Multi-target path planning method and device for power system data forwarding network

Abstract

The invention relates to a multi-target path planning method and device for a power system data forwarding network. The method comprises the following steps: acquiring network topology data, and establishing a network topology directed graph according to the network topology data; obtaining a message, and determining a target function from a plurality of functions according to the priority label corresponding to the message; and determining an optimal path according to a pre-constructed heuristic function, the network topology directed graph and the target function. At least the problem of static weight lag can be solved, it is ensured that a low-delay path is allocated to high-priority services, and the effects of service grading-load balancing joint optimization and reduction of high-priority service delay are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data forwarding path planning, in particular to a multi-target path planning method and device for a power system data forwarding network. BACKGROUND

[0002] The power system data forwarding network carries multiple types of services such as protection, measurement and control, among which critical services such as relay protection require millisecond-level latency, and services such as PMU (synchronous phasor measurement) generate periodic large data streams.

[0003] However, the current path calculation is based on static network topology and fixed link weights (such as physical distance and bandwidth capacity), which easily leads to the problem that static routing cannot dynamically allocate paths according to service types, high-priority services are blocked when links are congested, and the network load presents minute-level mutations when new energy is connected to the grid, and the initial weight is still calculated, resulting in the problem that the actual high-load link is continuously overloaded. SUMMARY

[0004] Therefore, it is necessary to provide a multi-target path planning method and device for a power system data forwarding network to at least solve the problem of static weight lag, ensure the allocation of low-latency paths for high-priority services, achieve joint optimization of service classification and load balancing, and reduce the latency of high-priority services.

[0005] In a first aspect, the present application provides a multi-target path planning method for a power system data forwarding network, comprising:

[0006] Obtaining network topology data and establishing a network topology directed graph according to the network topology data;

[0007] Obtaining a message and determining a target function from a plurality of functions according to a priority label corresponding to the message;

[0008] Determining an optimal path according to a pre-constructed heuristic function, the network topology directed graph and the target function.

[0009] In some embodiments, obtaining network topology data comprises:

[0010] Obtaining a network node relationship table and a link basic attribute set based on an SDN controller, wherein the link basic attribute set includes physical latency, bandwidth upper limit and historical load baseline, and the network node relationship table includes the interconnection relationship between network transmission nodes;

[0011] Establishing a network topology directed graph according to the network node relationship table;

[0012] The network nodes in the network node relationship table are nodes of a directed graph, and the communication connection relationship between the network nodes is an edge of the directed graph.

[0013] In some embodiments, the method further comprises:

[0014] According to the basic propagation delay and the link load rate between the two connected network nodes, the link weight of the two connected network nodes is determined.

[0015] In some embodiments, the packet includes a first priority packet, a second priority packet, and a third priority packet;

[0016] The method further comprises:

[0017] When network congestion is detected, the objective function corresponding to the first priority packet is determined as the objective function corresponding to the second priority packet;

[0018] When it is detected that the retransmission rate of the target service flow is greater than a preset retransmission rate threshold, the objective function of the target service is determined as the objective function corresponding to the first priority packet;

[0019] When it is detected that the key link optical power fluctuation is greater than a preset optical power fluctuation threshold, all services are switched to the minimum hop count objective function.

[0020] In some embodiments, the optimal path is determined according to the pre-constructed heuristic function, the network topology directed graph, and the objective function, comprising:

[0021] According to the network topology directed graph, the service classification factor corresponding to the objective function, and the pre-constructed heuristic function, a target heuristic function is determined;

[0022] According to the service corresponding to the packet, a plurality of paths are determined;

[0023] The optimal path is determined from the plurality of paths according to the target heuristic function.

