CN112990608A - 5G optimization construction method suitable for full coverage of electric power facilities - Google Patents
5G optimization construction method suitable for full coverage of electric power facilities Download PDFInfo
- Publication number
- CN112990608A CN112990608A CN202110449983.7A CN202110449983A CN112990608A CN 112990608 A CN112990608 A CN 112990608A CN 202110449983 A CN202110449983 A CN 202110449983A CN 112990608 A CN112990608 A CN 112990608A
- Authority
- CN
- China
- Prior art keywords
- population
- fitness
- initial
- network
- electric power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 23
- 238000005457 optimization Methods 0.000 title claims abstract description 18
- 210000000349 chromosome Anatomy 0.000 claims abstract description 62
- 230000005540 biological transmission Effects 0.000 claims abstract description 24
- 230000002068 genetic effect Effects 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 238000010353 genetic engineering Methods 0.000 claims abstract description 4
- 108090000623 proteins and genes Proteins 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 26
- 230000035772 mutation Effects 0.000 claims description 18
- 238000010606 normalization Methods 0.000 claims description 9
- 238000009401 outcrossing Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008929 regeneration Effects 0.000 description 2
- 238000011069 regeneration method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
Abstract
The application belongs to the technical field of 5G network slicing. The application provides a 5G optimization construction method suitable for electric power facility full coverage, which comprises the following steps of S1: arranging and generating an initial network slice by utilizing an edge calculation strategy, and normalizing transmission parameters of the initial network slice; s2: encoding the normalized network slice by using a binary chromosome encoding strategy to generate an initial chromosome population; s3: calculating fitness by using a genetic algorithm on the initial chromosome population; s4: setting an iteration condition, and if the iteration condition is met, outputting an iteration result to obtain an optimal network slice; otherwise, performing genetic manipulation on the initial chromosome population to generate a new chromosome population, and performing step S3 on the new chromosome population. The invention greatly simplifies the complexity of 5G optimization, improves the overall performance of the network, ensures that the optimized 5G network has higher real-time performance, and can meet the requirement of using a large-scale network in electric power facilities.
Description
Technical Field
The application relates to the technical field of 5G network slicing, in particular to a 5G optimization construction method suitable for full coverage of electric power facilities.
Background
The network slice is used as a key technology of a 5G enabling vertical industry, a virtual private network technology is utilized, end-to-end flexible customized 5G service with large bandwidth, low time delay and high reliability is provided for different industries such as smart homes, intelligent factories, Internet of vehicles, public safety and the like through a slice platform, and quick online business and more extreme user experience of the vertical industry are realized.
Although 5G is difficult to replace optical fiber in the short term, 5G also has its unique advantages: in the case of very complicated landform, such as erecting power equipment in mountainous areas where rivers are intersected constantly, the difficulty and cost of optical fiber access are much higher than 5G, and at the moment, 5G provides possibility for laying power equipment in severe environment.
In the prior art, the optimization network of the network is mostly carried out through edge calculation and network slicing, the 5G network slicing technology is applied to various links of power generation, power transmission, power transformation, power distribution and power utilization of a power system and emergency communication in different degrees, and the existing 5G slicing optimization technology is complex and difficult to meet the real-time requirement.
Disclosure of Invention
In view of this, the present application provides a 5G optimization construction method suitable for power facility full coverage, which can solve the problem of poor real-time performance in a network optimization process.
The specific technical scheme of the application is as follows:
A5G optimization construction method suitable for full coverage of electric power facilities comprises the following steps:
s1: arranging and generating an initial network slice by utilizing an edge calculation strategy, and normalizing transmission parameters of the initial network slice;
s2: encoding the normalized network slice by using a binary chromosome encoding strategy to generate an initial chromosome population;
s3: calculating fitness by using a genetic algorithm on the initial chromosome population;
s4: setting an iteration condition, and if the iteration condition is met, outputting an iteration result to obtain an optimal network slice; otherwise, performing genetic manipulation on the initial chromosome population to generate a new chromosome population, and performing step S3 on the new chromosome population.
