Network path planning method, device, electronic device and storage medium

Abstract

The present application provides a network path planning method, device, electronic device and storage medium. According to historical flow data, a characteristic flow matrix is ​​obtained, and the characteristic flow matrix and the business characteristics of the power data network are combined to screen out nodes that play a key role in flow path planning. These nodes are used to upgrade network nodes and plan paths, thereby improving the utilization rate of network links and ensuring the normal operation of the network.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a network path planning method, device, electronic device and storage medium. Background Art

[0002] With the continuous reform of the power industry and the continuous integration of new technologies such as artificial intelligence, 5G (5th generation), and the Internet of Things with power services, the traffic scale in the power data network has shown explosive growth. At the same time, as the types of power services are also increasing, the network architecture is becoming more and more complex, and some business traffic is dynamic and bursty, which puts higher requirements on the load capacity of traditional IPv6 (Internet Protocol Version 6) networks. SRv6 (Segment Routing over IPv6) is a new generation of IP (Internet Protocol) bearer protocol based on traditional IPv6 networks, which can improve the flexibility of routing planning in the network and enhance the load capacity of the network. However, due to economic, technical, time and other factors, the network cannot complete the upgrade of IPv6 to SRv6 for all devices in a short time. Therefore, some IPv6 network devices can be upgraded to SRv6 network devices first, so that traditional IPv6 network devices and SRv6 network devices will coexist in a long-term state, which is called "hybrid SRv6 network".

[0003] In this "hybrid SRv6 network" scenario, how to select appropriate nodes for SRv6 upgrade and how to maximize the routing planning effect of a limited number of SRv6 devices in the hybrid SRv6 network are key issues that need to be addressed. Summary of the invention

[0004] In view of this, the purpose of the present application is to propose a network path planning method, device, electronic device and storage medium.

[0005] Based on the above objectives, the present application provides a network path planning method, including:

[0006] Acquire historical traffic data, and obtain a characteristic traffic matrix based on the historical traffic data;

[0007] Obtaining a deployable index of a network node according to the service characteristics of the network and the characteristic traffic matrix;

[0008] According to the deployable index of the network node, a network path is selected for planning.

[0009] Optionally, obtaining a characteristic traffic matrix according to the historical traffic data includes:

[0010] According to the historical traffic data, a real traffic matrix is ​​obtained;

[0011] According to the real traffic matrix, a predicted traffic matrix is ​​obtained;

[0012] Based on the real traffic matrix, the characteristics of the predicted traffic matrix are extracted to obtain the characteristic traffic matrix.

[0013] Optionally, obtaining a deployable index of a network node according to a service characteristic of the network and the characteristic traffic matrix includes:

[0014] Acquire a network topology, and calculate a first shortest path set and a second shortest path set of the network topology;

[0015] Calculating the traffic load of the network node according to the first shortest path set and the characteristic traffic matrix;

[0016] Calculating the betweenness centrality of network nodes according to the first shortest path set;

[0017] Analyzing the service distribution in the first shortest path set according to the service characteristics of the network to obtain the service bearing of the network node;

[0018] Calculating the influence of the network node on the path according to the second shortest path set;

[0019] The degree of the node in the network topology is obtained, and the deployability index of the network node is calculated according to the traffic load, the betweenness centrality, the service carrying, the influence degree and the degree of the node.

[0020] Optionally, analyzing the service distribution in the first shortest path set according to the service characteristics of the network to obtain the service bearer of the network node includes:

[0021] According to the service characteristics of the network, the existing network services are quantitatively graded to obtain an importance weight matrix of the network services;

[0022] Analyzing, according to the network service, services carried by the paths in the first shortest path set;

[0023] The service carrying of the network node is obtained according to the importance weight matrix and the services carried by the paths in the first shortest path set.

[0024] Optionally, calculating the influence of the network node on the path according to the second shortest path set includes:

[0025] In response to the presence of two paths with repeated target nodes in the second shortest path set, and the next nodes of the target nodes in the two paths are not repeated, calculating the influence index of the target node on the path;

[0026] The influence degree of the network node on the path is obtained according to the influence degree index.

[0027] Optionally, the selecting a network path for planning according to the deployable index of the network node includes:

[0028] According to the deployable index of the network node, a deployment path set is obtained; wherein the deployment path set includes a plurality of network paths;

[0029] Determining, according to the deployment path set, a deployment value range for each network path in the deployment path set;

[0030] Obtaining a link traffic load matrix of the network, and obtaining a path selection strategy value according to the link traffic load matrix;

[0031] In response to the path selection policy value being within the deployment value range, a network path corresponding to the deployment value range is selected for planning.

