predicted power generation of the power generation node is obtained.
[0007] Based on the predicted power generation, the importance of the service to be transmitted and the link risk of the service to be transmitted are predicted.
[0008] Based on the importance and the link risk, the link cost is calculated.
[0009] In response to the congestion of the service to be transmitted during transmission, the service to be transmitted is diverted based on the link overhead.
[0010] In one possible implementation, the power generation prediction model is trained using the following method:
[0011] Obtain the training power generation time series data of the power generation node, and verify the stationarity of the training power generation time series data;
[0012] In response to the stationary nature of the time-series power generation data used for training, the initial power generation prediction model is ordered and its parameters are estimated to obtain the power generation prediction model to be trained.
[0013] The time-series power generation data used for training is input into the power generation prediction model to be trained to obtain the prediction data;
[0014] The error is calculated based on the predicted power generation data and the true value of the power generation data;
[0015] In response to the error being less than the error threshold, the trained power generation prediction model is used as the pre-built power generation prediction model.
[0016] In one possible implementation, predicting the importance of the service to be transmitted based on the predicted power generation includes:
[0017] Obtain the predicted power generation of the source node and the predicted power generation of the destination node for the service to be transmitted.
[0018] The importance of the source node is calculated based on the predicted power generation of the source node.
[0019] The importance of the destination node is predicted based on the predicted power generation of the destination node.
[0020] The importance of the service to be transmitted is calculated based on the importance of the source node and the importance of the destination node.
[0021] In one possible implementation, predicting the link risk level of the service to be transmitted based on the predicted power generation includes:
[0022] Based on the importance of the source node, the importance of the destination node, and the importance of the service to be transmitted, the link risk level of the service to be transmitted is calculated.
[0023] In one possible implementation, calculating the link cost based on the importance and the link risk includes:
[0024] Obtain the physical distance between the source node and the destination node;
[0025] The link cost is calculated based on the physical distance, the link risk level, and the importance level.
[0026] In one possible implementation, the process of routing the service to be transmitted based on the link overhead includes:
[0027] In response to the fact that the importance of the service to be transmitted is higher than a preset importance threshold, low-risk services with bandwidth occupancy greater than that of the service to be transmitted are found in the link where the service to be transmitted is located.
[0028] The low-risk services are rerouted, and the services to be transmitted are routed.
[0029] In one possible implementation, the method further includes:
[0030] If the importance of the service to be transmitted is lower than the preset importance threshold, or if the low-risk service does not exist in the link where the service to be transmitted is located, the service to be transmitted is placed in the blocking list.
[0031] Based on the same inventive concept, embodiments of this application also provide a network traffic diversion device, including:
[0032] The first prediction module is configured to predict the power generation of the power generation node based on a pre-built power generation prediction model.
[0033] The second prediction module is configured to predict the importance of the service to be transmitted and the link risk of the service to be transmitted based on the predicted power generation.
[0034] The calculation module is configured to calculate the link cost of the link based on the importance and the link risk.
[0035] The diversion module is configured to divert the service to be transmitted based on the link overhead in response to the service being blocked during transmission.
[0036] Based on the same inventive concept, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the network traffic routing method as described in any of the above.
[0037] Based on the same inventive concept, embodiments of this application also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute any of the network traffic routing methods described above.
[0038] As can be seen from the above, the network traffic diversion method and related equipment provided in this application predict the power generation of power generation nodes based on a pre-built power generation prediction model; based on the predicted power generation, the importance and link risk of the service to be transmitted are predicted; based on the importance and link risk, the link cost is calculated; and in response to congestion during transmission of the service to be transmitted, diversion is performed on the service based on the link cost. This embodiment of the application predicts power generation using a preset prediction model, predicts the importance and link risk of each service based on the power generation, dynamically adjusts the link weight, and diverts traffic based on the importance of the service when it is blocked. This effectively reduces the blocking rate, average importance of blocked services, and variance of link risk in the new power optical communication network, thereby improving the reliability of the power optical communication network. Attached Figure Description
[0039] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0040] Figure 1 This is a flowchart of the network traffic diversion method according to an embodiment of this application;
[0041] Figure 2 This is a schematic diagram of the model training process in an embodiment of this application;
[0042] Figure 3 This is a schematic diagram of the routing and traffic diversion process in an embodiment of this application;
[0043] Figure 4 This is a schematic diagram of the network traffic diversion device according to an embodiment of this application;
[0044] Figure 5 This is a schematic diagram of the electronic device structure according to an embodiment of this application. Detailed Implementation
[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.