Further, in step S1, the generating an initial network slice by using edge computation policy orchestration further includes:
acquiring the service types and available network resources of various request services of the access network, and generating an edge calculation strategy according to the scene requirements and the network state of the access network.
Further, in step S1, the normalizing the transmission parameters of the initial network slice specifically includes:
normalizing the transmission parameters of the initial network slice by using a normalization formula, wherein the transmission parameters comprise time delay and bandwidth;
the normalization formula is specifically as follows:
wherein n is a normalization result, c is the transmission parameter, m is a mean value of the transmission parameter, and α is a variance of the transmission parameter.
Further, in step S3, the calculating the fitness specifically includes:
designing a fitness function, and calculating the fitness according to the fitness function;
the Fitness function Fitness specifically includes:
Fitness＝ρeT-ωeW
wherein e is an index, T is a normalized network traffic delay value, W is a normalized traffic bandwidth, ρ is a proportion occupied by the high bandwidth class slice, and ω is a proportion occupied by the low delay class slice.
Further, in step S3, the calculating a fitness by using a genetic algorithm for the initial chromosome population and setting an iteration condition specifically includes:
calculating the fitness of the network slices in the initial chromosome population, and taking the network slices with the highest fitness as a local optimal population and a global optimal population;
performing iterative operation by using a genetic algorithm to update the local optimal population;
the iteration condition comprises a preset iteration number.
Further, the step S4 specifically includes:
when the number of iterative operations reaches the preset number of iterations, if the fitness of the local optimal population is greater than that of the global optimal population, outputting the local optimal population serving as an optimal network slice to meet the iteration condition;
when the number of iterative operations reaches the preset number of iterations, if the fitness of the local optimal population is smaller than the fitness of the global optimal population, performing genetic operation on the initial chromosome population to generate a new chromosome population, and performing step S3 on the new chromosome population.
Further, the genetic manipulation specifically comprises:
selecting: selecting individuals in the initial chromosome to construct a gene library, and carrying out selection operation on the gene library by using a roulette method to obtain a next generation population;
and (3) crossing: selecting different crossing modes for the next generation population by using a random algorithm to carry out crossing operation to obtain a new next generation population;
mutation: and carrying out mutation operation on the new next generation population by using a basic potential mutation mode to generate a new chromosome population.
Further, the selecting specifically includes:
constructing a gene library based on the individual fitness in the initial chromosome;
putting the individual with the highest fitness into the gene bank, putting the parent individual with the fitness change value larger than 10 into the gene bank, putting the farthest individual away from the individual with the highest fitness into the gene bank, and putting the nearest individual away from the individual with the highest fitness into the gene bank;
selecting individuals from the gene bank, gene bank by the betting board method;
and putting the selection result and the gene library into a next generation group.
Further, the different crossing modes include:
single point crossing, two point crossing, multiple point crossing and even crossing.
In summary, the application provides a 5G optimization construction method suitable for full coverage of electric power facilities. In the method, the network slice is generated by adopting the edge calculation strategy, and the genetic algorithm is adopted for optimizing the network slice, so that the complexity of 5G optimization is greatly simplified, the overall performance of the network is improved, the optimized 5G network has higher real-time performance, and the requirement of using a large-scale network in an electric power facility can be met.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a 5G optimization construction method suitable for full coverage of an electric power facility according to a first embodiment of the present application;
fig. 2 is a schematic genetic operation flow diagram of a 5G optimization construction method suitable for full coverage of an electric power facility according to a second embodiment of the present application.
Detailed Description
In order to make the objects, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, an embodiment of the present application provides a schematic flow chart of a 5G optimization construction method suitable for full coverage of an electric power facility, including the following steps:
s110: and arranging and generating an initial network slice by utilizing an edge calculation strategy, and normalizing the transmission parameters of the initial network slice.
It should be noted that, in the access network slice architecture based on edge computation, it is necessary to obtain the service types of various request services of the access network and available network resources, and generate an edge computation policy according to the scene requirements and the network state of the access network.