[0032] Optionally, obtaining a path selection strategy value according to the link traffic load matrix includes:

[0033] Based on the pre-built path planning model, a path selection strategy value is obtained according to the link traffic load matrix;

[0034] Wherein, the negative number of the maximum link utilization of the network is used as the feedback function of the path planning model.

[0035] Based on the above purpose, the present application also provides a network path planning device, including:

[0036] An acquisition module, configured to acquire historical traffic data;

[0037] An extraction module is configured to obtain a characteristic traffic matrix according to the historical traffic data;

[0038] A calculation module is configured to obtain a deployable index of a network node according to the service characteristics of the network and the characteristic traffic matrix;

[0039] The planning module is configured to select a network path for planning according to the deployable index of the network node.

[0040] Based on the above purpose, the present 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 when the processor executes the program, the method described in any of the above embodiments is implemented.

[0041] Based on the above purpose, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method described in any of the above embodiments.

[0042] From the above, it can be seen that the network path planning method, device, electronic device and storage medium provided by the present application, by combining the business characteristics of the power data network, screen out the nodes that play a key role in traffic path planning, and use these nodes to upgrade the network nodes and plan the paths, thereby improving the utilization rate of the network links and ensuring the normal operation of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A flowchart of an exemplary network path planning method according to an embodiment of the present application is shown.

[0045] Figure 2 A schematic diagram showing an application scenario of a network path planning method according to an embodiment of the present application.

[0046] Figure 3 A schematic diagram of a network path planning device according to an embodiment of the present application is shown.

[0047] Figure 4 A schematic diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0049] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like 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.

[0050] As described in the background technology, it is particularly important to propose a dynamic routing planning method suitable for hybrid SRv6 network scenarios. In related technologies, the network path deployment strategy simply considers the topological characteristics of the network (such as key nodes in the case of the shortest path), without considering factors such as specific traffic characteristics and business characteristics in the power data network. If this deployment strategy is applied to a hybrid SRv6 network, the role that SRv6 devices can play in network routing planning will be reduced. In addition, in routing planning, deep reinforcement learning can continuously learn and improve according to the network status and output a suitable routing planning strategy. However, in related technologies, traditional deep reinforcement learning models consider the controllability of all network nodes, and the output content is usually the weight of the link, and then the path set is calculated based on the output link weight. In the hybrid SRv6 network scenario, due to the limited number of controllable paths, the output weight of the entire matrix has little effect on the path calculation results and converges slowly.

[0051] In response to the above problems, this application proposes a network path planning method, which takes into account the specific traffic characteristics and topological characteristics of the power data network, designs an incremental deployment plan for SRv6 in combination with business characteristics, and performs dynamic routing planning on the hybrid SRv6 network based on the deep reinforcement learning DDQN algorithm (Double DQN, which is a deep learning algorithm of Double Q-Learning). Considering that only SRv6 nodes are controllable, the path of controllable flow is planned for each SRv6 node according to the network traffic, thereby improving the network link utilization and reducing the probability of link congestion.

[0052] Figure 1 A flowchart of an exemplary network path planning method according to an embodiment of the present application is shown. The method may include the following steps.

[0053] In step S101, historical flow data is obtained, and a characteristic flow matrix is ​​obtained based on the historical flow data. The historical flow data in the power data network is analyzed by a network flow prediction model based on LSTM (Long Short Term Memory) and linear regression function to capture the periodic flow change characteristics in the network.

[0054] Before training the constructed network traffic prediction model, it is necessary to collect the historical traffic data of the network as the training data set of the model. Since the business traffic matrix in the power data network has the characteristics of periodic distribution, the historical traffic data in the power data network is periodically collected on a daily basis as the training data of the traffic prediction model. The collected data mainly includes the source node of the flow (flow, i.e., network flow), the destination node, the size of the flow, the timestamp information, etc. Then, the collected data is grouped in units of weeks as an Epoch (one Epoch is equal to training once with all the data samples in the training data set) cycle of model training.

[0055] In some embodiments, obtaining a characteristic traffic matrix based on the historical traffic data may further include: obtaining a real traffic matrix based on the historical traffic data; obtaining a predicted traffic matrix based on the real traffic matrix; and extracting features of the predicted traffic matrix based on the real traffic matrix to obtain the characteristic traffic matrix.