[0046] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0047] As described in the background section, power optical communication networks are dedicated communication networks used to connect power equipment. The stable operation of the services they carry is crucial. The power generation of new energy power plants directly affects the importance of power communication network services. The volatility of power generation directly leads to the volatility of the importance of power communication network services. In the past, the resource allocation algorithm and traffic routing algorithm of power optical communication networks only considered fixed service importance and optical network constraints, without considering the random and fluctuating characteristics of new energy power networks, which lead to the high dynamism of the importance of new power communication network services. This may result in problems such as high-importance services clustering on local links and the inability to balance topology risks.
[0048] In summary, this application proposes a network traffic diversion method and related equipment. Based on a pre-built power generation prediction model, the predicted power generation of power generation nodes is obtained. Based on the predicted power generation, the importance and link risk of the service to be transmitted are predicted. Based on the importance and link risk, the link cost is calculated. In response to congestion during transmission of the service to be transmitted, diversion is performed based on the link cost. This application's embodiment predicts power generation using a preset prediction model, predicts the importance and link risk of each service based on the power generation, and dynamically adjusts link weights. When a service is blocked, diversion is performed based on the service's importance, which can effectively reduce the blocking rate, average importance of blocked services, and variance of link risk in the new power optical communication network, thereby improving the reliability of the power optical communication network.
[0049] The technical solutions of the embodiments of this application will be described in detail below through specific examples.
[0050] refer to Figure 1 The network traffic diversion method of this application includes the following steps:
[0051] Step S101: Based on the pre-built power generation prediction model, predict the power generation of the power generation node.
[0052] Step S102: Based on the predicted power generation, predict the importance of the service to be transmitted and the link risk of the service to be transmitted.
[0053] Step S103: Calculate the link cost of the link based on the importance and the link risk.
[0054] Step S104: In response to the congestion of the service to be transmitted during transmission, the service to be transmitted is diverted based on the link overhead.
[0055] The primary objective of this application is to improve the reliability of power optical communication networks. A reliable power communication network should simultaneously possess a low congestion rate, a low average importance of congested services, and a low link risk variance. The risk of a network topology link is related to the total number and importance of the services it carries; the more services carried and the higher their importance, the higher the risk of that link. In a reliable network, the risk of each link should be similar; therefore, a lower link risk variance indicates a higher level of network risk equilibrium.
[0056] To better describe the solution, the topology is represented by G(V,E), where V represents the set of nodes in the topology, including renewable energy generation nodes and communication nodes. E represents the set of links in the topology. Services in the topology are represented as s. i = <V S ,D>,V S V is the source node of business Si. D This is the destination node for business Si.
[0057] For step S101, refer to Figure 2 This is a schematic diagram of the model training process in an embodiment of this application.
[0058] As shown in the figure, in this step, the corresponding target sequence needs to be obtained first, and then the stationarity of the sequence is tested. If it is not stationary, it is subjected to difference operation and then the stationarity test is performed again until it passes the stationarity test. After passing the stationarity test, the steps of model order determination and parameter estimation are required. Then, the training set data is input into the power generation prediction model to be trained for prediction. After that, the prediction results are tested to determine whether they can pass the model test. If they can pass, the model is used as the pre-built power generation prediction model. If they fail the model test, the model parameters are reset from the model order determination until they can pass the model test.
[0059] In one feasible embodiment, the power generation prediction model is trained using the following method:
[0060] Obtain the training power generation time series data of the power generation node, and verify the stationarity of the training power generation time series data;
[0061] In response to the stationary nature of the time-series power generation data used for training, the initial power generation prediction model is ordered and its parameters are estimated to obtain the power generation prediction model to be trained.
[0062] The time-series power generation data used for training is input into the power generation prediction model to be trained to obtain the prediction data;
[0063] The error is calculated based on the predicted power generation data and the true value of the power generation data;
[0064] In response to the error being less than the error threshold, the trained power generation prediction model is used as the pre-built power generation prediction model.
