CN115278413B - Ultra-low loss optical fiber upgrading method, device and storage medium - Google Patents
Ultra-low loss optical fiber upgrading method, device and storage medium Download PDFInfo
- Publication number
- CN115278413B CN115278413B CN202210820720.7A CN202210820720A CN115278413B CN 115278413 B CN115278413 B CN 115278413B CN 202210820720 A CN202210820720 A CN 202210820720A CN 115278413 B CN115278413 B CN 115278413B
- Authority
- CN
- China
- Prior art keywords
- optical fiber
- ultra
- low loss
- link
- population
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
- H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
- H04Q11/0062—Network aspects
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0813—Configuration setting characterised by the conditions triggering a change of settings
- H04L41/082—Configuration setting characterised by the conditions triggering a change of settings the condition being updates or upgrades of network functionality
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Genetics & Genomics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Optical Communication System (AREA)
Abstract
The invention is based on genetic algorithm, and mainly researches the upgrade strategy of ultra-low loss optical fiber in the elastic optical network. The link upgrading sequence is encoded into a chromosome gene sequence, iteration is carried out through the processes of crossing, mutation, selection and the like, the link upgrading sequence with the best overall network performance is finally selected, the mutation in the genetic algorithm is the change of the genetic structure caused by allele replacement, and the purpose is to ensure the diversity of groups and prevent the final result from being a local optimal solution. The method starts from improving the overall network performance, and finds out the sequence generating the maximum gain by calculating the gains generated by different link upgrading sequences after iteration. Meanwhile, the found upgrading sequence is the upgrading sequence with the largest gain generated under the fixed cost, so that the defect of high cost in the prior art is well overcome. In addition, compared with the prior art, the method is simpler and easier to understand due to the adoption of the genetic algorithm, the iteration speed is faster, and the error is relatively smaller.
Description
Technical Field
The invention relates to the technical field of elastic optical networks, in particular to an ultralow-loss optical fiber upgrading method, equipment, a device and a computer storage medium.
Background
The popularity of a large number of emerging internet applications creates a significant challenge for operators to provide high quality network services. Currently, in the upgrade of ultra-low loss optical fibers for elastic optical networks, the following three technical strategies are often used:
(1) Link physical length based upgrade strategy
The technology is one of the three most basic technologies, and is based on the fact that the physical length of each optical fiber link in an optical network is ordered from long to short, then the optical fiber links to be upgraded are selected from long to short according to the ordering order, the original common optical fibers are upgraded into ultra-low loss optical fibers until the total length of the upgraded links reaches the maximum value of the length of the existing ultra-low loss optical fibers, so that the bottleneck problem of the ultra-long links on the quality of optical channel signals is reduced, and the overall performance of the optical network is improved.
(2) Link-based maximum gain strategy
The technique attempts to individually implement upgrades for each fiber link and calculates the gain of the overall performance of the optical network after each fiber link upgrade relative to the overall performance before upgrade. And then sequencing the calculated gain of each updated link from large to small, and sequentially selecting the optical fiber links from the gain to perform gradual updating until a sufficient number of optical fiber links are selected. The technology is based on the improvement of the overall performance of the network, and can realize the greater improvement of the performance of the optical network after the upgrading.
(3) Upgrading strategy based on simulated annealing algorithm
The simulated annealing algorithm is derived from the solid annealing principle, heats the solid to a sufficient height, and then slowly cools the solid. The basic idea of the algorithm can be summarized as: first, iterating L times at each temperature T, finding the optimal value at the current temperature by constantly changing the solution x. The temperature search is then reduced until the temperature reaches a minimum, i.e., the temperature reaches a steady state. Based on the algorithm, the technology adopts a mode of randomly generating a link upgrading sequence as a solution x, calculates the gain generated by an initial solution and a new solution, and if the former is smaller than the latter, receives the new solution, otherwise, receives the new solution with a certain probability. Then the temperature is slowly reduced, and the iterative loop is carried out. The algorithm is terminated when none of the new solutions are accepted. The algorithm idea is generally as shown in fig. 1.
(1) Shortcomings of link physical length upgrade policy
The technology only orders the links according to the physical length of the links, and upgrades the optical fiber links from long to short. The whole performance of the optical network is improved by only reducing the bottleneck problem of the ultra-long link on the signal quality of the optical channel, the gain after upgrading is not actually calculated, and the problem of ultra-low loss optical fiber upgrading is not solved from the aspect of network performance gain. At the same time, preferential upgrading of some fiber links with longer physical lengths may result in a smaller number of links that are ultimately upgraded resulting in lower overall gain, or more ultra low loss fibers may be used at more cost to upgrade more links. I.e. lower gain boost at the original cost or higher cost to achieve greater gain.