[0056] The collected training data set is used to train a network traffic prediction model based on the LSTM model and linear regression function. The LSTM model includes 1 input layer, z LSTM network layers, and 1 input layer, where the setting of z is related to the number of overall traffic in the network. The input vector of the model is the traffic matrix x at time t t =(f 1 (t), f 2 (t), f 3 (t), ..., f n (t)), where f n (t) represents the network flow f n The flow size at time t, n represents the number of flows marked by <source node-destination node>. This flow matrix is ​​extracted from the collected historical flow data. Therefore, this flow matrix can be a real flow matrix. The input of a model training cycle T is X T =(x 1 , x 2 , ..., x t ), where T is in weeks and t is in days. The output vector of the output layer is P t+1 =(f 1 (t+1), f2 (t+1), f 3 (t+1), ..., f n (t+1)), where P t+1 is the traffic matrix predicted by the model at time t+1, that is, the predicted traffic matrix output by the LSTM model. According to the results of the predicted traffic matrix output by the model output layer, the results are fitted using a polynomial linear regression function. Combining the fitting results, the traffic matrix prediction results (e.g., the predicted traffic matrix), and the actual measurement data (e.g., the real traffic matrix), the representative traffic matrix M of the network traffic in period T is obtained. T =(M 1 , M 2 , ..., M t ), the traffic matrix M T To include network features M t The characteristic flow matrix of .

[0057] In step S103, the deployable index of the network node is obtained according to the service characteristics of the network and the characteristic traffic matrix. Based on the characteristic traffic matrix output by the network traffic prediction model, combined with the service characteristics of different power data networks (for example, reliability requirements and importance, adjacent loads of nodes carrying key services, traffic loads, and the degree of influence on path results, etc.), the influence index of the network node is obtained as the strategic basis for the incremental deployment of SRv6.

[0058] In some embodiments, obtaining the deployable index of the network node according to the service characteristics of the network and the characteristic traffic matrix may further include: obtaining the network topology, and calculating the first shortest path set and the second shortest path set of the network topology; calculating the traffic load of the network node according to the first shortest path set and the characteristic traffic matrix; calculating the betweenness centrality of the network node according to the first shortest path set; analyzing the service distribution in the first shortest path set according to the service characteristics of the network to obtain the service carrying capacity of the network node; calculating the degree of influence of the network node on the path according to the second shortest path set; obtaining the degree of the node in the network topology, and calculating the deployable index of the network node according to the traffic load, the betweenness centrality, the service carrying capacity, the degree of influence and the degree of the node.

[0059] Since this method is to upgrade the network based on the existing non-SRv6 network, the network topology of the existing non-SRv6 network can be directly obtained. The Dijkstra algorithm (a shortest path algorithm) is used to calculate the shortest path set Pshort of all flows in the network topology, and Pshort can be the first shortest path set. The Yen's algorithm (a shortest path algorithm) is used to calculate the k shortest path set Pkshort of all flows in the network topology, and Pkshort can be the second shortest path set. In some embodiments, k can be set to 3.

[0060] According to the path set Pshort and the characteristic flow matrix M T Calculate the traffic load (TrafficLoad, TL) of the network node, based on the path set Pshort, and calculate the betweenness centrality JL of the network node through the following agency:

[0061]

[0062] Among them, g(v) is the betweenness centrality, θ src，dst is the number of shortest paths from node src to node dst, θ src，dst (v) is the number of times these paths pass through node v.

[0063] In some embodiments, analyzing the service distribution in the first shortest path set according to the service characteristics of the network to obtain the service carrying capacity of the network node may further include: quantizing and classifying the existing network services according to the service characteristics of the network to obtain an importance weight matrix of the network services; analyzing the services carried by the paths in the first shortest path set according to the network services; and obtaining the service carrying capacity of the network node according to the importance weight matrix and the services carried by the paths in the first shortest path set.

[0064] According to the service characteristics of different power data networks (for example, safety requirements, reliability requirements, accuracy requirements, etc.), the analytic hierarchy process is used to quantify the existing services in the network and obtain the importance weight matrix W of the network services. Combined with the specific power data network services, the services carried by the paths in the path set Pshort and their distribution are analyzed. For example, path v 2 →v 1 and v 10 →v 8 →v 6 Mainly carries the traffic of relay protection services, path v 1 →v 8 →v 9It mainly carries the traffic of dispatch telephone service. The importance weight of relay protection service is 3, and the importance weight of dispatch telephone service is 2. Then v 8 The service load value is 3+2=5. In this way, the service load SL (Service Load) of all nodes is calculated.