[0024] In some embodiments, the target heuristic function includes an estimated generation value;

[0025] The estimated generation value of the plurality of paths of the service corresponding to the first priority packet is calculated by the following steps:

[0026] A plurality of Manhattan distances and a plurality of basic delay coefficients of a plurality of paths between the target node and the end point of the service corresponding to the first priority packet are determined;

[0027] According to the plurality of Manhattan distances and the plurality of basic delay coefficients, an estimated generation value corresponding to each path is determined;

[0028] The estimated generation value of the plurality of paths of the service corresponding to the second priority packet is calculated by the following steps:

[0029] determining a plurality of path links of the service corresponding to the second priority message and a real-time load rate of each path link;

[0030] determining an estimated cost value corresponding to each path according to the plurality of path links of the service corresponding to the second priority message and the real-time load rate of each path link;

[0031] wherein the estimated cost value of the plurality of paths of the service corresponding to the third priority message is calculated by the following steps:

[0032] determining an estimated cost value corresponding to each path according to the hop distance and the hop delay of each path, and the hop delay is a measured value in the network.

[0033] In a second aspect, the present application further provides a multi-target path planning device of a power system data forwarding network, the device comprising:

[0034] a topology directed graph establishing module, configured to acquire network topology data and establish a network topology directed graph according to the network topology data;

[0035] a target function determining module, configured to acquire a message and determine a target function from a plurality of functions according to a priority label corresponding to the message;

[0036] an optimal path determining module, configured to determine an optimal path according to a pre-constructed heuristic function, the network topology directed graph and the target function.

[0037] In a third aspect, the present application further provides a computer device comprising a memory and a processor, the memory storing a computer program, and the processor realizing the following steps when executing the computer program:

[0038] acquiring network topology data and establishing a network topology directed graph according to the network topology data;

[0039] acquiring a message and determining a target function from a plurality of functions according to a priority label corresponding to the message;

[0040] determining an optimal path according to a pre-constructed heuristic function, the network topology directed graph and the target function.

[0041] In a fourth aspect, the present application further provides a computer readable storage medium storing a computer program, the computer program being executed by a processor to realize the following steps:

[0042] acquiring network topology data and establishing a network topology directed graph according to the network topology data;

[0043] acquiring a message and determining a target function from a plurality of functions according to a priority label corresponding to the message;

[0044] determine the optimal path according to the pre-constructed heuristic function, the network topology directed graph and the target function.

[0045] In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the following steps:

[0046] obtaining network topology data, and establishing a network topology directed graph according to the network topology data;

[0047] obtaining a message, and determining a target function from a plurality of functions according to a priority label corresponding to the message;

[0048] determine the optimal path according to the pre-constructed heuristic function, the network topology directed graph and the target function.

[0049] The multi-objective path planning method and device for the power system data forwarding network can at least solve the problem of static weight lag, ensure that high-priority services are allocated low-latency paths, achieve joint optimization of service classification and load balancing, and reduce the latency of high-priority services. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0051] Figure 1 a flowchart of the multi-objective path planning method for the power system data forwarding network in an embodiment;

[0052] Figure 2 a structural block diagram of the multi-objective path planning device based on the power system data forwarding network in an embodiment;

[0053] Figure 3 an internal structure diagram of the computer device in an embodiment.

[0054] Reference signs and descriptions:

[0055] 201, a topology directed graph establishing module; 202, a target function determining module; 203, an optimal path determining module. DETAILED DESCRIPTION

[0056] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0057] The multi-target path planning method of the power system data forwarding network provided by the embodiments of the present application can be applied to various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart sound boxes, smart televisions, smart air conditioners, smart vehicle-mounted devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0058] The power system data forwarding network carries multiple types of services such as protection, measurement and control. Key services such as relay protection require millisecond-level latency, while services such as PMU (synchronous phasor measurement) generate periodic large data streams.

[0059] However, the current path calculation is based on static network topology and fixed link weights (such as physical distance, bandwidth capacity), which easily leads to the problem that static routing cannot dynamically allocate paths according to service types, high-priority services are blocked when links are congested, and the network load presents minute-level mutations when new energy is connected to the grid, causing the actual high-load links to be continuously overloaded.