(2) Shortcomings of maximum gain strategy based on link upgrades
Although the technology starts from the improvement of the overall performance of the network and upgrades the ultra-low loss optical fiber, only the gain of the overall network performance after each upgrade of a single optical fiber is considered, and the upgrade is carried out from large to small based on the gain. It is not considered that an upgrade of an ultra low loss fiber is an upgrade of a fiber link sequence, and the gain of an upgrade sequence ordered by maximum gain is often not the optimal sequence among all possible upgrade sequences after the upgrade. I.e. the solution obtained after upgrading according to the technology is only a local optimal solution but not a global optimal solution.
(3) Shortcomings of upgrading strategy based on simulated annealing algorithm
Compared with the first two technologies, the technology not only starts from the improvement of the overall performance of the network, but also obtains the global optimal solution. However, the design thought of the upgrade strategy of the technology is abstract and difficult to understand easily, the process of solving the optimal upgrade sequence by the design algorithm is very complex, the iteration speed is slow, and the finally obtained result often has errors due to the problem of parameter setting.
Therefore, the defects of the prior art mainly lie in the problems of high cost, poor precision, complex algorithm and the like.
Disclosure of Invention
Therefore, the invention aims to solve the technical problems of high cost, poor precision, complex algorithm and the like in the prior art.
In order to solve the technical problems, the invention provides an ultra-low loss optical fiber upgrading method, which comprises the following steps:
step 1: encoding a sequence of fiber links into chromosomes, each fiber link in the sequence of fiber links acting as a gene on a chromosome;
step 2: establishing a gene library, wherein genes in the gene library comprise all optical fiber links in an original optical network;
step 3: randomly sequencing genes in the gene library to generate n groups of different chromosomes serving as an initial population;
step 4: calculating individual fitness of all individuals in the current population, and selecting father according to the individual fitness, wherein the individual fitness is the performance gain brought to an optical network after ultra-low loss optical fiber upgrading is carried out on each optical fiber link sequence;
step 5: randomly selecting two individuals in the parents as parent chromosomes to cross, generating two groups of new optical fiber link sequences, and repeating the steps until n groups of new optical fiber link sequences are generated;
step 6: the new optical fiber link sequences of each group are mutated according to preset probability to generate a child population, and chromosomes with the largest individual fitness in the current population are stored in an alternative set;
step 7: judging whether the algebra of the child population is smaller than the preset maximum iteration times, if not, selecting the chromosome with the maximum individual fitness in the current alternative set for decoding, and obtaining the optimal sequence of the ultra-low loss optical fiber upgrading in the optical network.
Preferably, if the algebra of the offspring population is not smaller than the preset maximum iteration number, updating the offspring population to the current population, and repeating the steps 4-7.
Preferably, the genes in the gene library further comprise newly-built optical fiber links between all nodes in the optical network, which accord with the principle of newly-drawn ultralow-loss optical fibers.
Preferably, the obtaining the optimal sequence of the ultra-low loss optical fiber upgrade in the optical network includes:
and judging the optical fiber links in the decoded optical fiber link sequence one by one, if the optical fiber links are old optical fiber links in the original optical network, upgrading the optical fiber links into ultralow-loss optical fiber links, and if the optical fiber links are newly built, newly drawing the ultralow-loss optical fibers between the two nodes.
Preferably, the selecting a parent according to the individual fitness comprises:
an i individuals is selected as the parent using a roulette algorithm, wherein the probability of selection of each individual is proportional to its individual fitness value.
Preferably, the randomly selecting two individuals of the parents to cross as parent chromosomes, generating two new sets of fiber link sequences comprises:
randomly generating two numbers a, b and a < b, wherein the part corresponding to the a-th link to the b-th link in the parent chromosome is a switching part;
searching the same link in the parent chromosome as the optical fiber link in the parent chromosome exchanging part, and correspondingly completing the exchanging with the parent chromosome exchanging part;
the same links as the fiber links in the parent chromosome exchange section are searched in the parent chromosome, and the exchange is completed correspondingly to the parent chromosome exchange section.
Preferably, the mutating each new optical fiber link sequence with a preset probability to generate a child population, and storing the chromosome with the largest individual fitness in the current population into the candidate set includes:
and (3) carrying out sequential exchange on one optical fiber link in each group of new optical fiber link sequences and the other optical fiber link at random according to preset probability, so as to finish mutation and generate a sub population.
The invention also provides a device for upgrading the ultralow-loss optical fiber, which comprises:
the coding module is used for coding the optical fiber link sequences into chromosomes, and each optical fiber link in the optical fiber link sequences is used as a gene on the chromosomes;
the gene library establishing module is used for establishing a gene library, wherein genes in the gene library comprise all optical fiber links in an original optical network;
the population initialization module is used for randomly sequencing genes in the gene library to generate n groups of different chromosomes serving as an initial population;
the parent selection module is used for calculating individual fitness of all individuals in the current population, selecting a parent according to the individual fitness, and performing ultra-low loss optical fiber upgrading on each optical fiber link sequence by the individual fitness to obtain performance gain for the optical network;
the crossing module is used for randomly selecting two individuals in the parents as parent chromosomes to cross, generating two groups of new optical fiber link sequences, and repeating the steps until n groups of new optical fiber link sequences are generated;
the mutation module is used for mutating each new optical fiber link sequence with preset probability to generate a child population, and storing chromosomes with the greatest individual fitness in the current population into an alternative set;
and the decoding module is used for judging whether the algebra of the child population is smaller than the preset maximum iteration times, and if not, selecting the chromosome with the maximum individual fitness in the current alternative set for decoding to obtain the optimal sequence of the ultra-low loss optical fiber upgrading in the optical network.