[0065] Specifically, the first step is stationarity verification. A time series can only be predicted using a predictive model if it is stationary. Before prediction, the input power generation data must be verified for stationarity. If the series is not stationary, it is differencing until a stationary series is obtained. Typically, short-term power generation data only requires one differencing prediction to achieve stationarity.
[0066] Furthermore, the model needs to be determined in order. This can be done based on the model's autocorrelation function or partial autocorrelation function, or by using information criteria (such as the Bayesian information criterion or the Akaike information criterion). In this embodiment, specifically in short-term time series prediction, a suitable model order leads to better fitting results. In this embodiment, the Bayesian information criterion is used for model order determination.
[0067] Furthermore, it is necessary to estimate the model's parameters. In this embodiment, parameter estimation methods (such as the method of moments or the least squares method) are used for parameter estimation. Parameter estimation is to determine the weight of each indicator in the model fitting. At this point, all the model parameters have been determined, and the power generation prediction model to be trained is obtained. In this embodiment, the least squares method is used for parameter estimation.
[0068] Furthermore, the power generation prediction model to be trained needs to be validated. Specifically, the predicted values from several sets of data are compared with the actual values. If the average error of the predicted values exceeds the model error threshold, the model validation fails, and the model order determination and parameter estimation are repeated until the model validation is successful. In this embodiment, ARMA (Autoregressive Moving Average model) is used as the prediction model, and the error threshold is set to 10%. This achieves high accuracy while preventing excessive model reordering.
[0069] Further reference Figure 3 This is a schematic diagram of the routing and traffic diversion process in an embodiment of this application.
[0070] like Figure 3 As shown, after the model is trained, it is first used to predict the power generation of each node. Here, a node refers to a node in the set topology. When predicting the power generation of each node, it is also necessary to combine historical data and topology parameters. Then, the importance of services in the current topology and the risk of each link are calculated. Then, the topology weights are updated based on the data obtained from the above calculations. Then, dynamic routing and spectrum allocation are performed based on the updated topology weights. Further, it is determined whether the service is successfully transmitted. If the service is successfully transmitted, the topology parameters are updated. If it is unsuccessful, that is, the service is blocked during transmission, it is necessary to determine whether it is a high-importance service. If it is not a high-importance service, it is directly determined that the service is blocked and placed in the blocking list. If it is a high-importance service, it is searched for whether there is a suitable yielding service. If not, the service is still placed in the blocking list. If there is a suitable yielding service, the yielding service is performed so that the blocked high-importance service can be transmitted. Then, the topology parameters are updated.
[0071] Specifically, regarding step S102, in a feasible embodiment, predicting the importance of the service to be transmitted based on the predicted power generation includes:
[0072] Obtain the predicted power generation of the source node and the predicted power generation of the destination node for the service to be transmitted.
[0073] The importance of the source node is calculated based on the predicted power generation of the source node.
[0074] The importance of the destination node is predicted based on the predicted power generation of the destination node.
[0075] The importance of the service to be transmitted is calculated based on the importance of the source node and the importance of the destination node.
[0076] Specifically, in the embodiments of this application, the importance of service Si is represented as I. Si In the new power optical communication network, I Si The value of is dynamic and directly related to the importance of the source and destination nodes of this service. The importance of the source and destination nodes is calculated from the predicted values of the node's power generation.
[0077] The importance of a node is calculated using the following formula:
[0078] I Vi = Vi
[0079] Among them, I Vi δ represents the importance of a node. Vi This represents the predicted power generation value of the node.
[0080] The importance of the service to be transmitted is calculated using the following formula:
[0081]
[0082] in, Indicates the importance of the service to be transmitted. Indicates the importance of the source node of the service to be transmitted. This indicates the importance of the destination node for the service to be transmitted.
[0083] In this embodiment, the importance level range is set to 0 to 1. Based on the importance values of the source and destination nodes, the importance of each service in the current topology is calculated and normalized, i.e., the service importance range is 0 to 1. Services with an importance greater than 0.7 are marked as important.
[0084] Furthermore, in a feasible embodiment, predicting the link risk level of the service to be transmitted based on the predicted power generation includes:
[0085] Based on the importance of the source node, the importance of the destination node, and the importance of the service to be transmitted, the link risk level of the service to be transmitted is calculated.
[0086] Specifically, the link risk level is calculated using the following formula:
[0087]
[0088] in, This indicates the risk level of link E(m,n). α represents the importance of the i-th service carried by link E(m,n) in the next unit of time. V and α EThis represents the normalization parameter.
