A routing planning method for relay protection private network based on genetic algorithm

Abstract

The present invention relates to a method for relay protection private network routing planning based on a genetic algorithm, comprising: inputting relevant parameters of the actual network topology, switching nodes, and optical cable links; directly determining the first and second routes for each service; encoding chromosomes using a priority-based encoding method; randomly generating an initial population and setting a maximum genetic generation number; performing multiple rounds of selection, crossover, and mutation operations on the population based on the maximum genetic generation number; after the genetic algorithm iteration is completed, selecting the chromosome of the optimal individual in the current population, and decoding it to obtain the third route for each service. The present invention can meet the "dual protection and three routes" requirements of relay protection service routing planning and reduce the total transmission delay of all services while meeting the relay protection service delay constraints. The present invention can effectively balance the load of the optical cable link and improve the reliability of relay protection service transmission.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system communications, and in particular relates to a relay protection private network routing planning method based on a genetic algorithm. Background Art

[0002] With the advancement of computer and communications technologies, traditional power grids are evolving into smart grids with greater reliability, sustainability, and flexibility. The power communication network is a crucial component of the smart grid, carrying a wide range of services required for grid production and operations. Among these, relay protection services are the most crucial, ensuring the smooth transmission of electric energy between power stations. The high-quality development of the power grid requires reliable data transmission for relay protection services. However, with the increasing variety and number of services on the power communication network, it is necessary to establish a dedicated relay protection network specifically for transmitting relay protection service data.

[0003] The network generally contains multiple switching nodes and multiple optical cable links. The switching nodes of the relay protection private network basically coincide with the power sites of the power grid, and the optical cable links basically coincide with the power lines, so that direct optical cables can be used to transmit relay protection service data. In addition, if there is an optical cable link between two switching nodes, there must be two optical cable links. In the relay protection private network, each switching node is equipped with two sets of protection equipment, respectively called protection one and protection two. Each set of protection equipment has two ports, namely port A and port B. Therefore, the source node and destination node of the relay protection service have four ports, so there are four communication channels. For these four communication channels, three independent communication routes need to be configured, respectively called the first route, the second route, and the third route. Such a configuration requirement is called "dual protection and three routes". The architecture diagram of the relay protection private network is as follows: Figure 1 As shown. Assume that the source node and destination node of a business are v i and v j The diagram of its "double protection and three routing" configuration requirements is as follows Figure 2 shown.

[0004] Chinese patent document CN107689917A discloses a "power communication network routing allocation method based on non-consistent service balancing." This method uses the average risk of the entire network, the risk balance, and the service route separation constraint to establish a network-wide energy function. Using this function as the target, the KSP algorithm is used to obtain alternative routes, from which the two routes with the lowest network-wide energy values ​​are selected as the main and backup service routes. Chinese patent document CN108809828B discloses a "power communication network routing method for joint load flow and service risk balancing." This method introduces a balancing factor to construct a link cost function that comprehensively considers load and risk, and uses the Dijkstra algorithm to obtain working and backup routes that meet link disjointness. Chinese patent document CN111210361B discloses a "power communication network routing planning method based on reliability prediction and particle swarm optimization." This method uses a recursive neural network to predict the reliability of nodes and links, and further uses a particle swarm optimization algorithm to obtain service routing solutions.

[0005] However, none of the above methods consider the service transmission delay and the "double protection three routes" routing planning requirements of relay protection services. Therefore, a routing planning method for relay protection private networks that meets the "double protection three routes" requirements is urgently needed. Summary of the Invention

[0006] In order to solve the above problems, the present invention proposes a relay protection private network routing planning method based on genetic algorithm.

[0007] According to some embodiments, the present invention adopts the following technical solutions:

[0008] A genetic algorithm-based relay protection network routing planning method includes:

[0009] Step 1: Input the relevant parameters of the actual network topology, switching nodes and optical cable links;

[0010] Step 2: Directly determine the first route and the second route of each relay protection service;

[0011] Step 3: Encode the chromosomes using a priority-based encoding method;

[0012] Step 4: Randomly generate an initial population of size Q as the parent population and set the maximum genetic generation number;

[0013] Step 5: Calculate the fitness F of individuals in the parent population;

[0014] Step 6: Perform a binary tournament selection operation on the parent population to obtain a new population with a population size of Q / 2;

[0015] Step 7: Perform a crossover operation on the chromosomes in the new population to expand the population size to Q;

[0016] Step 8: Perform mutation operations on the chromosomes in the new population according to the mutation probability;

[0017] Step 9: Replace the first individual of the new population with the individual with the smallest fitness F in the parent population, thereby retaining the optimal individual and obtaining a descendant population with a population size of Q;

[0018] Step 10: Determine whether the population generation number in the offspring population has reached the maximum genetic generation number. If not, use the offspring population as the parent population and go to step 6. Otherwise, the iteration ends and the chromosome of the optimal individual in the current offspring population is selected. After decoding, the third route of each relay protection service is obtained.