The invention also provides a device for upgrading the ultra-low loss optical fiber, which comprises:
a memory for storing a computer program; and the processor is used for realizing the steps of the ultra-low loss optical fiber upgrading method when executing the computer program.
The invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the steps of the ultra-low loss optical fiber upgrading method when being executed by a processor.
Compared with the prior art, the technical scheme of the invention has the following advantages:
the invention is based on genetic algorithm, and mainly researches the upgrade strategy of ultra-low loss optical fiber in the elastic optical network. The link upgrading sequence is encoded into a chromosome gene sequence, iteration is carried out through the processes of crossing, mutation, selection and the like, the link upgrading sequence with the best overall network performance is finally selected, the mutation in the genetic algorithm is the change of the genetic structure caused by allele replacement, and the purpose is to ensure the diversity of groups and prevent the final result from being a local optimal solution. The method starts from improving the overall network performance, and finds out the sequence generating the maximum gain by calculating the gains generated by different link upgrading sequences after iteration. Meanwhile, the found upgrading sequence is the upgrading sequence with the largest gain generated under the fixed cost, so that the defect of high cost in the prior art is well overcome. In addition, compared with the prior art, the method is simpler and easier to understand due to the adoption of the genetic algorithm, the iteration speed is faster, and the error is relatively smaller.
Drawings
In order that the invention may be more readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings, in which:
FIG. 1 is a schematic diagram of an upgrade strategy based on a simulated annealing algorithm;
FIG. 2 is a flow chart of an implementation of the ultra-low loss fiber upgrade method of the present invention;
fig. 3 is a block diagram of an optical network of 14 nodes;
FIG. 4 is a simulation result of a population count of 100, and a number of iterations of 20;
FIG. 5 is a simulation result of a population count of 100, iteration number of 30;
FIG. 6 is a simulation result of a population count of 100, iteration number of 40;
FIG. 7 is a simulation result of a maximum gain strategy for link upgrades;
fig. 8 is a block diagram of an apparatus for upgrading an ultra-low loss optical fiber according to an embodiment of the present invention.
Detailed Description
The core of the invention is to provide an ultra-low loss optical fiber upgrading method, device, equipment and computer storage medium, which reduce cost, error and algorithm complexity.
In order to better understand the aspects of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The genetic algorithm belongs to a heuristic search algorithm, is a calculation model for simulating the natural selection of the Darwin biological evolutionary theory and the biological evolutionary process of genetic mechanism, and is a method for searching the optimal solution by simulating the natural evolutionary process. The algorithm converts the solving process of the problem into processes like crossing, mutation and the like of chromosome genes in biological evolution in a mathematical mode. The invention adopts programming language Java to write codes, applies genetic algorithm to the upgrade of ultra-low loss optical fiber, and the whole realization thinking is shown in figure 2, and the specific operation steps are as follows:
s101: encoding a sequence of fiber links into chromosomes, each fiber link in the sequence of fiber links acting as a gene on a chromosome;
coding is actually a conversion method that converts one problem into another in some way. In the invention, because we need to search the optimal upgrading sequence of the optical fiber link, the research object is the upgrading sequence of the optical fiber link. Therefore, the technology takes the optical fiber link sequence as a gene sequence, namely a chromosome in biology, takes the length of the optical fiber link sequence as the length of the chromosome, and takes each optical fiber link in the sequence as a gene on the chromosome.
S102: establishing a gene library, wherein genes in the gene library comprise all optical fiber links in an original optical network;
the genes in the gene library also comprise new optical fiber links which accord with the principle of newly drawing ultra-low loss optical fibers among all nodes in the optical network.
In the invention, the optical fiber links are divided into two types, one is an old optical fiber link originally existing in the optical network, the other is a newly built ultralow-loss optical fiber link, namely, the ultralow-loss optical fiber is newly pulled directly between nodes in the optical network, and the length of the ultralow-loss optical fiber is the physical length between two nodes. Attention is paid here to the principle of a new ultra-low loss fiber, i.e. that light cannot newly pull the ultra-low loss fiber between two nodes where old fiber links are present, nor can the newly pulled ultra-low loss fiber cross existing old fiber links in an optical network. The genes on the chromosome should therefore be randomly chosen from among all fiber links in the original optical network and newly created fiber links that may exist between nodes in all optical networks. The coding operation is finished, and the problem of searching the optimal optical fiber link upgrading sequence is converted into the genetic problem in biology.