[0089] Furthermore, since the new power communication network is dynamic, a dynamic routing algorithm is selected for routing calculation, meaning that link weights and service routing costs are updated in real time.
[0090] For newly arriving services, the KSP algorithm (K=5) is selected as the routing algorithm, the First-Fit algorithm is selected as the spectrum allocation algorithm, and the link cost is dynamically adjusted. The calculation method is as follows.
[0091] Specifically, calculating the link cost based on the importance and the link risk includes:
[0092] Obtain the physical distance between the source node and the destination node;
[0093] The link cost is calculated based on the physical distance, the link risk level, and the importance level.
[0094] The link cost is calculated using the following method:
[0095]
[0096] Among them, W Si This represents the link cost of the service to be transmitted. This indicates the importance of the i-th service carried by link E(m,n) in the next unit of time. This indicates the risk level of link E(m,n). This represents the physical distance between node m and node n.
[0097] Furthermore, the process of routing the service to be transmitted based on the link overhead includes:
[0098] In response to the fact that the importance of the service to be transmitted is higher than a preset importance threshold, low-risk services with bandwidth occupancy greater than that of the service to be transmitted are found in the link where the service to be transmitted is located.
[0099] The low-risk services are rerouted, and the services to be transmitted are routed.
[0100] The method further includes:
[0101] If the importance of the service to be transmitted is lower than the preset importance threshold, or if the low-risk service does not exist in the link where the service to be transmitted is located, the service to be transmitted is placed in the blocking list.
[0102] Specifically, for high-importance services that fail to be allocated, the service with the lowest importance level from the congested links is selected for rerouting, releasing the link resources it occupies. Then, resources are allocated to the high-importance services that failed to be allocated. Specifically, routing calculations and spectrum allocation are performed based on the updated topology weights. When a high-importance service is blocked, a diversion operation is performed. Suitable low-risk services (with bandwidth usage greater than the high-importance service) are found on the congested links, and rerouting is performed on these low-risk services. Then, the high-importance service is routed (yielding operation). If the blocked service has low importance, or there is no suitable low-importance service to yield to it, the blocked service is added to the blocking list. Finally, the network topology information is updated.
[0103] In this embodiment, during the resource allocation process for services, the future importance of the services is predicted simultaneously. When service resource allocation fails, the importance of the service at the next moment is predicted. If the service is important, traffic diversion measures are used; otherwise, the blocked service is directly placed in the blocking list. For services with an importance greater than 0.7, a low-importance service (service importance less than 0.3) is selected from the path with the shortest routing cost. The power communication network resources occupied by this low-importance service are first released and made available for use by high-importance services. Subsequently, resources are reallocated for the low-importance services.
[0104] As can be seen from the above embodiments, the network traffic diversion method described in this application predicts the predicted power generation of power generation nodes based on a pre-built power generation prediction model; based on the predicted power generation, it predicts the importance of the service to be transmitted and the link risk of the service to be transmitted; based on the importance and the link risk, it calculates the link cost; and in response to the service to be transmitted being blocked during transmission, it diverts the service to be transmitted based on the link cost. This application first uses a prediction model to predict the power generation of new energy power plants, which can quickly predict the power generation of each new energy power plant in the next unit of time. Then, based on the short-term power generation of new energy power plants, this application predicts the importance of future services and the link risk, dynamically adjusts the link weight, and uses a routing algorithm for routing calculation. When a high-importance service is blocked, this application can select a low-importance service in the congested section to give way to it. Therefore, this application can effectively reduce the blocking rate, average importance of blocked services, and link risk variance of the new power optical communication network, and improve the reliability of the power optical communication network.
[0105] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.
[0106] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0107] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a network traffic diversion device.
[0108] refer to Figure 4 The network traffic diversion device includes:
[0109] The first prediction module 41 is configured to predict the predicted power generation of the power generation node based on a pre-built power generation prediction model.
[0110] The second prediction module 42 is configured to predict the importance of the service to be transmitted and the link risk of the service to be transmitted based on the predicted power generation.
[0111] The calculation module 43 is configured to calculate the link cost of the link based on the importance and the link risk.
[0112] The diversion module 44 is configured to divert the service to be transmitted based on the link overhead in response to the service being blocked during transmission.
[0113] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.