[0065] In some embodiments, calculating the degree of influence of the network node on the path based on the second shortest path set may further include: in response to the presence of two paths with repeated target nodes in the second shortest path set, and the next node of the target node in the two paths is not repeated, calculating the influence index of the target node on the path; based on the influence index, obtaining the influence of the network node on the path.

[0066] The influence degree PL of the network node on the path is calculated based on the path set Pkshort. The calculation steps are as follows:

[0067] For each flow f in the network i , the source node is src, the destination node is dst, f i The path set is Pkshort(src, dst). If there are repeated intermediate nodes (for example, target nodes) in two paths and the next hop of the node is not repeated, the importance index of the target node for the path is increased by 1. For example, for the path set <(v 1 →v 2 →v 4 -v 5 ), (v 1 →v 2 →v 3 →v 5 ), (v 1 →v 7 →v 5 )>, node v 2 To repeat the intermediate node, which affects the subsequent path, then v 2 The importance index of the path is increased by 1. All flows in the network are traversed, and the importance index of the path is accumulated to obtain the final PL value of the node.

[0068] The node indexes TL, JL, SL, PL, and the node degree NL in the network topology are normalized to calculate the deployable index of the network node:

[0069] D(v)=β 0 *TL(v)+β 1 *SL(v)+β 2 *PL+(1-β 0 -β 1 -β2 )*(NL+JL)

[0070] Among them, β 0 , β 1 , β 2 It is the weight of each index, which is set according to the specific network topology.

[0071] The higher the deployability index D(v) of a network node, the more suitable it is for upgrading to an SRv6 device.

[0072] In step S105, a network path is selected for planning according to the deployable index of the network node, and dynamic path planning is performed in a hybrid SRv6 scenario with the improvement of network link utilization as the optimization goal.

[0073] Since only SRv6 nodes are controllable in the hybrid SRv6 scenario, the paths in the network can be divided into two types: controllable paths and uncontrollable paths. A controllable path is a path that contains SRv6 nodes, and different forwarding paths can be selected for the same <source node-destination node> flow by deploying different SID lists. For non-SRv6 nodes, traffic is forwarded according to the shortest path. For SRv6 nodes, the traffic forwarding path is adjusted according to the SID (Segment ID, the network path is divided into several segments, each segment has a SID) list issued by the routing planning model. Similarly, flows in the network can also be divided into controllable flows and uncontrollable flows.

[0074] In some embodiments, selecting a network path for planning based on the deployable index of the network node may further include: obtaining a deployment path set based on the deployable index of the network node; wherein the deployment path set includes a number of network paths; determining a deployment value range for each network path in the deployment path set based on the deployment path set; obtaining a link traffic load matrix of the network, and obtaining a path selection strategy value based on the link traffic load matrix; in response to the path selection strategy value being within the deployment value range, selecting a network path corresponding to the deployment value range for planning.

[0075] like Figure 2 As shown in the figure, SRv6 nodes are deployed in a known power data network. A dynamic routing planning model based on the deep reinforcement learning DDQN algorithm is constructed. The model contains state input, action output, and feedback function. The state input Sate of the model is the network link state load information obtained from the known power data network, that is, the link traffic load matrix of the network. The action output Action is the delivery of the path strategy, that is, the path selection strategy of all SRv6 nodes for their controllable flows issued by the routing planning module based on deep reinforcement learning.

[0076] According to the deployable index of the network node obtained in the above steps, the network nodes that can be upgraded to SRv6 devices can be determined (the higher the deployable index D(v) of the network node, the more suitable it is for upgrading to SRv6 devices). According to the determined SRv6 nodes, the paths in the network that can be controlled by the SRv6 nodes and the network flows from user applications can be determined, and a set of deployment paths for SRv6 nodes with controllable flows can be obtained, which contains several network paths. Randomly sort the optional paths for different flows of each SRv6 node to facilitate numbering of network paths. Then construct the <value range-path> mapping model, and the value range in the model is the deployment value range of each network path in the deployment path set. Assume that the dynamic routing planning model obtains the output value of the path selection strategy of the action according to the input network link traffic load matrix as f 1 (s 1 ,s 2 ,..,s c ), where c is the number of SRv6 nodes, s c Indicates an SRv6 node. Based on the path selection policy value, you can get the path selection result of the SRv6 node.