S103: randomly sequencing genes in the gene library to generate n groups of different chromosomes serving as an initial population;
the population is the basic unit of evolution, and subsequent operations such as crossing, mutation, selection and the like are all carried out in the population. While all organisms of the same population share a gene bank, in the present invention the gene bank corresponds to all optical fiber links in the original optical network and to newly created optical fiber links that may exist between nodes in all optical networks. Therefore, for the subsequent operation, we choose to sort the fiber links in a random sorting manner, so as to generate 100 groups of fiber link sequences as an initial population, which completes the initialization operation of the population. Meanwhile, the random sorting operation also ensures the diversity of the population, so that the result is more convincing.
S104: calculating individual fitness of all individuals in the current population, and selecting father according to the individual fitness, wherein the individual fitness is the performance gain brought to an optical network after ultra-low loss optical fiber upgrading is carried out on each optical fiber link sequence;
s105: randomly selecting two individuals in the parents as parent chromosomes to cross, generating two groups of new optical fiber link sequences, and repeating the steps until n groups of new optical fiber link sequences are generated;
s106: the new optical fiber link sequences of each group are mutated according to preset probability to generate a child population, and chromosomes with the largest individual fitness in the current population are stored in an alternative set;
s107: judging whether the algebra of the child population is smaller than the preset maximum iteration times, if not, selecting the chromosome with the maximum individual fitness in the current alternative set for decoding, and obtaining the optimal sequence of the ultra-low loss optical fiber upgrading in the optical network.
And if the algebra of the child population is not smaller than the preset maximum iteration number, updating the child population into the current population, and repeating the steps S104-S107.
After the selection, crossover and mutation operations, a new generation of more environment-friendly populations is generated. At this time, it is determined whether the algebra of the population is less than the maximum number of iterations. If the algebra of the population is smaller than the maximum iteration number, the new individual fitness is recalculated, and the new individual fitness is calculated, and then the selection, the crossover and the mutation operations are carried out again through the calculated new individual fitness, and the cycle is performed until the algebra of the population reaches the maximum iteration number, and the cycle is jumped out. Meanwhile, the best individual fitness in each generation is continuously compared in the iterative process, so that the chromosome with the largest individual fitness in all generations can be found after the iteration is finished, namely the optical fiber link sequence with the largest gain after upgrading, and subsequent decoding operation is carried out.
Decoding is the reverse process of coding, namely, restoring the chromosome with the greatest individual fitness found after algorithm iteration into an optical fiber link sequence, wherein the sequence is the optimal sequence of the ultra-low loss optical fiber upgrading in the optical network finally solved by the genetic algorithm. And judging the optical fiber links in the decoded optical fiber link sequence one by one, if the optical fiber links are old optical fiber links in the original optical network, upgrading the optical fiber links into ultralow-loss optical fiber links, and if the optical fiber links are newly built, newly drawing the ultralow-loss optical fibers between the two nodes. Until the upgradeable links supported by the cost are maximized. This also ensures maximization of overall network performance improvement at fixed cost. So far, the invention successfully obtains the optimal upgrading strategy of the ultra-low loss optical fiber in the elastic optical network based on the genetic algorithm.
Based on the above embodiments, the present embodiment further describes in detail steps S104 to S106:
an i individuals is selected as the parent using a roulette algorithm, wherein the probability of selection of each individual is proportional to its individual fitness value. The traditional selection is often to arrange according to the calculated fitness of individuals and the quality sequence according to the principle of the superior and inferior elimination, and select the individuals with good fitness as parents to reproduce the offspring. In the present invention, however, a roulette algorithm is used for the selection operation in order to increase the stringency and reduce the error. Roulette is the simplest and most commonly used selection method in which the probability of selection of each individual is proportional to its fitness value, the greater the fitness, the greater the probability of selection, just as a roulette game would be played. After the fitness of the individual, namely the performance gain is calculated, each optical fiber link sequence can be selected as an individual capable of genetic operation with corresponding probability according to the size of the gain, so that the selection operation is completed.