Because different parameters of the network slice have different value ranges and units, quantitative comparison and analysis cannot be performed, the embodiment normalizes the transmission parameters of the network slice by using a zero-mean normalization method, and the transmission parameters are specifically selected as time delay and bandwidth, and the normalization formula is as follows:
wherein n is the normalization result, c is the transmission parameter, m is the mean value of the transmission parameter, and α is the variance of the transmission parameter.
S120: and coding the normalized network slices by using a binary chromosome coding strategy to generate an initial chromosome population.
It should be noted that the encoding using the binary chromosome encoding strategy is to convert decimal variables into binary, and simulate chromosomes with numbers 0 and 1, thereby generating chromosome populations.
S130: and calculating the fitness of the initial chromosome population by using a genetic algorithm, and setting iteration conditions.
It should be noted that, when the Fitness is calculated by using the genetic algorithm for the initial chromosome population, a Fitness function needs to be designed, and according to the selection of the transmission parameters for the network slice, the designed Fitness function Fitness is as follows:
Fitness＝ρeT-ωeW
wherein e is an index, T is a normalized network traffic delay value, W is a normalized traffic bandwidth, ρ is a proportion occupied by the high bandwidth class slice, and ω is a proportion occupied by the low delay class slice.
In addition, when the fitness of the initial chromosome population is calculated by using a genetic algorithm, the network slice with the highest fitness is used as a local optimal population and a global optimal population; and (4) carrying out iterative operation by using a genetic algorithm, and continuously updating the local optimal population.
S140: setting an iteration condition, and if the iteration condition is met, outputting an iteration result to obtain an optimal network slice; otherwise, the initial chromosome population is genetically manipulated to generate a new chromosome population, and step S130 is performed on the new chromosome population.
It should be noted that the set iteration condition includes setting a preset number of iterations. And setting the iteration condition as that when the number of times of the iteration operation reaches the preset iteration number, the fitness of the local optimal population is greater than the fitness of the global optimal population.
I.e. when the number of iteration operations reaches a preset number of iterations,
if the fitness of the local optimal population is greater than that of the global optimal population, outputting the local optimal population serving as an optimal network slice to meet the iteration condition;
if the fitness of the local optimum population is smaller than the fitness of the global optimum population, performing genetic operation on the initial chromosome population to generate a new chromosome population, and performing step S3 on the new chromosome population.
The above is a detailed description of an embodiment of a 5G optimal construction method suitable for full coverage of an electric power facility, and the following is a detailed description of another embodiment of a 5G optimal construction method suitable for full coverage of an electric power facility.
S210: and arranging and generating an initial network slice by utilizing an edge calculation strategy, and normalizing the transmission parameters of the initial network slice.
It should be noted that the processing manner in this step is the same as that in step S110 in the previous embodiment, and therefore, the description is omitted.
S220: and coding the normalized network slices by using a binary chromosome coding strategy to generate an initial chromosome population.
It should be noted that the processing manner in this step is the same as that in step S120 in the previous embodiment, and therefore, the description is omitted.
S230: fitness is calculated for the initial chromosome population using a genetic algorithm.
It should be noted that the processing manner in this step is the same as that in step S130 in the previous embodiment, and therefore, the description is omitted.
S240: setting an iteration condition, and if the iteration condition is met, outputting an iteration result to obtain an optimal network slice; otherwise, the initial chromosome population is genetically manipulated to generate a new chromosome population, and step S230 is performed on the new chromosome population.
It should be noted that when the iteration condition is satisfied, the processing manner in this step is the same as that in step S140 in the previous embodiment. When the iteration condition is not satisfied, the method further comprises the following steps:
s241: selecting, namely selecting individuals in the initial chromosome to construct a gene library, and performing selection operation on the gene library by using a roulette method to obtain a next generation population;
it should be noted that the operation of selecting the superior individuals from the population and eliminating the inferior individuals is called selection, and the selection operator is sometimes called regeneration operator (regeneration operator), and the purpose of selection is to directly inherit the optimized individuals to the next generation or generate new individuals by pairing and crossing and then inherit the new individuals to the next generation.