[0114] The apparatus described above is used to implement the corresponding network traffic diversion method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0115] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the network traffic diversion method described in any of the above embodiments.
[0116] Figure 5 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.
[0117] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.
[0118] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.
[0119] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.
[0120] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0121] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.
[0122] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.
[0123] The electronic devices described above are used to implement the corresponding network traffic diversion methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0124] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to execute the network traffic routing method as described in any of the above embodiments.
[0125] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.
[0126] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the network traffic diversion method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0127] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.
[0128] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0129] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.
[0130] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.
Claims
1. A method for network traffic diversion, characterized in that, include: Based on a pre-built power generation prediction model, combined with historical data and topology parameters, the predicted power generation of the power generation node is obtained. The power generation node includes a new energy power generation node and a communication node; the power generation node is located in the topology diagram; Based on the predicted power generation, the importance of the service to be transmitted and the link risk of the service to be transmitted are predicted; the importance of the service to be transmitted is calculated based on the importance of the source node and the importance of the destination node; the importance of the source node is calculated based on the predicted power generation of the source node; the importance of the destination node is predicted based on the predicted power generation of the destination node; the link risk of the service to be transmitted is calculated based on the importance of the source node, the importance of the destination node, and the importance of the service to be transmitted. Based on the importance of the service to be transmitted and the link risk level, the link cost is calculated; routing and spectrum allocation are performed based on the link cost; the routing algorithm is the KSP algorithm; the spectrum allocation algorithm is... Algorithm; the link cost is calculated based on the physical distance between the source node and the destination node, the link risk level, and the importance of the service to be transmitted; In response to the congestion during transmission of the service to be transmitted, and the importance of the service to be transmitted being higher than a preset importance threshold, a low-risk service with a bandwidth occupancy greater than that of the service to be transmitted is found in the link where the service to be transmitted is located. The low-risk service is rerouted, and the service to be transmitted is routed. If the importance of the service to be transmitted is lower than the preset importance threshold, or if the low-risk service does not exist in the link where the service to be transmitted is located, the service to be transmitted is placed in the blocking list.
2. The method according to claim 1, characterized in that, The power generation prediction model is trained using the following method: Obtain the training power generation time series data of the power generation node, and verify the stationarity of the training power generation time series data; In response to the stationary nature of the time-series power generation data used for training, the initial power generation prediction model is ordered and its parameters are estimated to obtain the power generation prediction model to be trained. The time-series power generation data used for training is input into the power generation prediction model to be trained to obtain the prediction data; The error is calculated based on the predicted power generation data and the true value of the power generation data; In response to the error being less than the error threshold, the trained power generation prediction model is used as the pre-built power generation prediction model.
3. A network traffic diversion device, characterized in that, include: The first prediction module is configured to predict the power generation of the power generation node based on a pre-built power generation prediction model, combined with historical data and topology parameters. The power generation node includes a new energy power generation node and a communication node; the power generation node is located in the topology diagram; The second prediction module is configured to predict the importance of the service to be transmitted and the link risk of the service to be transmitted based on the predicted power generation. The importance of the service to be transmitted is calculated based on the importance of the source node and the importance of the destination node; the importance of the source node is calculated based on the predicted power generation of the source node; the importance of the destination node is predicted based on the predicted power generation of the destination node. The link risk level of the service to be transmitted is calculated based on the importance of the source node, the importance of the destination node, and the importance of the service to be transmitted. The calculation module is configured to calculate the link cost of the link based on the importance of the service to be transmitted and the link risk level; perform routing calculation and spectrum allocation based on the link cost; the routing calculation algorithm is the KSP algorithm; the spectrum allocation algorithm is... Algorithm; the link cost is calculated based on the physical distance between the source node and the destination node, the link risk level, and the importance of the service to be transmitted; The diversion module is configured to respond to the congestion of the service to be transmitted during transmission and the importance of the service to be transmitted is higher than a preset importance threshold, and to find low-risk services in the link where the service to be transmitted is located whose bandwidth occupancy is greater than that of the service to be transmitted. The low-risk service is rerouted, and the service to be transmitted is routed. If the importance of the service to be transmitted is lower than the preset importance threshold, or if the low-risk service does not exist in the link where the service to be transmitted is located, the service to be transmitted is placed in the blocking list.
4. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 2.
5. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 2.