Randomly generating two numbers a, b and a < b, wherein the part corresponding to the a-th link to the b-th link in the parent chromosome is a switching part; searching the same link in the parent chromosome as the optical fiber link in the parent chromosome exchanging part, and correspondingly completing the exchanging with the parent chromosome exchanging part; the same links as the fiber links in the parent chromosome exchange section are searched in the parent chromosome, and the exchange is completed correspondingly to the parent chromosome exchange section. Crossover is understood as the process of pairwise pairing of individuals in a genetic algorithm, i.e., selecting two individuals in a parent and exchanging parts of the chromosome between them with a certain probability. In the present technique, the parent individuals are two random chromosomes after the selection operation in the population, i.e., two sequences are randomly selected from the selected fiber link sequences. Two numbers a, b of a size not exceeding the sequence length are then randomly generated and the minimum value min and the maximum value max of both are found. The part to be exchanged is the corresponding part from the min-th link to the max-th link in the two optical fiber link sequences. However, in the actual implementation process, two identical links appear in one optical fiber link sequence after the direct exchange of the links in two different sequences, which is not practical. Therefore, in order to solve this problem, an exchange concept is replaced here to perform an exchange operation, that is, when one Link1 is exchanged with a Link2 of another optical fiber Link sequence Linklist2, it is not directly exchanged with the Link, but exchanged with a Link3 identical to Link2 in the Link sequence Linklist1 where Link1 is located. Thus, the situation that two identical links appear in one optical fiber link sequence is avoided, and the switching operation is completed in another thought. The two new fiber link sequences generated after the exchange are then stored in the collection, and the operation is repeated until 100 new fiber link sequences are generated.
And (3) carrying out sequential exchange on one optical fiber link in each group of new optical fiber link sequences and the other optical fiber link at random according to preset probability, so as to finish mutation and generate a sub population. The variation in the genetic algorithm is the variation of the genetic structure caused by allele replacement, and aims to ensure the diversity of the population and prevent the final result from being a local optimal solution. In the present invention, the population is subjected to a genetic mutation with a probability of 0.01, i.e., each chromosome in the population has a probability of 0.01. If the gene mutation occurs, the mutated gene bit number is a random number which does not exceed the length of the optical fiber link sequence. In theory, a mutation of a gene is a mutation of a certain gene into another random gene in the gene bank, i.e. a certain link becomes another random link in the optical network. However, considering that two identical links cannot exist in the optical network, another variation idea is adopted here, namely, one link in the optical fiber link sequence is sequentially exchanged with the other random link, so as to complete the variation operation. And storing all the mutated optical fiber link sequences into a new set to be used as a child population set. Thus, one genetic operation is completed.
First, the invention can be distinguished from the prior art in that it allows for the direct new pulling of ultra-low loss optical fibers between nodes of an optical network, rather than merely upgrading old optical fiber links in the optical network. Considering that direct new pulling of ultra-low loss fibers tends to bring higher overall network performance gains for the optical network than upgrading old fiber links, the invention will make the performance of the final calculated link upgrade strategy superior to the prior art.
And secondly, the whole searching strategy and the optimized searching method of the genetic algorithm do not depend on gradient information or other auxiliary knowledge in calculation, but only need to influence an objective function and a corresponding fitness function of a searching direction, so the genetic algorithm provides a general framework for solving complex system problems, does not depend on the specific field of the problems, has strong universality on the types of the problems, and can be well applied to the problem of upgrading the ultralow-loss optical fibers in the elastic optical network. And according to the technical implementation result, the gain of the link upgrading sequence solved by using the genetic algorithm to the overall network performance is approximately 2000 higher than that of the link upgrading sequence solved by using the link upgrading maximum gain strategy widely applied at present.
Meanwhile, the result is always advanced towards the optimal solution by utilizing the natural selection of the Darwin biological evolutionary theory and the biological evolutionary process of the genetic mechanism. The selection operation enables the invention to always discard the link upgrading sequence with low gain in the solving process. The crossover operation plays a core role in the genetic algorithm, and the searching capability of the genetic algorithm is improved dramatically through crossover, and repeated crossover operation enables the invention to search for the optimal solution in a large range. The mutation operation maintains the population diversity of the genetic algorithm to prevent the final result from falling into the locally optimal solution.
In addition, compared with the prior art, the method and the device have the advantages that due to the fact that the genetic algorithm is used, the technical scheme is easy to understand, and the operation complexity is greatly reduced. In addition, compared with other technologies, the technical scheme can obtain results superior to those of other technologies at the same cost, and the cost is greatly reduced.
Based on the above embodiments, in order to verify the feasibility of the present invention, based on the technical scheme, the present embodiment writes the program simulation implementation process by using the java programming language, specifically as follows:
selecting a 14-node optical network as a network to be upgraded, wherein the network structure diagram is shown in fig. 3;
wherein, 0-13 are 14 nodes in the network, the connection line between the nodes is an optical fiber link to be upgraded, and the number on the connection line is the physical length of the link. For example, the link between node 0 and node 1 may be represented as N0-N1, which has a physical length of 260. All other links can be represented similarly.
In order to reduce errors, the invention is more convincing, 100 population generation 20, 100 population generation 30 and 100 population generation 40 are taken as examples for specific description, meanwhile, the variation probability is set to be 0.01, and the length of the optical fiber links for upgrading is set to be 80% of the total length of all links.