[0060] It should be noted that the traditional path calculation is based on static network topology and fixed link weights (such as physical distance, bandwidth capacity), which has two major contradictions: the first is the difference in service requirements: protection messages (such as GOOSE) require very low latency (≤4ms) and small data volume; measurement messages (such as PMU) allow higher latency (100ms) but have high bandwidth occupancy (≥2Mbps / node). Static routing cannot dynamically allocate paths according to service types, resulting in high-priority services being blocked when links are congested; the second is the dynamic nature of load state: new energy connected to the grid causes power flow fluctuations, resulting in minute-level mutations in network load. For example, when the output of a photovoltaic power station surges at noon, the load rate of adjacent communication links can increase from 30% to 90%, but the traditional shortest path algorithm still calculates according to the initial weight, resulting in the actual high-load links being continuously overloaded.

[0061] GOOSE, Generic Object Oriented Substation Event, a high-speed communication service defined in the IEC 61850 standard, is used for real-time data exchange in substation automation systems.

[0062] In the related art, in recent years, power data forwarding path optimization mainly evolves in two directions: the first is the improvement of graph algorithm. In 2018, Huawei proposed a time-varying weight Dijkstra algorithm, which adjusts the weight by predicting the periodic change of link load. However, prediction errors cause routers to constantly replace the selected path, making the data transmission path unstable and changing frequently. In 2020, Siemens applied Yen's K shortest path algorithm to provide backup paths for services, but did not solve the problem of dynamic switching when the main path is congested. The second is the improvement of load balancing mechanism. In 2021, the State Grid Electric Power Research Institute developed a traffic scheduling model based on QoS classification, which allocates a fixed bandwidth ratio according to the type of service, but lacks the ability to respond to real-time load.

[0063] Please refer to Figure 1 In one exemplary embodiment, a multi-objective path planning method for a power system data forwarding network is provided, comprising the following steps S101-S103. Among them:

[0064] S101, obtaining network topology data, and establishing a network topology directed graph according to the network topology data.

[0065] Specifically, obtaining network topology data includes: obtaining a network node relationship table and a link basic attribute set based on an SDN controller, wherein the link basic attribute set includes physical delay, bandwidth upper limit, and historical load baseline, and the network node relationship table includes the interconnection relationship between network transmission nodes; and establishing a network topology directed graph according to the network node relationship table.

[0066] Among them, the network nodes in the network node relationship table are nodes of the directed graph, and the communication connection relationship between the network nodes is an edge of the directed graph.

[0067] Among them, SDN is Software Defined Network, a network architecture paradigm that separates the control plane from the data plane of network devices, and centrally controls network traffic through software.

[0068] In some embodiments, the method further comprises determining the link weight of the two connected network nodes according to the basic propagation delay and the link load rate between the two connected network nodes.

[0069] Specifically, when acquiring the topology data, the SDN controller acquires a network node relationship table (containing the interconnection relationship of devices such as switches and routers) and a link basic attribute set (containing physical delay, bandwidth upper limit, and historical load baseline). A directed graph is established based on the network node relationship table, and the network nodes are nodes of the directed graph, and the communication connection relationship between the network nodes is an edge of the directed graph.

[0070] In some embodiments, the method further comprises: dynamic weight calculation:

[0071] ;

[0072] wherein, is the link weight of node i to j, is the basic propagation delay, is, is a load influence coefficient (dynamically adjusted according to the business peak and valley period, and the default value is 1.2).

[0073] wherein, the basic propagation delay is pre-determined by the cable length / medium type, and the unit is millisecond.

[0074] wherein, the current link load rate = real-time traffic / bandwidth upper limit, and the value is between 0 and 1.

[0075] wherein, the load influence coefficient is dynamically adjusted according to the business peak and valley period, and can be between 1.2 and 2.4.