[0077] For example, for a controllable flow f 1 , SRv6 nodes c The set of optional paths is <p1, p2>, then the range of selecting p1 is (0, 0.5), and the range of selecting p2 is (0.5, 1). If the path selection strategy value output by the model is within the deployment value range of p1 (0, 0.5), then path p1 is selected for network path planning, that is, the controllable flow f 1 will flow through path p1; if the path selection strategy value output by the model is within the deployment value range of p2 (0.5, 1), path p2 will be selected for network path planning, that is, the controllable flow f 1 Will flow through path p2.

[0078] In some embodiments, obtaining the path selection strategy value according to the link traffic load matrix may further include: obtaining the path selection strategy value according to the link traffic load matrix based on a pre-constructed path planning model; wherein the negative of the maximum link utilization of the network is used as a feedback function of the path planning model.

[0079] In the dynamic routing planning model (i.e., path planning model) based on the deep reinforcement learning DDQN algorithm, the model's feedback function Reward is the negative of the maximum link utilization of the network after the decision is executed. The maximum link utilization is minimized to achieve the purpose of improving the network link utilization.

[0080] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0081] It should be noted that the above describes some embodiments of the present 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 an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] Based on the same technical concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a network path planning device.

[0083] refer to Figure 3 , the network path planning device comprises:

[0084] The acquisition module 301 may be configured to acquire historical traffic data.

[0085] The extraction module 302 is configured to obtain a characteristic flow matrix according to the historical flow data;

[0086] In some embodiments, the extraction module 302 can also be configured to obtain a real traffic matrix based on the historical traffic data; obtain a predicted traffic matrix based on the real traffic matrix; and extract the characteristics of the predicted traffic matrix based on the real traffic matrix to obtain the characteristic traffic matrix.

[0087] The calculation module 303 is configured to obtain a deployable index of a network node according to the service characteristics of the network and the characteristic traffic matrix;

[0088] In some embodiments, the computing module 303 can also be configured to obtain the network topology and calculate the first shortest path set and the second shortest path set of the network topology; calculate the traffic load of the network node based on the first shortest path set and the characteristic traffic matrix; calculate the betweenness centrality of the network node based on the first shortest path set; analyze the service distribution in the first shortest path set according to the service characteristics of the network to obtain the service carrying capacity of the network node; calculate the degree of influence of the network node on the path according to the second shortest path set; obtain the degree of the node in the network topology, and calculate the deployability index of the network node based on the traffic load, the betweenness centrality, the service carrying capacity, the degree of influence and the degree of the node.

[0089] In some embodiments, the computing module 303 can also be configured to quantify the existing network services according to the service characteristics of the network to obtain an importance weight matrix of the network services; analyze the services carried by the paths in the first shortest path set according to the network services; and obtain the service carrying capacity of the network node according to the importance weight matrix and the services carried by the paths in the first shortest path set.

[0090] In some embodiments, the calculation module 303 can also be configured to calculate the influence index of the target node on the path in response to the presence of two paths with repeated target nodes in the second shortest path set, and the next node of the target node in the two paths is not repeated; and obtain the influence degree of the network node on the path based on the influence index.

[0091] The planning module 304 is configured to select a network path for planning according to the deployment index of the network node.

[0092] In some embodiments, the planning module 304 can also be configured to obtain a deployment path set based on the deployable index of the network node; wherein the deployment path set includes a number of network paths; according to the deployment path set, determine the deployment value range of each network path in the deployment path set; obtain the link traffic load matrix of the network, and obtain the path selection strategy value according to the link traffic load matrix; in response to the path selection strategy value being within the deployment value range, select the network path corresponding to the deployment value range for planning.

[0093] In some embodiments, the planning module 304 can also be configured to obtain a path selection strategy value based on a pre-built path planning model and the link traffic load matrix; wherein the negative of the maximum link utilization of the network is used as a feedback function of the path planning model.

[0094] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0095] The device of the above embodiment is used to implement the corresponding network path planning method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0096] Based on the same technical concept, corresponding to any of the above-mentioned embodiments, the present 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 when the processor executes the program, the network path planning method described in any of the above embodiments is implemented.

[0097] Figure 4 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0098] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an 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.

[0099] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0100] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0101] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0102] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0103] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0104] The electronic device of the above embodiment is used to implement the corresponding network path planning method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0105] Based on the same technical concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the network path planning method described in any of the above embodiments.

[0106] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0107] The computer instructions stored in the storage medium of the above embodiments are used to enable the computer to execute the network path planning method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0108] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0109] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0110] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, 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 use the embodiments discussed.

[0111] The embodiments of the present 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 the present application should be included in the scope of protection of the present application.