The population number is set to 100, the iteration number is set to 20, and then the program is used for running, so that the result shown in fig. 4 can be finally obtained. Links N4-N5 through N10-N11 are the optimal link upgrade sequences that the algorithm eventually solves, and this sequence finally exists in the population of the 20 th generation (genei=0 is the 1 st generation, and thus genei=19 is the 20 th generation). y this sequence can be a gain for overall network performance, as can be seen from the figure as 22040, and the corresponding value of x as 144. Where x is the number of frequency slots of the fiber upgrade sequence, its magnitude is inversely related to the gain, and the smaller the number of frequency slots, the larger the gain. In addition, the program calculates some other parameters such as worst individual fitness, average fitness, population fitness, etc.
The population number is set to 100, the iteration number is set to 30, and the result shown in fig. 5 can be finally obtained by running the program written in advance. Links N4-N5 through N8-N12 are the optimal link upgrade sequences that the algorithm eventually solves for, and this sequence finally exists in the population at generation 30 (genei=0 is generation 1, and thus genei=29 is generation 30). The gain is 22230, and the corresponding number of slots is 143. Compared with the results obtained by the population number of 100 and the iteration number of 20, it can be seen that the program finds a better result as the iteration number increases. The fiber upgrade sequence has a smaller number of frequency slots and a larger gain, while the algorithm finds a population with a higher average fitness and population fitness even if the worst individual fitness becomes worse. Therefore, the population number 100 is not difficult to see, the result obtained by the iteration times 20 is a local optimal solution, but we cannot judge the population number 100, and the result obtained by the iteration times 30 is a global optimal solution, so that the iteration times are required to be increased for further verification.
The population number is set to be 100, the iteration times are increased to 40, and the result shown in fig. 6 can be finally obtained by running a program written in advance. Links N4-N5 through N6-N7 are the optimal link upgrade sequences that the algorithm eventually solves, and this sequence finally exists in the population of the 40 th generation (genei=0 is the 1 st generation, and thus genei=39 is the 40 th generation). The gain is 22230, and the corresponding number of slots is 143. Even if the number of iterations increases, the program does not find the result with the greatest gain, compared to the result obtained with the population number 100 and the number of iterations 30. In fact, to make the results more rigorous, we gradually increase the iteration times to 50, 60, and 70, all of which have the same results, and detailed processes are not repeated here. Therefore, the number of slots is 143, and the result of the gain 22230 is the global optimal solution. However, it is not difficult to find that even if the gains are the same, the resulting link upgrade order is not exactly the same, and in fact, different link upgrade orders may bring about the same gain, so that the globally optimal link upgrade order is not unique.
In order to make the implementation result of the invention more convincing, the method is selected to be compared with the current most common link-upgrading-based maximum gain strategy, and similar to the method, the strategy can also use java to write programs to simulate the implementation process. Therefore, the 14-node optical network which is the same as the implementation process of the present invention is adopted, the length of the optical fiber link for upgrading is set to 80% of the total length of all links, and simulation is carried out, the obtained result is shown in fig. 7, and it can be seen from the graph that links N10-N11 to N2-N5 are the optimal link upgrading sequences finally solved by the algorithm, the frequency slot number is 152, and the corresponding overall network gain is 20520. Therefore, the gain of the link upgrading sequence solved by the technology is even lower than the gain of the local optimal solution obtained by 100 groups of numbers and 20 iterations, and the gain of the overall performance of the optical network of the optimal link upgrading sequence solved by the invention is approximately 2000 higher than the gain solved by the strategy. The superiority of the present invention over other prior art methods can thus be seen.
Referring to fig. 8, fig. 8 is a block diagram illustrating a device for upgrading an ultra-low loss optical fiber according to an embodiment of the present invention; the specific apparatus may include:
the coding module is used for coding the optical fiber link sequences into chromosomes, and each optical fiber link in the optical fiber link sequences is used as a gene on the chromosomes;
an encoding module 100 for encoding a sequence of fiber links into chromosomes, each fiber link in the sequence of fiber links acting as a gene on a chromosome;
the gene library establishment module 200 is used for establishing a gene library, wherein genes in the gene library comprise all optical fiber links in an original optical network;
the population initialization module 300 is used for randomly sequencing genes in the gene library to generate n groups of different chromosomes serving as an initial population;
the parent selection module 400 is configured to calculate individual fitness of all individuals in the current population, and select a parent according to the individual fitness, where the individual fitness is a performance gain brought to the optical network after performing ultra-low loss optical fiber upgrade for each optical fiber link sequence;
a crossover module 500, configured to randomly select two individuals in the parents as parent chromosomes for crossover, generate two new fiber link sequences, and repeat the steps until n new fiber link sequences are generated;
the mutation module 600 is configured to mutate each new group of optical fiber link sequences with a preset probability, generate a child population, and store a chromosome with the greatest individual fitness in the current population into an alternative set;
and the decoding module 700 is configured to determine whether the algebra of the child population is smaller than a preset maximum iteration number, and if not, select a chromosome with the greatest individual fitness in the current candidate set for decoding, so as to obtain an optimal sequence of ultra-low loss optical fiber upgrade in the optical network.