[0076] Specifically, the adjustment is realized according to the historical load law of the power business peak and valley period and the average of the real-time whole network load rate, for example, in the peak period (such as the noon photovoltaic output peak), when > 75, from the default value 1.2 linearly to 2.0 (formula: ); in the valley period (such as night): when 30%, decreases to 0.5, weakening the influence of load on weight; in burst congestion: if the single link > 85%, is immediately multiplied (for example: 1.2-2.4), strengthening the weight punishment of the congestion link.

[0077] That is, the weight and the link delay in the application are positively correlated, and when a path with smaller delay needs to be selected, a path with the smallest weight can be selected as the target path.

[0078] The SDN controller collects link traffic data every 10 ms through the P4 programmable switch, updates , and dynamically adjusts the weight .

[0079] S102, acquire the message, and determine the target function from a plurality of functions according to a priority label corresponding to the message.

[0080] Specifically, the message includes a first priority message, a second priority message, and a third priority message.

[0081] The method further includes: when network congestion is detected, determining the target function corresponding to the first priority message as the target function corresponding to the second priority message; when a target service flow retransmission rate is detected to be greater than a preset retransmission rate threshold, determining the target function of the target service as the target function corresponding to the first priority message; and when a key link optical power fluctuation is detected to be greater than a preset optical power fluctuation threshold, switching all services to a minimum hop target function.

[0082] Specifically, when the service label is parsed, the message can be received and the priority label of the message can be parsed in the process of forwarding data in real time.

[0083] The priority label can be specifically obtained by mapping an original QoS field of a message header. For example, a DSCP value in an IP message: -DSCP 46 corresponds to P0; -DSCP 34 corresponds to P1; and -DSCP 18 corresponds to P2.

[0084] The P0 is a first priority, the P1 is a second priority, and the P2 is a third priority.

[0085] Specifically, in the field of power communication, it can be that DSCP 46 corresponds to a protection class message (such as a GOOSE message, label P0): the requirement is that the delay is less than or equal to 4 ms; DSCP 34 corresponds to a measurement class message (such as a PMU message, label P1): the requirement is bandwidth guarantee; and DSCP 18 corresponds to a management class message (such as a SCADA message, label P2): a higher delay is allowed.

[0086] In some embodiments, for some messages without a QoS field, a preset mapping relationship can be used for classification, such as a recording wave class (fault recording wave) being classified into P1 and a synchronization class (such as IEEE 1588) being classified into P0.

[0087] The QoS is a Quality of Service in network technology, and is a mechanism for controlling and guaranteeing network performance (such as bandwidth, delay, and reliability) of a specific application or user.

[0088] In some embodiments, for P0 services, a target function is used to calculate a path (from a starting node i to a target node j) of a minimized target function with the minimum total weight of the path as the target (equivalent minimum delay); and for P1 services, a target function , select the path with load rate approaching 50% for each link to forward, which can avoid link underload or overload on the one hand, and ensure that P1 service has enough bandwidth on the other hand; for P2 service, the objective function , the path with minimum hop count is selected. Hop_ij is the hop count required between node i and node j. Reducing hop count can reduce the time-consuming of intermediate node processing, reduce transmission delay, and also reduce packet loss rate and improve reliability.

[0089] For some special scenarios, other objective functions can also be selected, for example, for high-bandwidth links, the objective function can be used to force load balancing around 60%, which can reserve bandwidth to deal with burst traffic and reduce queuing delay and jitter.

[0090] For example, for new energy monitoring scenarios, the objective function can be selected for path selection. Here, maximizing the sum of the remaining bandwidth is equivalent to minimizing the used bandwidth. If the objective function is directly minimized, it is easy to cause some links to be overloaded or the traffic to be unevenly distributed; using the objective function of maximizing the remaining bandwidth, more attention is paid to the total amount and balance of available resources, and the core goal is to evenly distribute traffic and avoid congestion to improve resource flexibility.