[0019] According to the preferred embodiment of the present invention, in step 1, in the actual network topology, the two optical cable links between the switching nodes are equivalent to one optical cable link, and an equivalent network topology G = (V, E) is obtained, where V = {v i , i∈Λ} is the set of exchange nodes, Λ={1,2,...,N}, N is the number of nodes, E={e ij |i<j,v i With v j There are equivalent links between them} is the set of equivalent links, K = |E| is the number of equivalent links;

[0020] The parameters related to the switching node and the optical cable link include: switching node v i Data processing and forwarding delay t v (v i ), optical cable link e ij The length l(e ij ), bandwidth capacity f(e ij ) and the number of services carried b(e ij );

[0021] The number of relay protection services is equal to the number of equivalent links. All relay protection services form a service set S = {s k ,k∈Π}, where Π={1,2,...,K}, and the delay requirement and bandwidth requirement of the relay protection service are τ and ω respectively.

[0022] Preferably, according to the present invention, in step 2, there are two direct optical cable links between the source node and the destination node of the relay protection service, and the two direct optical cable links serve as the first route and the second route of the relay protection service respectively.

[0023] Preferably, according to the present invention, in step 3, in the priority-based coding method, one chromosome corresponds to one routing scheme; one chromosome coding segment corresponds to the third route of a relay protection service, the gene position in the chromosome coding segment represents the switching node, the gene value corresponds to the priority size of the switching node, and the chromosome coding segments corresponding to the third routes of all relay protection services constitute a chromosome.

[0024] According to the preferred embodiment of the present invention, in step 5, the steps for calculating the fitness function F of the individual are as follows:

[0025] Step 501: Calculate a single service s k transmission delay;

[0026] Calculate the forwarding processing delay t1(k) of the intermediate switching node of the service route, as shown in formula (I):

[0027]

[0028] Calculate the transmission delay t2(k) of the optical cable link, as shown in formula (II):

[0029]

[0030] In formula (I) and formula (II), is the set of intermediate switching nodes for the service routing, E k is the set of optical cable links for this service routing, c is the speed of light, and r is the refractive index of the optical cable core; t v (v i ) represents node v i Data processing and forwarding delay;

[0031] Computing Services k The transmission delay t(k) is shown in formula (III):

[0032] t(k)=t1(k)+t2(k) (III)

[0033] Step 502: Sum the transmission delays of all services to obtain the total transmission delay T of all services;

[0034] Step 503: Calculate the variance B of the number of services carried by the equivalent link, as shown in formula (IV):

[0035]

[0036] In formula (IV), is the average number of services carried by the equivalent link;

[0037] Step 504: Normalize T and B to obtain and As shown in formula (V) and formula (VI):

[0038]

[0039]

[0040] In formula (V) and formula (VI), T max and T min are the maximum and minimum values ​​of T in different routing planning schemes, B max and B min are the maximum and minimum values ​​of B in different routing planning schemes respectively;

[0041] Step 505: Obtain the fitness function F, as shown in formula (VII):

[0042]

[0043] In formula (VII), α is the equalization factor;

[0044] Step 506: Determine whether each routing solution meets the service delay constraint and link bandwidth constraint using equations (VIII) and (IX);

[0045] t(k)≤τ,k∈Π(VIII)

[0046] b(e ij )@ω≤f(e ij ),e ij ∈E(IX)

[0047] If the routing scheme corresponding to an individual does not satisfy the service delay constraint, i.e., formula (VIII), or the routing scheme corresponding to an individual does not satisfy the link bandwidth constraint, i.e., formula (IX), its fitness F is set to the maximum fitness of the individuals in the population; otherwise, no change is made.

[0048] Preferably, according to the present invention, in step 6, the parent population is divided into two populations, an individual is selected from each of the two populations in turn, and the individual with the smaller fitness F is placed into the new population.

[0049] Preferably, according to the present invention, in step 7, two individuals are randomly selected from the new population, and the chromosome coding segments at the same position in the chromosomes of the two individuals are exchanged to generate two new chromosomes, thereby obtaining two corresponding new individuals.