The surface defect detection device based on machine vision of the present embodiment is used to implement the aforementioned ultra-low loss optical fiber upgrade method, so that the specific implementation of the ultra-low loss optical fiber upgrade device can be found in the example parts of the aforementioned ultra-low loss optical fiber upgrade method, for example, the encoding module 100, the gene library creation module 200, the population initialization module 300, the parent selection module 400, the intersection module 500, the mutation module 600, and the decoding module 700, which are respectively used to implement steps S101, S102, S103, S104, S105, S106, and S107 in the aforementioned ultra-low loss optical fiber upgrade method, so that the specific implementation thereof will be described with reference to the corresponding examples of the respective parts and will not be repeated herein.
The embodiment of the invention also provides equipment for upgrading the ultralow-loss optical fiber, which comprises the following components: a memory for storing a computer program; and the processor is used for realizing the steps of the ultra-low loss optical fiber upgrading method when executing the computer program.
The specific embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium is stored with a computer program, and the computer program realizes the steps of the ultra-low loss optical fiber upgrading method when being executed by a processor.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations and modifications of the present invention will be apparent to those of ordinary skill in the art in light of the foregoing description. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the invention.
Claims (9)
1. An ultra-low loss optical fiber upgrade method, comprising:
step 1: encoding a sequence of fiber links into chromosomes, each fiber link in the sequence of fiber links acting as a gene on a chromosome;
step 2: establishing a gene library, wherein genes in the gene library comprise all optical fiber links in an original optical network;
step 3: randomly sequencing genes in the gene library to generate n groups of different chromosomes serving as an initial population;
step 4: calculating individual fitness of all individuals in the current population, and selecting father according to the individual fitness, wherein the individual fitness is the performance gain brought to an optical network after ultra-low loss optical fiber upgrading is carried out on each optical fiber link sequence;
step 5: randomly selecting two individuals in the parents as parent chromosomes to cross, generating two groups of new optical fiber link sequences, and repeating the steps until n groups of new optical fiber link sequences are generated;
step 6: each group of the n groups of new optical fiber link sequences is mutated according to preset probability to generate a child population, and chromosomes with the greatest individual fitness in the current population are stored in an alternative set;
step 7: judging whether the algebra of the child population is smaller than the preset maximum iteration times, if not, selecting the chromosome with the maximum individual fitness in the current alternative set for decoding, and obtaining the optimal sequence of the ultra-low loss optical fiber upgrading in the optical network.
2. The method for upgrading ultra-low loss optical fiber according to claim 1, wherein the genes in the gene library further comprise newly built optical fiber links between all nodes in the optical network according to the principle of newly drawing ultra-low loss optical fiber.
3. The method for upgrading an ultra-low loss optical fiber according to claim 1, wherein the obtaining the optimal sequence of the ultra-low loss optical fiber upgrade in the optical network comprises:
and judging the optical fiber links in the decoded optical fiber link sequence one by one, if the optical fiber links are old optical fiber links in the original optical network, upgrading the optical fiber links into ultralow-loss optical fiber links, and if the optical fiber links are newly built, newly drawing the ultralow-loss optical fibers between the two nodes.
4. The ultra-low loss fiber upgrade method according to claim 1, wherein said selecting parents according to said individual fitness comprises:
an i individuals is selected as the parent using a roulette algorithm, wherein the probability of selection of each individual is proportional to its individual fitness value.
5. The ultra-low loss fiber upgrade method according to claim 1, wherein the randomly selecting two individuals of the parents to cross as parent chromosomes, generating two new sets of fiber link sequences comprises:
randomly generating two numbers a, b and a < b, wherein the part corresponding to the a-th link to the b-th link in the parent chromosome is a switching part;
searching the same link in the parent chromosome as the optical fiber link in the parent chromosome exchanging part, and correspondingly completing the exchanging with the parent chromosome exchanging part;
the same links as the fiber links in the parent chromosome exchange section are searched in the parent chromosome, and the exchange is completed correspondingly to the parent chromosome exchange section.
6. The method of claim 1, wherein mutating each of the n new fiber link sequences with a predetermined probability to generate a population of offspring, and storing chromosomes with the greatest fitness of individuals in the current population in the candidate set comprises:
and (3) carrying out sequential exchange on one optical fiber link in each group of new optical fiber link sequences and the other optical fiber link at random according to preset probability, so as to finish mutation and generate a sub population.