Claims

1. A network path planning method, characterized in that: include: Acquire historical traffic data, and obtain a characteristic traffic matrix based on the historical traffic data; Obtaining a deployable index of a network node according to the service characteristics of the network and the characteristic traffic matrix; Selecting a network path for planning according to the deployable index of the network node; The obtaining of the deployable index of the network node according to the service characteristics of the network and the characteristic traffic matrix includes: Acquire a network topology, and calculate a first shortest path set and a second shortest path set of the network topology, wherein the first shortest path set is calculated using a Dijkstra algorithm, and the second shortest path set is calculated using a Yen's algorithm; Calculating the traffic load of the network node according to the first shortest path set and the characteristic traffic matrix; Calculating the betweenness centrality of network nodes according to the first shortest path set; Analyzing the service distribution in the first shortest path set according to the service characteristics of the network to obtain the service bearing of the network node; Calculating the influence of the network node on the path according to the second shortest path set; The degree of the node in the network topology is obtained, and the deployability index of the network node is calculated according to the traffic load, the betweenness centrality, the service load, the influence degree and the degree of the node. The deployability index of the network node is expressed as: in, is the weight of each index, is the traffic load, For the business bearer, For the degree of impact, is the degree of the node, is the betweenness centrality, Represents the network node.

2. The method according to claim 1, characterized in that: The characteristic flow matrix is ​​obtained according to the historical flow data, including: According to the historical traffic data, a real traffic matrix is ​​obtained; According to the real traffic matrix, a predicted traffic matrix is ​​obtained; Based on the real traffic matrix, the characteristics of the predicted traffic matrix are extracted to obtain the characteristic traffic matrix.

3. The method according to claim 1, characterized in that The analyzing, according to the service characteristics of the network, the service distribution in the first shortest path set to obtain the service bearing of the network node includes: According to the service characteristics of the network, the existing network services are quantitatively graded to obtain an importance weight matrix of the network services; Analyzing, according to the network service, services carried by the paths in the first shortest path set; The service carrying of the network node is obtained according to the importance weight matrix and the services carried by the paths in the first shortest path set.

4. The method according to claim 1, characterized in that: The calculating, according to the second shortest path set, the influence degree of the network node on the path includes: In response to the presence of two paths with repeated target nodes in the second shortest path set, and the next nodes of the target nodes in the two paths are not repeated, calculating the influence index of the target node on the path; The influence degree of the network node on the path is obtained according to the influence degree index.

5. The method according to claim 1, characterized in that The selecting a network path for planning according to the deployable index of the network node includes: According to the deployable index of the network node, a deployment path set is obtained; wherein the deployment path set includes a plurality of network paths; Determining, according to the deployment path set, a deployment value range for each network path in the deployment path set; Obtaining a link traffic load matrix of the network, and obtaining a path selection strategy value according to the link traffic load matrix; In response to the path selection policy value being within the deployment value range, a network path corresponding to the deployment value range is selected for planning.

6. The method according to claim 5, characterized in that The obtaining a path selection strategy value according to the link traffic load matrix includes: Based on the pre-built path planning model, a path selection strategy value is obtained according to the link traffic load matrix; Wherein, the negative number of the maximum link utilization of the network is used as the feedback function of the path planning model.

7. A network path planning device, characterized in that: include: An acquisition module, configured to acquire historical traffic data; An extraction module is configured to obtain a characteristic traffic matrix according to the historical traffic data; A calculation module is configured to obtain a deployable index of a network node according to the service characteristics of the network and the characteristic traffic matrix; A planning module, configured to select a network path for planning according to the deployable index of the network node; The calculation module is further configured to obtain a network topology and calculate a first shortest path set and a second shortest path set of the network topology, wherein the first shortest path set is calculated using a Dijkstra algorithm, and the second shortest path set is calculated using a Yen's algorithm; Calculating the traffic load of the network node according to the first shortest path set and the characteristic traffic matrix; Calculating the betweenness centrality of network nodes according to the first shortest path set; Analyzing the service distribution in the first shortest path set according to the service characteristics of the network to obtain the service bearing of the network node; Calculating the influence of the network node on the path according to the second shortest path set; The degree of the node in the network topology is obtained, and the deployability index of the network node is calculated according to the traffic load, the betweenness centrality, the service load, the influence degree and the degree of the node. The deployability index of the network node is expressed as: in, is the weight of each index, is the traffic load, For the business bearer, For the degree of impact, is the degree of the node, is the betweenness centrality, Represents the network node.

8. 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, the method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

Images