[0050] Preferably, according to the present invention, in step 8, all individuals in the new population are traversed, and for each individual, a number is randomly generated between [0, 1]. If the number is less than the preset mutation probability, it means that the chromosome of the individual needs to mutate, then a coding segment position is randomly selected, and the gene values ​​of two gene positions in the coding segment are randomly exchanged. Otherwise, no operation is performed.

[0051] According to the preferred embodiment of the present invention, in step 10, the chromosome decoding process is:

[0052] Decode each chromosome encoding segment in turn, starting from the source node of the service. When there are multiple optional links, select the link with the higher priority of the next node until reaching the destination node.

[0053] Further preferably, each node is only allowed to exist once in the path.

[0054] Further preferably, during the decoding process of the chromosome, each node has a blocked node set; initially, the blocked node set corresponding to each node is empty; during the normal decoding process, the blocked node set of the current node includes the nodes that have been passed, thereby ensuring that each node exists at most once in the path; if the current node has no optional links, that is, a dead end occurs, it is necessary to go back to the previous node and add the node to the blocked node set of the previous node; and reselect the next link at the previous node.

[0055] A computer device comprises a memory and a processor, wherein the memory stores a computer program and the processor implements the steps of a genetic algorithm-based relay protection private network routing planning method when executing the computer program.

[0056] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a relay protection private network routing planning method based on a genetic algorithm.

[0057] Compared with the existing method, the present invention has the following beneficial effects:

[0058] The method proposed in the present invention can meet the "double protection three routes" requirements of relay protection service routing planning, and reduce the total transmission delay of all services while meeting the delay constraints of relay protection services.

[0059] The method proposed in the present invention can effectively balance the load of the optical cable link and improve the reliability of relay protection service transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The drawings in the specification, which constitute a part of this application, are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0061] Figure 1 This is a schematic diagram of the architecture of the relay protection network;

[0062] Figure 2 This is a schematic diagram of the dual protection and three routing architecture of the relay protection network;

[0063] Figure 3 1 is a flow chart of a method for relay protection private network routing planning based on a genetic algorithm according to an embodiment of the present invention;

[0064] Figure 4 It is a schematic diagram of the topology of an equivalent network of the NSFNET network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0066] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application.

[0067] Example 1

[0068] A routing planning method for relay protection private network based on genetic algorithm, such as Figure 3 Shown, including:

[0069] Step 1: Input the relevant parameters of the actual network topology, switching nodes and optical cable links;

[0070] Step 2: Directly determine the first route and the second route of each relay protection service;

[0071] Step 3: Encode the chromosomes using a priority-based encoding method;

[0072] Step 4: Randomly generate an initial population of size Q as the parent population and set the maximum genetic generation number;

[0073] Step 5: Calculate the fitness F of individuals in the parent population;

[0074] Step 6: Perform a binary tournament selection operation on the parent population to obtain a new population with a population size of Q / 2;

[0075] Step 7: Perform a crossover operation on the chromosomes in the new population to expand the population size to Q;

[0076] Step 8: Perform mutation operations on the chromosomes in the new population according to the mutation probability;

[0077] Step 9: Replace the first individual of the new population with the individual with the smallest fitness F in the parent population, thereby retaining the optimal individual and obtaining a descendant population with a population size of Q;

[0078] Step 10: Determine whether the population generation number in the offspring population has reached the maximum genetic generation number. If not, use the offspring population as the parent population and go to step 6. Otherwise, the iteration ends and the chromosome of the optimal individual in the current offspring population is selected. After decoding, the third route of each relay protection service is obtained.

[0079] Example 2

[0080] The difference between the genetic algorithm-based relay protection network routing planning method described in Example 1 is that:

[0081] In step 1, in the actual network topology, the two optical cable links between the switching nodes are equivalent to one optical cable link, and the equivalent network topology G = (V, E) is obtained, where V = {v i , i∈Λ} is the set of exchange nodes, Λ={1,2,...,N}, N is the number of nodes, E={e ij |i<j,v i With v j There are equivalent links between them} is the set of equivalent links, K = |E| is the number of equivalent links;

[0082] The parameters related to the switching node and the optical cable link include: switching node v i Data processing and forwarding delay t v (v i ), optical cable link e ij The length l(e ij ), bandwidth capacity f(e ij ) and the number of services carried b(e ij );

[0083] The number of relay protection services is equal to the number of equivalent links. All relay protection services form a service set S = {s k ,k∈Π}, where Π={1,2,...,K}, and the delay requirement and bandwidth requirement of the relay protection service are τ and ω respectively.