[0091] Specifically, when network congestion is detected (the average value of the whole network > 70%), the P1 service target is automatically switched to , which prioritizes connectivity.

[0092] Specifically, when the retransmission rate of a certain service flow is > 5%, the objective function can be temporarily changed to , and the path with lower latency, smaller load, and better communication quality is selected for forwarding.

[0093] Specifically, when the key link optical power fluctuation is > 3dB, all services are switched to the minimum hop count objective function. Optical power fluctuation exceeding 3dB usually means that the link has intensified signal attenuation, increased noise interference, or equipment failure, at which time the signal-to-noise ratio (SNR) decreases, resulting in an increase in data packet transmission error rate and packet loss rate, which in turn triggers service retransmission, latency jitter, and even link interruption. Therefore, at this time, the minimum hop count path can be selected to improve forwarding reliability and reduce transmission loss and risk.

[0094] S103, according to the pre-constructed heuristic function, network topology directed graph and objective function, determine the optimal path.

[0095] The optimal path is determined according to a pre-constructed heuristic function, a network topology directed graph and a target function, and the optimal path comprises: determining a target heuristic function according to the network topology directed graph, a service classification factor corresponding to the target function and the pre-constructed heuristic function; determining a plurality of paths according to the service corresponding to the message; and determining the optimal path from the plurality of paths according to the target heuristic function.

[0096] Specifically, the target heuristic function comprises an estimated generation value.

[0097] The estimated generation value of the plurality of paths of the service corresponding to the first-priority message is calculated by the following steps: determining a plurality of Manhattan distances and a plurality of basic delay coefficients of the plurality of paths between the target node and the terminal point of the service corresponding to the first-priority message; and determining the estimated generation value corresponding to each path according to the plurality of Manhattan distances and the plurality of basic delay coefficients.

[0098] The estimated generation value of the plurality of paths of the service corresponding to the second-priority message is calculated by the following steps: determining a plurality of path links and a real-time load rate of each path link of the service corresponding to the second-priority message; and determining the estimated generation value corresponding to each path according to the plurality of path links and the real-time load rate of each path link of the service corresponding to the second-priority message.

[0099] The estimated generation value of the plurality of paths of the service corresponding to the third-priority message is calculated by the following steps: determining the estimated generation value corresponding to each path according to a hop distance and a hop delay of each path, and the hop delay is a measured value in the network.

[0100] In some embodiments, the target heuristic function can be:

[0101] ;

[0102] Here, this formula can also be called a cost function, is the total cost of node n, is the actual path cost (accumulated ) from the starting point i to node n, is the estimated cost from node n to the terminal point (the corresponding calculation formula can be selected or converted based on the target function), is the service classification factor (P0=0.8, P1=1.0, P2=1.2), which reduces the estimated weight ratio of high-priority services.

[0103] Specifically, the network topology directed graph G=(V, E, ), the target function and the service classification factor corresponding to the service ; the calculation formula of h(n) corresponding to the target function is selected to calculate the cost of each possible path.

[0104] wherein, for P0 traffic, the calculation of h(n) is: Manhattan distance between node n and the end point x base latency coefficient, to achieve the minimum latency orientation.

[0105] wherein, Manhattan distance is the distance between the network topology node coordinates of two nodes: D_manhattan=|x1-x2|+|y1-y2|, and the base latency coefficient is a coefficient related to the type of transmission medium (optical fiber).

[0106] Specifically, for P1 traffic, the calculation of h(n) is: to achieve load balancing orientation.

[0107] wherein, is the estimated path link set from the current node n to the end point t, and jk is the real-time load rate of link jk.

[0108] Specifically, for P2 traffic, the calculation of h(n) is: hop distance x hop latency, to achieve the minimum hop orientation.

[0109] In some possible embodiments, the path calculation process includes: initialization, adding the starting point A to the open list, calculating f(A);

[0110] Loop, take out the node with the minimum f(n) from the open list (i.e. A), expand its neighbors (B, C, etc.), calculate the f value of the neighbors and add them to the open list, until the node with the minimum f(n) is taken out is the end point, or, the open list is empty (the search path fails), or, the number of times of taking out the node in the current path calculation is equal to the maximum number of times.