In this embodiment, a gene library is constructed, and a selection operation is performed by a betting board method, which includes the following specific steps:
constructing a gene library G (a great face) based on individual fitness in an initial chromosomeG1，G2，G3，G4}；
Putting the individual with the highest fitness into a gene bank G1Putting the parent individuals with the fitness variation value larger than 10 into a gene bank G2Placing the farthest individual from the individual with the highest fitness into the gene bank G3Putting the nearest individual with the highest distance fitness into the gene bank G4；
The gene bank G2Gene bank G3Gene bank G4Selecting individuals by a roulette method;
the selection results and the gene bank G1Put into the next generation population.
It should be noted that the roulette method is also called a proportional selection method, and the basic idea is that the probability of each individual being selected is proportional to the fitness thereof, and the specific operation is as follows:
1) calculating the fitness f (i is 1, 2.. multidot.M) of each individual in the population, wherein M is the size of the population;
2) the probability of each individual being inherited into the next generation population is calculated:
wherein, x is chromosome individual, i is next generation chromosome number, j is previous generation chromosome number, and N is chromosome total number;
3) calculating the cumulative probability q of each individual;
4) generating a uniformly distributed pseudo-random number r in the interval of [0, 1 ];
5) if r < q [1], then individual 1 is selected, otherwise, individual k is selected such that: q [ k-1] < r < q [ k ];
6) repeating steps 4 and 5M times.
S242: crossing, namely, the next generation population selects different crossing modes by using a random algorithm to carry out crossing operation to obtain a new next generation population;
it should be noted that, the crossover refers to an operation of replacing and recombining partial structures of two parent individuals to generate a new individual, and through crossover, the search capability of the genetic algorithm is dramatically improved, and the crossover includes single-point crossover, two-point crossover, multi-point crossover and uniform crossover;
one-point crossbar (One-point crossbar): only one cross point is randomly arranged in an individual code string, and then the cross points exchange partial chromosomes of two paired individuals;
two-point Crossover (Two-point Crossover): randomly setting two cross points in the individual code string, and then carrying out partial gene exchange;
multipoint intersection (Multi-point crossbar): the intersection points are multiple points;
uniform Crossover (also known as Uniform Crossover, Uniform cross): genes at each locus of two paired individuals are exchanged with the same crossover probability, thereby forming two new individuals;
preferably, in order to avoid the singularity of the population caused by the single intersection method, the embodiment utilizes a random algorithm to select one of the single-point intersection, the two-point intersection, the multi-point intersection and the uniform intersection with equal probability for the intersection.
S243: and (4) mutation, namely performing mutation operation on the new next generation population by using a basic potential mutation mode to generate a new chromosome population.
It should be noted that, a change in the gene value at a certain locus in a cluster of individuals in a population is called a mutation; when the genetic algorithm is close to the optimal solution neighborhood through the crossover operator, the convergence to the optimal solution can be accelerated by utilizing the local random search capability of the mutation operator, and meanwhile, the genetic algorithm can maintain the group diversity through mutation so as to prevent the immature convergence phenomenon.
Performing Mutation operation by a basic bit Mutation method, wherein the basic bit Mutation (Simple Mutation) is: and (3) carrying out mutation operation on one or more randomly specified bits in the individual code strings according to the mutation probability only by the value on the seat.
Through the operation of the genetic iterative evolution, a new generation of chromosome population can be obtained, then fitness calculation is carried out on the obtained new generation of chromosome population until the iteration times are reached, the iteration is terminated, and the optimal solution of the network slice is output.
The above is a detailed description of an embodiment of a 5G optimal construction method suitable for full coverage of an electric power facility, and the following is a detailed description of another embodiment of a 5G optimal construction method suitable for full coverage of an electric power facility.