[0084] In step 2, there are two direct fiber optic links between the source and destination nodes of the relay protection service. These two direct fiber optic links serve as the primary and secondary routes for the relay protection service, respectively. Based on this, a third route needs to be planned for the relay protection service. This third route should be a circuitous route, meaning it cannot include the fiber optic link between the source and destination nodes.

[0085] In step 3, in the priority-based coding method, one chromosome corresponds to one routing scheme; one chromosome coding segment corresponds to the third route of a relay protection service, the gene position in the chromosome coding segment represents the switching node, the gene value corresponds to the priority size of the switching node, and the chromosome coding segments corresponding to the third routes of all relay protection services constitute a chromosome.

[0086] In step 5, the calculation steps of the individual fitness function F are as follows:

[0087] Step 501: Calculate a single service s k transmission delay;

[0088] Calculate the forwarding processing delay t1(k) of the intermediate switching node of the service route, as shown in formula (I):

[0089]

[0090] Calculate the transmission delay t2(k) of the optical cable link, as shown in formula (II):

[0091]

[0092] In formula (I) and formula (II), is the set of intermediate switching nodes for the service routing, E k is the set of optical cable links for this service routing, c is the speed of light, and r is the refractive index of the optical cable core; t v (v i ) represents node v i Data processing and forwarding delay;

[0093] Computing Services k The transmission delay t(k) is shown in formula (III):

[0094] t(k)=t1(k)+t2(k)(III)

[0095] Step 502: Sum the transmission delays of all services to obtain the total transmission delay T of all services;

[0096] Step 503: Calculate the variance B of the number of services carried by the equivalent link, as shown in formula (IV):

[0097]

[0098] In formula (IV), is the average number of services carried by the equivalent link;

[0099] Step 504: Normalize T and B to obtain and As shown in formula (V) and formula (VI):

[0100]

[0101]

[0102] In formula (V) and formula (VI), T max and T min are the maximum and minimum values ​​of T in different routing planning schemes, B max and B min are the maximum and minimum values ​​of B in different routing planning schemes respectively;

[0103] Step 505: Obtain the fitness function F, as shown in formula (VII):

[0104]

[0105] In formula (VII), α is the equalization factor;

[0106] Step 506: Determine whether each routing solution meets the service delay constraint and link bandwidth constraint using equations (VIII) and (IX);

[0107] t(k)≤τ,k∈Π(VIII)

[0108] b(e ij )·ω≤f(e ij ),e ij ∈E(IX)

[0109] If the routing scheme corresponding to an individual does not satisfy the service delay constraint, i.e., formula (VIII), or the routing scheme corresponding to an individual does not satisfy the link bandwidth constraint, i.e., formula (IX), its fitness F is set to the maximum fitness of the individuals in the population; otherwise, no change is made.

[0110] The smaller the fitness function F of an individual in the population, the better the adaptability of the individual, and the better the routing solution corresponding to the individual.

[0111] In step 6, the parent population is divided into two populations, and an individual is selected from each population in turn, and the individual with the smaller fitness F is placed in the new population.

[0112] In step 7, two individuals are randomly selected from the new population, and the chromosome coding segments at the same position in the chromosomes of the two individuals are exchanged to generate two new chromosomes, thereby obtaining two corresponding new individuals.

[0113] In step 8, all individuals in the new population are traversed. For each individual, a number is randomly generated between [0, 1]. If the number is less than the preset mutation probability, it means that the chromosome of the individual needs to mutate. Then, a coding segment position is randomly selected, and the gene values ​​of two gene positions in the coding segment are randomly exchanged. Otherwise, no operation is performed.

[0114] In step 10, the chromosome decoding process is:

[0115] Decode each chromosome encoding segment in turn, starting from the source node of the service. When there are multiple optional links, select the link with the higher priority of the next node until reaching the destination node.

[0116] To avoid loops in routing, each node is allowed to exist only once in a path.

[0117] Due to the particularity of the priority encoding method, dead ends may occur during the path solving process. To this end, during the chromosome decoding process, each node has a blocked node set; initially, the corresponding blocked node set for each node is empty. During normal decoding, the blocked node set of the current node includes the nodes that have already been passed, ensuring that each node exists at most once in the path. If the current node has no optional links, it is a dead end, and it is necessary to go back to the previous node and add that node to the previous node's blocked node set. The next link is reselected at the previous node.