[0111] wherein, remove the path of which >90% of the links to ensure availability. And after ensuring availability, the optimal path with the minimum cost is selected.

[0112] In some embodiments, generally three optimal paths K=3 are calculated, and are split and forwarded to provide redundancy backup.

[0113] After obtaining the optimal path, the optimal path is split into multiple sub-path segments, and a new sub-optimal path can be obtained by disabling one of the sub-path segments and re-executing the above algorithm.

[0114] Specifically, in the calculation process, conditions need to be received, including that the link load rate is less than 90%, and the path hop count is less than or equal to the optimal path hop count+2, to prevent detours from being too far.

[0115] In some embodiments, for the forwarding of P0 traffic, the optimal path occupies 70% of the traffic, and the suboptimal path occupies 30%; for the forwarding of P1 traffic, the three paths are load balanced in a ratio of 5:3:2; and for P2 traffic, only the optimal path is used for forwarding.

[0116] wherein the traffic grading factor The estimated cost can reduce the proportion in the total cost, and more rely on the actual cost, thereby preferentially selecting a path with lower actual delay.

[0117] Specifically, the K-path mechanism provides redundant backup.

[0118] The multi-objective path planning method and device for the power system data forwarding network of the present application can at least solve the problem of static weight lag, ensure that high-priority traffic is allocated to a low-latency path, achieve joint optimization of traffic grading and load balancing, and reduce the latency of high-priority traffic.

[0119] It should be understood that, although each step in the flowchart involved in each of the above embodiments is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or stages in other steps.

[0120] Based on the same inventive concept, the present application also provides a multi-objective path planning device for a power system data forwarding network for implementing the above-mentioned multi-objective path planning method for a power system data forwarding network. The implementation scheme for solving problems provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more multi-objective path planning device embodiments for a power system data forwarding network provided below can refer to the limitations of the multi-objective path planning method for a power system data forwarding network described above, and will not be repeated here.

[0121] Please refer to Figure 2In an example embodiment, a multi-objective path planning apparatus of a power system data forwarding network is provided, comprising: a topology directed graph establishing module 201, an objective function determining module 202, and an optimal path determining module 203. The topology directed graph establishing module 201 is configured to acquire network topology data, and establish a network topology directed graph according to the network topology data. The objective function determining module 202 is configured to acquire a message, and determine an objective function from a plurality of functions according to a priority label corresponding to the message. The optimal path determining module 203 is configured to determine an optimal path according to a pre-constructed heuristic function, the network topology directed graph, and the objective function.

[0122] The modules in the multi-objective path planning apparatus of the power system data forwarding network can be implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the modules.

[0123] In an example embodiment, a computer device is provided, which can be a terminal. The computer device comprises a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, near field communication (NFC), or other technologies. The computer program is executed by the processor to implement a multi-objective path planning method of a power system data forwarding network. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball, or touchpad arranged on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0124] Those skilled in the art can understand that Figure 3The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] In one exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0126] Obtaining network topology data, and establishing a network topology directed graph according to the network topology data;

[0127] Obtaining a message, and determining a target function from a plurality of functions according to a priority label corresponding to the message;

[0128] Determining an optimal path according to a pre-constructed heuristic function, the network topology directed graph, and the target function.

[0129] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implements the following steps when executed by a processor:

[0130] Obtaining network topology data, and establishing a network topology directed graph according to the network topology data;

[0131] Obtaining a message, and determining a target function from a plurality of functions according to a priority label corresponding to the message;

[0132] Determining an optimal path according to a pre-constructed heuristic function, the network topology directed graph, and the target function.