In order to verify and explain the technical effect adopted in the method, the embodiment selects the traditional OSPF algorithm and the greedy strategy and adopts the method to perform comparison test, and compares the test results by means of scientific demonstration to verify the real effect of the method.
The traditional OSPF algorithm cannot be used for a large-scale network, and the greedy strategy cannot optimize the energy consumption of the network as a whole. The stability is poor.
In the embodiment, the time for generating the network route is compared by adopting the traditional OSPF algorithm and the greedy strategy and the method under different network scales, the route strategy of each method is deployed in an experimental network, and the resource utilization rate of the whole network under different loads is measured according to the difference of source node access service flow, so that the stability and the efficiency of the method are verified.
And (3) testing environment: setting active (O) nodes O1, O2, … and On in a network environment, wherein the active (O) nodes are nodes for receiving user traffic and are responsible for receiving the user traffic; also destination (D) nodes, D1, D2, …, Dn; and a switch running an Open Flow protocol.
The OSPF algorithm is a data link state routing protocol, and adopts a minimum spanning tree algorithm, namely, a traditional network does not use a network slice, and the network slice is forwarded according to the shortest path without considering load balance; the greedy strategy performs QoS requirement (slice) ordering and then performs routing for each slice in the case of using network slices.
In the following experimental analysis process, firstly, the flow demand, namely the total slice amount is kept unchanged, and the time for generating the routing strategy and the energy consumption after the routing is deployed by the 3 methods are compared by increasing the nodes of the network (network scale change); then, the same network scale is used to be unchanged, and the traditional OSPF algorithm and the greedy strategy and the performance of the method in the aspect of resource utilization rate are analyzed according to various continuously changing traffic demands.
The time used by the method is increased slowly with the increase of the network scale, the time consumed by the method is good in stability, and obviously superior to the time-consuming stability based on the greedy strategy, and the traditional OSPF algorithm is low in relative time complexity but unstable in network performance; the method keeps the average utilization rate of the link at about 80 percent, and the average utilization rate of the link is not fluctuated greatly along with the increase of the load, thereby showing that the method has better load balancing effect and stability and is obviously superior to the traditional OSPF algorithm and greedy strategy.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (9)
1. A5G optimization construction method suitable for full coverage of electric power facilities is characterized by comprising the following steps:
s1: arranging and generating an initial network slice by utilizing an edge calculation strategy, and normalizing transmission parameters of the initial network slice;
s2: encoding the normalized network slice by using a binary chromosome encoding strategy to generate an initial chromosome population;
s3: calculating fitness by using a genetic algorithm on the initial chromosome population;
s4: setting an iteration condition, and if the fitness meets the iteration condition, outputting an iteration result to obtain an optimal network slice; otherwise, performing genetic manipulation on the initial chromosome population to generate a new chromosome population, and performing step S3 on the new chromosome population.
2. The 5G optimized construction method suitable for electric power facility full coverage according to claim 1, wherein in the step S1, the generating an initial network slice by using the edge calculation strategy layout further comprises:
acquiring the service types and available network resources of various request services of the access network, and generating an edge calculation strategy according to the scene requirements and the network state of the access network.
3. The 5G optimal construction method suitable for electric power facility full coverage according to claim 1, wherein in the step S1, the normalizing the transmission parameters of the initial network slice specifically includes:
normalizing the transmission parameters of the initial network slice by using a normalization formula, wherein the transmission parameters comprise time delay and bandwidth;
the normalization formula is specifically as follows:
wherein n is a normalization result, c is the transmission parameter, m is a mean value of the transmission parameter, and α is a variance of the transmission parameter.
4. The 5G optimal construction method suitable for electric power facility full coverage according to claim 1, wherein in the step S3, the calculating the fitness specifically comprises:
designing a fitness function, and calculating the fitness according to the fitness function;
the Fitness function Fitness specifically includes:
Fitness＝ρeT-ωeW
wherein e is an index, T is a normalized network traffic delay value, W is a normalized traffic bandwidth, ρ is a proportion occupied by the high bandwidth class slice, and ω is a proportion occupied by the low delay class slice.
5. The 5G optimized construction method suitable for electric power facility full coverage according to claim 1 or 4, wherein in the step S3, the calculating fitness by using a genetic algorithm on the initial chromosome population and setting iteration conditions specifically comprises:
calculating the fitness of the network slices in the initial chromosome population, and taking the network slices with the highest fitness as a local optimal population and a global optimal population;
and carrying out iterative operation by using a genetic algorithm to update the local optimal population.
6. The 5G optimal construction method suitable for the full coverage of the electric power facility according to claim 5, wherein the step S4 specifically comprises:
the iteration condition comprises a preset iteration number;
when the number of iterative operations reaches the preset number of iterations, if the fitness of the local optimal population is greater than that of the global optimal population, outputting the local optimal population serving as an optimal network slice to meet the iteration condition;
when the number of iterative operations reaches the preset number of iterations, if the fitness of the local optimal population is smaller than the fitness of the global optimal population, performing genetic operation on the initial chromosome population to generate a new chromosome population, and performing step S3 on the new chromosome population.
7. The 5G optimized construction method suitable for electric power facility full coverage according to claim 1, wherein in the step S4, the genetic operation specifically comprises:
selecting: selecting individuals in the initial chromosome to construct a gene library, and carrying out selection operation on the gene library by using a roulette method to obtain a next generation population;
and (3) crossing: selecting different crossing modes for the next generation population by using a random algorithm to carry out crossing operation to obtain a new next generation population;
mutation: and carrying out mutation operation on the new next generation population by using a basic potential mutation mode to generate a new chromosome population.
8. The 5G optimization construction method suitable for the full coverage of the electric power facility according to claim 7, wherein the selecting specifically comprises:
constructing a gene bank G ═ { G ] based on individual fitness in the initial chromosome1，G2，G3，G4}；
Putting the individual with the highest fitness into the gene bank G1Putting the parent individuals with the fitness variation value larger than 10 into the gene bank G2Placing the farthest individual from the individual with the highest fitness into the gene bank G3Placing the closest individual to the individual with the highest fitness into the gene bank G4；
The gene bank G2Gene bank G3Gene bank G4Selecting individuals by the roulette method;
the selection result and the gene bank G1Put into the next generation group GN。
9. The 5G optimization construction method suitable for the full coverage of the electric power facility according to claim 7, wherein the different crossing modes comprise:
single point crossing, two point crossing, multiple point crossing and even crossing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110449983.7A CN112990608A (en) | 2021-04-25 | 2021-04-25 | 5G optimization construction method suitable for full coverage of electric power facilities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110449983.7A CN112990608A (en) | 2021-04-25 | 2021-04-25 | 5G optimization construction method suitable for full coverage of electric power facilities |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112990608A true CN112990608A (en) | 2021-06-18 |
Family
ID=76340135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110449983.7A Pending CN112990608A (en) | 2021-04-25 | 2021-04-25 | 5G optimization construction method suitable for full coverage of electric power facilities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990608A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114071513A (en) * | 2021-10-18 | 2022-02-18 | 国网江苏省电力有限公司南京供电分公司 | Section arranging method and device based on improved locust optimization method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108108815A (en) * | 2017-12-13 | 2018-06-01 | 北京邮电大学 | Mapping method of virtual network and device based on improved adaptive GA-IAGA |
| CN108174394A (en) * | 2018-01-12 | 2018-06-15 | 西安邮电大学 | A kind of Arrangement algorithm of 5G networks slice |
| CN108846472A (en) * | 2018-06-05 | 2018-11-20 | 北京航空航天大学 | A kind of optimization method of Adaptive Genetic Particle Swarm Mixed Algorithm |
| US20180359337A1 (en) * | 2017-06-09 | 2018-12-13 | At&T Intellectual Property I, L.P. | Next generation mobility core network controller for service delivery |
| CN109219020A (en) * | 2018-09-14 | 2019-01-15 | 云迅智能科技南京有限公司 | A kind of network dicing method and system |
| US20200052991A1 (en) * | 2018-08-09 | 2020-02-13 | At&T Intellectual Property I, L.P. | Mobility network slice selection |
-
2021
- 2021-04-25 CN CN202110449983.7A patent/CN112990608A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180359337A1 (en) * | 2017-06-09 | 2018-12-13 | At&T Intellectual Property I, L.P. | Next generation mobility core network controller for service delivery |
| CN108108815A (en) * | 2017-12-13 | 2018-06-01 | 北京邮电大学 | Mapping method of virtual network and device based on improved adaptive GA-IAGA |
| CN108174394A (en) * | 2018-01-12 | 2018-06-15 | 西安邮电大学 | A kind of Arrangement algorithm of 5G networks slice |
| CN108846472A (en) * | 2018-06-05 | 2018-11-20 | 北京航空航天大学 | A kind of optimization method of Adaptive Genetic Particle Swarm Mixed Algorithm |
| US20200052991A1 (en) * | 2018-08-09 | 2020-02-13 | At&T Intellectual Property I, L.P. | Mobility network slice selection |
| CN109219020A (en) * | 2018-09-14 | 2019-01-15 | 云迅智能科技南京有限公司 | A kind of network dicing method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114071513A (en) * | 2021-10-18 | 2022-02-18 | 国网江苏省电力有限公司南京供电分公司 | Section arranging method and device based on improved locust optimization method |
| CN114071513B (en) * | 2021-10-18 | 2023-09-15 | 国网江苏省电力有限公司南京供电分公司 | Slice arrangement method and device based on improved locust optimization method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106656598B (en) | Power communication gateway key service alternative route configuration method and system | |
| Altiparmak et al. | Optimal design of reliable computer networks: A comparison of metaheuristics | |
| CN108880886B (en) | Method for planning protection communication network of cross-regional power system | |
| Haghighat et al. | GA-based heuristic algorithms for bandwidth-delay-constrained least-cost multicast routing | |
| CN108874525A (en) | A kind of service request distribution method towards edge calculations environment | |
| CN113794494B (en) | Edge computing system and computing unloading optimization method for low-orbit satellite network | |
| Kumar et al. | Topological design of communication networks using multiobjective genetic optimization | |
| CN105323166A (en) | Cloud computing-oriented routing method based on network efficiency priority | |
| CN115242295B (en) | Satellite network SDN multi-controller deployment method and system | |
| CN108494678A (en) | Alternate routing configuration method based on genetic algorithm and system | |
| CN113472671B (en) | Method, device and computer readable storage medium for determining multicast route | |
| Oda et al. | Effect of different grid shapes in wireless mesh network-genetic algorithm system | |
| CN111885493A (en) | Micro-cloud deployment method based on improved cuckoo search algorithm | |
| CN112990608A (en) | 5G optimization construction method suitable for full coverage of electric power facilities | |
| Li et al. | Network topology optimization via deep reinforcement learning | |
| CN111404727A (en) | Route analysis method based on standby route potential risk assessment model | |
| CN112486651A (en) | Cloud test platform task scheduling method based on improved genetic algorithm | |
| CN109889573B (en) | NGSA multi-target-based copy placement method in hybrid cloud | |
| CN113285832B (en) | NSGA-II-based power multi-mode network resource optimization allocation method | |
| Ikhelef et al. | A knapsack-based optimization algorithm for VNF placement and chaining problem | |
| Shakya et al. | Investigating binary EAs for Passive In-Building Distributed Antenna Systems | |
| Premkumar et al. | Telecommunications network design—Comparison of alternative approaches | |
| Pan et al. | A genetic algorithm for the overlay multicast routing problem | |
| Wang et al. | Alternate routing optimization method for power communication network | |
| Guan et al. | Multidimensional Resource Fragmentation-Aware Virtual Network Embedding for IoT Applications in MEC Networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |
|
| RJ01 | Rejection of invention patent application after publication |