[0118] This embodiment selects the topology of the NSFNET network as the topology of the equivalent network. The topology of the network is as follows: Figure 4 As shown, the network includes 14 switching nodes and 21 equivalent links. Therefore, the number of relay protection services is also 21. Assume that the processing and forwarding delay of each switching node is fixed at 0.022 ms, the length of each equivalent link is randomly selected from 30 to 130 km, the bandwidth utilization is 0.6, and the refractive index of the fiber core is 1.48. Two scenarios are considered based on the link bandwidth capacity. The bandwidth capacity of each link is randomly selected from 20 to 70 Mbits / s. The maximum transmission delay of the relay protection service is 12 ms, and the bandwidth requirement is 2 Mbits / s.

[0119] The balancing factor in the method of the present invention is set to 0.8, and is recorded as Scheme A. Currently, in relay protection private networks, the path with the shortest total length is usually selected as the third route for relay protection services. The main purpose of this method is to reduce the transmission delay of the service. In practice, the transmission delay of the route is also related to the processing and forwarding delay of the switching node. Therefore, according to the definition of route transmission delay, the Dijkstra algorithm is used to select the path with the smallest transmission delay as the third route for the service, and this method is recorded as Scheme B. Since Scheme B only considers the service transmission delay, for comparison, the balancing factor in the method of the present invention is set to 1, and is recorded as Scheme C.

[0120] Table 1

[0121] plan Total transmission delay of all services Variance of the number of services carried by the link Plan A 1.4386 0.3311 Plan B 1.3044 3.0385 Plan C 1.2810 2.8707

[0122] According to Table 1, the total transmission delay of all services in Plan A is the largest, Plan C is the smallest, and Plan B is in the middle. However, the variance of the number of link service carriers in Plan A is the smallest, Plan B is the largest, and Plan C is in the middle. The effect of Plan C is better than that of Plan B. This is because Plan A not only considers the transmission delay of the service, but also considers the variance of the number of link service carriers. Therefore, its total transmission delay is the largest, but the variance of the number of link service carriers is the smallest. Although Plan B and Plan C only consider the total service transmission delay, Plan B plans the routes for the services in sequence, and the route planning of the subsequent services will be affected by the previous services, resulting in an increase in the total transmission delay. Plan C does not consider the order of the services and can obtain a routing solution with a smaller total transmission delay. Therefore, the method proposed in the present invention can reduce the total transmission delay of all services while meeting the requirements of service transmission delay, effectively balance the link load, and improve the reliability of relay protection service transmission.

[0123] Example 3

[0124] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the genetic algorithm-based relay protection private network routing planning method of embodiment 1 or 2 are implemented.

[0125] Example 4

[0126] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the genetic algorithm-based relay protection private network routing planning method of embodiment 1 or 2.

Claims

1. A method for relay protection private network routing planning based on genetic algorithm, characterized in that: include: Step 1: Input the relevant parameters of the actual network topology, switching nodes and optical cable links; In step 1, in the actual network topology, the two optical cable links between the switching nodes are equivalent to one optical cable link, and the equivalent network topology G = (V, E) is obtained, where V = {v i , i∈Λ} is the set of exchange nodes, Λ={1,2,...,N}, N is the number of nodes, E={e ij |i <j,v i With v j There are equivalent links between them} is the set of equivalent links, K = |E| is the number of equivalent links; The parameters related to the switching node and the optical cable link include: switching node v i Data processing and forwarding delay t v (v i ), optical cable link e ij The length l(e ij ), bandwidth capacity f(e ij ) and the number of services carried b(e ij ); The number of relay protection services is equal to the number of equivalent links. All relay protection services form a service set S = {s k ,k∈Π}, where Π={1,2,...,K}, the delay requirement and bandwidth requirement of relay protection service are τ and ω respectively; Step 2: Directly determine the first route and the second route of each relay protection service; Step 3: Encode the chromosomes using a priority-based encoding method; Step 4: Randomly generate an initial population of size Q as the parent population and set the maximum genetic generation number; Step 5: Calculate the fitness F of individuals in the parent population; Step 6: Perform a binary tournament selection operation on the parent population to obtain a new population with a population size of Q / 2; Step 7: Perform a crossover operation on the chromosomes in the new population to expand the population size to Q; Step 8: Perform mutation operations on the chromosomes in the new population according to the mutation probability; Step 9: Replace the first individual of the new population with the individual with the smallest fitness F in the parent population, thereby retaining the optimal individual and obtaining a descendant population with a population size of Q; Step 10: Determine whether the population generation number in the offspring population has reached the maximum genetic generation number. If not, use the offspring population as the parent population and go to step 6. Otherwise, the iteration ends and the chromosome of the optimal individual in the current offspring population is selected. After decoding, the third route of each relay protection service is obtained. In step 5, the calculation steps of the individual fitness function F are as follows: Step 501: Calculate a single service s k transmission delay; Calculate the forwarding processing delay t1(k) of the intermediate switching node of the service route, as shown in formula (I): Calculate the transmission delay t2(k) of the optical cable link, as shown in formula (II): In formula (I) and formula (II), is the set of intermediate switching nodes for the service routing, E k is the set of optical cable links for this service routing, c is the speed of light, and r is the refractive index of the optical cable core; Computing Services k The transmission delay t(k) is shown in formula (III): t(k)=t1(k)+t2(k)(III) Step 502: Sum the transmission delays of all services to obtain the total transmission delay T of all services; Step 503: Calculate the variance B of the number of services carried by the equivalent link, as shown in formula (IV): In formula (IV), is the average number of services carried by the equivalent link; Step 504: Normalize T and B to obtain and As shown in formula (V) and formula (VI): In formula (V) and formula (VI), T max and T min are the maximum and minimum values ​​of T in different routing planning schemes, B max and B min are the maximum and minimum values ​​of B in different routing planning schemes respectively; Step 505: Obtain the fitness function F, as shown in formula (VII): In formula (VII), α is the equalization factor; Step 506: Determine whether each routing solution meets the service delay constraint and link bandwidth constraint using equations (VIII) and (IX); t(k)≤τ,k∈Π(VIII) b (ie ij )·ω≤f(e ij ),have been ij ∈E(IX) Where ω refers to the bandwidth requirement; If the routing scheme corresponding to an individual does not satisfy the service delay constraint, i.e., formula (VIII), or the routing scheme corresponding to an individual does not satisfy the link bandwidth constraint, i.e., formula (IX), its fitness F is set to the maximum fitness of the individuals in the population; otherwise, no change is made.

2. The method for relay protection private network routing planning based on genetic algorithm according to claim 1, characterized in that: In step 2, there are two direct optical cable links between the source node and the destination node of the relay protection service. The two direct optical cable links serve as the first route and the second route of the relay protection service respectively.

3. The method for relay protection private network routing planning based on genetic algorithm according to claim 1, characterized in that: In step 3, in the priority-based coding method, one chromosome corresponds to one routing scheme; one chromosome coding segment corresponds to the third route of a relay protection service, the gene position in the chromosome coding segment represents the switching node, the gene value corresponds to the priority size of the switching node, and the chromosome coding segments corresponding to the third routes of all relay protection services constitute a chromosome.

4. The method for relay protection private network routing planning based on genetic algorithm according to claim 1, characterized in that: In step 6, the parent population is divided into two populations, and an individual is selected from each population in turn, and the individual with the smaller fitness F is placed in the new population.

5. The method for relay protection private network routing planning based on genetic algorithm according to claim 1, characterized in that: In step 7, two individuals are randomly selected from the new population, and the chromosome coding segments at the same position in the chromosomes of the two individuals are exchanged to generate two new chromosomes, thereby obtaining two new individuals. In step 8, all individuals in the new population are traversed. For each individual, a number is randomly generated between [0, 1]. If the number is less than the preset mutation probability, it means that the chromosome of the individual needs to mutate. Then, a coding segment position is randomly selected, and the gene values ​​of two gene positions in the coding segment are randomly exchanged. Otherwise, no operation is performed.

6. A method for relay protection private network routing planning based on genetic algorithm according to any one of claims 1 to 5, characterized in that: In step 10, the chromosome decoding process is: Decode each chromosome code segment in turn, starting from the source node of the service. When there are multiple optional links, select the link with the higher priority of the next node until reaching the destination node; Each node is only allowed to exist once in the path; During the decoding process of the chromosome, each node has a blocked node set. Initially, the blocked node set corresponding to each node is empty. During the normal decoding process, the blocked node set of the current node includes the nodes that have been passed, thereby ensuring that each node exists at most once in the path. If the current node has no optional links, that is, a dead end occurs, it is necessary to go back to the previous node and add the node to the blocked node set of the previous node. The next link is reselected at the previous node.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the genetic algorithm-based relay protection private network routing planning method described in any one of claims 1-6 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the genetic algorithm-based relay protection private network routing planning method according to any one of claims 1 to 6 are implemented.

Images