[0133] In one embodiment, a computer program product is provided, comprising a computer program, and the computer program implements the following steps when executed by a processor:

[0134] Obtaining network topology data, and establishing a network topology directed graph according to the network topology data;

[0135] Obtaining a message, and determining a target function from a plurality of functions according to a priority label corresponding to the message;

[0136] Determining an optimal path according to a pre-constructed heuristic function, the network topology directed graph, and the target function.

[0137] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing relevant hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, the processes of the above-mentioned embodiment methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0138] The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, it should be considered as the scope of the present application.

[0139] The above embodiments only express several implementation ways of the present application, and the description is specific and detailed, but it should not be understood as a limitation to the patent scope of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A multi-objective path planning method for a power system data forwarding network, characterized in that, The method includes: Obtain network topology data, and establish a directed network topology graph based on the network topology data; Obtain the message and determine the target function from multiple functions based on the priority label corresponding to the message; The optimal path is determined based on a pre-constructed heuristic function, a directed graph of the network topology, and an objective function.

2. The multi-objective path planning method according to claim 1, characterized in that, The acquisition of network topology data includes: The network node relationship table and link basic attribute set are obtained based on the SDN controller. The link basic attribute set includes physical latency, bandwidth limit, and historical load baseline. The network node relationship table includes the interconnection relationship between network transmission nodes. Based on the network node relationship table, construct a directed graph of the network topology; In this context, the network nodes in the network node relationship table are nodes in a directed graph, and the communication connections between network nodes are edges in the directed graph.

3. The multi-objective path planning method according to claim 2, characterized in that, The method further includes: The link weights of two connected network nodes are determined based on the basic propagation delay and link load rate between them.

4. The multi-objective path planning method according to claim 1, characterized in that, The message includes a first priority message, a second priority message, and a third priority message; The method further includes: When network congestion is detected, the objective function corresponding to the first priority message is determined as the objective function corresponding to the second priority message; When the retransmission rate of the target service flow is detected to be greater than the preset retransmission rate threshold, the objective function of the target service is determined as the objective function corresponding to the first priority message. When the optical power fluctuation of a critical link is detected to be greater than the preset optical power fluctuation threshold, all services are switched to the minimum hop count objective function.

5. The multi-objective path planning method according to claim 4, characterized in that, Based on a pre-constructed heuristic function, a directed graph of the network topology, and an objective function, the optimal path is determined, including: The target heuristic function is determined based on the directed graph of the network topology, the business classification factor corresponding to the objective function, and the pre-constructed heuristic function. Based on the service corresponding to the message, multiple paths are determined; The optimal path is determined from the plurality of paths based on the target heuristic function.

6. The multi-objective path planning method according to claim 5, characterized in that, The target heuristic function includes the estimated cost; The estimated cost of multiple paths for the service corresponding to the first priority message is calculated through the following steps: Determine multiple Manhattan distances and multiple base delay coefficients for multiple paths between the target node and the destination of the service corresponding to the first priority message; The estimated cost value for each path is determined based on multiple Manhattan distances and multiple base delay coefficients. The estimated cost of multiple paths for the service corresponding to the second priority message is calculated through the following steps: Determine the multiple path links of the service corresponding to the second priority message and the real-time load rate of each path link; Based on the multiple path links of the service corresponding to the second priority message and the real-time load rate of each path link, determine the estimated cost value corresponding to each path. The estimated cost of multiple paths for the service corresponding to the third priority message is calculated through the following steps: Based on the hop count distance and hop count delay of each path, the estimated cost corresponding to each path is determined, where the hop count delay is the measured value in the network.

7. A multi-objective path planning device for a power system data forwarding network, characterized in that, The device includes: The directed graph topology building module is used to acquire network topology data and build a directed graph topology based on the network topology data. The objective function determination module is used to acquire messages and determine the objective function from multiple functions based on the priority label corresponding to the message. The optimal path determination module is used to determine the optimal path based on a pre-built heuristic function, a directed graph of the network topology, and an objective function.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images