7. An apparatus for ultra-low loss fiber optic upgrades comprising:
the coding module is used for coding the optical fiber link sequences into chromosomes, and each optical fiber link in the optical fiber link sequences is used as a gene on the chromosomes;
the gene library establishing module is used for establishing a gene library, wherein genes in the gene library comprise all optical fiber links in an original optical network;
the population initialization module is used for randomly sequencing genes in the gene library to generate n groups of different chromosomes serving as an initial population;
the parent selection module is used for calculating individual fitness of all individuals in the current population, selecting a parent according to the individual fitness, and performing ultra-low loss optical fiber upgrading on each optical fiber link sequence by the individual fitness to obtain performance gain for the optical network;
the crossing module is used for randomly selecting two individuals in the father as parent chromosomes to cross to generate two groups of new optical fiber link sequences, and repeatedly randomly selecting two individuals in the father as parent chromosomes to cross to generate two groups of new optical fiber link sequences until n groups of new optical fiber link sequences are generated;
the mutation module is used for mutating each group of the n groups of new optical fiber link sequences with preset probability to generate a child population, and storing chromosomes with the greatest individual fitness in the current population into an alternative set;
and the decoding module is used for judging whether the algebra of the child population is smaller than the preset maximum iteration times, and if not, selecting the chromosome with the maximum individual fitness in the current alternative set for decoding to obtain the optimal sequence of the ultra-low loss optical fiber upgrading in the optical network.
8. An ultra-low loss fiber optic upgrade apparatus comprising:
a memory for storing a computer program;
a processor for implementing the steps of a method for ultra low loss fiber upgrade as claimed in any one of claims 1 to 6 when executing said computer program.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of a method for ultra low loss optical fiber upgrade according to any one of claims 1 to 6.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2022107525753 | 2022-06-29 | ||
| CN202210752575 | 2022-06-29 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115278413A CN115278413A (en) | 2022-11-01 |
| CN115278413B true CN115278413B (en) | 2023-08-04 |
Family
ID=83766017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210820720.7A Active CN115278413B (en) | 2022-06-29 | 2022-07-13 | Ultra-low loss optical fiber upgrading method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115278413B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100419482C (en) * | 2004-05-09 | 2008-09-17 | 上海理工大学 | Waveguide-optical fiber automatic core adjusting method based on genetic algorithm and device thereof |
| US20130272711A1 (en) * | 2012-04-13 | 2013-10-17 | Nec Laboratories America, Inc. | Light-Tree Provisioning for Multicast Traffic in Flexible Optical WDM Networks |
| CN109543314B (en) * | 2018-11-27 | 2022-04-15 | 苏州大学 | Optical amplifier rearrangement method of elastic optical network after optical fiber upgrading |
| CN113114365B (en) * | 2021-04-13 | 2021-12-07 | 苏州大学 | Optical fiber deployment method, storage medium, electronic device and system |
| CN113542939B (en) * | 2021-07-12 | 2022-04-22 | 苏州大学 | Multi-cycle upgrading scheduling method based on ultra-low loss optical fiber |
-
2022
- 2022-07-13 CN CN202210820720.7A patent/CN115278413B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115278413A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bajpai et al. | Genetic algorithm–an approach to solve global optimization problems | |
| CN115310664A (en) | RBF neural network training method and prediction system based on gene regulation genetic algorithm | |
| CN113449930A (en) | Optical fiber preform preparation quality prediction method based on BP neural network | |
| CN115965169A (en) | Path planning method, intelligent device and computer readable storage medium | |
| EP3739473B1 (en) | Optimization device and method of controlling optimization device | |
| CN113656156A (en) | Scheduling optimization method based on combination of tabu search algorithm and genetic algorithm | |
| CN117075545A (en) | Multi-target flexible job shop scheduling method, electronic equipment and medium | |
| CN116647459A (en) | Multi-agent co-evolution topological robustness optimization method for Internet of things | |
| CN115278413B (en) | Ultra-low loss optical fiber upgrading method, device and storage medium | |
| JP2002533960A (en) | Code compression by evolutionary algorithm | |
| JP2019194765A (en) | Optimization device and method of controlling the same | |
| CN110570134A (en) | Scheduling method for solving transportation time of flexible workshop belt through improved cultural genetic algorithm | |
| CN110598943A (en) | Method for solving flexible job shop scheduling with transportation time by using improved cultural genetic algorithm | |
| KR100986160B1 (en) | System and method for manufacturing mask using genetic algorithm and dna computing | |
| Nearchou | Flow-shop sequencing using hybrid simulated annealing | |
| CN113503885A (en) | Robot path navigation method and system based on sampling optimization DDPG algorithm | |
| Zhang et al. | Aligning multiple protein sequence by an improved genetic algorithm | |
| CN111681607B (en) | Gamma adjusting method and system based on genetic algorithm | |
| CN117745390B (en) | Multi-objective fuzzy supply chain configuration optimization method and system for multi-population genetic algorithm | |
| Bidlo | On routine evolution of new replicating structures in cellular automata | |
| Huang et al. | A systematic study of genetic algorithms with genotype editing | |
| CN116401037B (en) | Genetic algorithm-based multi-task scheduling method and system | |
| CN117950894A (en) | Software data generation and restoration method based on genetic algorithm | |
| EP4357984A1 (en) | Constrained search: improve multi-objective nas quality by focus on demand | |
| CN110598944A (en) | Cultural genetic algorithm-based flexible workshop scheduling method for solving transportation time |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |