Search

CN-116451820-B - Site location determination method, apparatus, electronic device and storage medium

CN116451820BCN 116451820 BCN116451820 BCN 116451820BCN-116451820-B

Abstract

The application discloses a station position determining method, a station position determining device, electronic equipment and a storage medium. The method comprises the steps of generating a first population in a random mode, enabling each individual in the population to correspond to a group of sites with different positions, processing the first population by utilizing a redundancy pole technology to obtain a second population, and determining the positions of the different sites by utilizing the second population based on a distribution estimation algorithm (EDA). According to the technical scheme provided by the application, the initial population generated randomly is processed through the redundant pole technology, so that stations in the population are uniformly distributed, the diversity of the population in the iteration process is ensured, the situation of being trapped into local optimum is avoided, and therefore, the probability of obtaining the global optimum solution is improved, namely, the accuracy of the station positions is improved.

Inventors

  • ZHANG TAO

Assignees

  • 中移(苏州)软件技术有限公司
  • 中国移动通信集团有限公司

Dates

Publication Date
20260505
Application Date
20220106

Claims (6)

  1. 1. A method for determining a location of a station, comprising: generating a first population in a random manner, wherein each individual in the population corresponds to a group of sites in different positions; Processing the first population by utilizing a redundant pole technology to obtain a second population, wherein the redundant pole technology is used for converting the position of a station corresponding to each individual in the first population; determining the positions of different sites based on a distribution estimation algorithm EDA by using the second population, wherein in the process of determining the positions of different sites based on EDA by using the second population, Determining a first parameter, wherein the first parameter characterizes an adaptability distribution value and a mean square error of the current population; determining the relevance of the fitness of each group of sites in the current population to other groups of sites; Dividing the current population into at least two sub-populations based on the determined correlation, and determining a second parameter, wherein the second parameter characterizes an fitness distribution value and a mean square error corresponding to each sub-population in the at least two sub-populations; determining learning parameters corresponding to each sub-population in at least two sub-populations; updating the second parameter based on the first parameter and the corresponding learning parameter; generating a normal distribution model by using the updated second parameters; obtaining at least two new sub-populations by using the normal distribution model; Determining a third parameter, wherein the third parameter characterizes the adaptability of the current population; Determining a fourth parameter, wherein the fourth parameter characterizes the adaptability of the new sub-population; And determining a next generation population from the current population and the new sub-population by using the third parameter and the fourth parameter.
  2. 2. The method of claim 1, wherein said determining a correlation to other sets of site fitness comprises: and determining the relevance of the fitness of each group of sites and other groups of sites by using the Pearson coefficient.
  3. 3. The method of claim 1, wherein the determining the first parameter comprises: Determining, for each individual in the current population, location information and fitness of a site of the respective individual, and determining a fitness distribution value of the respective individual based on the determined location information and fitness of the site; and determining the mean square error of the corresponding individual by utilizing the fitness distribution value of the corresponding individual and the position information of the corresponding individual site.
  4. 4. A station position determining apparatus, comprising, The generation unit is used for generating a first population in a random mode, and each individual in the population corresponds to a group of sites in different positions; The processing unit is used for processing the first population by utilizing a redundant pole technology to obtain a second population, and the redundant pole technology is used for converting the position of a station corresponding to each individual in the first population; a determining unit for determining the location of the different sites based on EDA using the second population, wherein, The determining unit is used for determining a first parameter, wherein the first parameter represents the fitness distribution value and the mean square error of the current population, determining the relevance of the fitness of each group site in the current population to other groups sites, dividing the current population into at least two sub-populations based on the determined relevance, determining a second parameter, wherein the second parameter represents the fitness distribution value and the mean square error corresponding to each sub-population in the at least two sub-populations, determining learning parameters corresponding to each sub-population in the at least two sub-populations, updating the second parameter based on the first parameter and the corresponding learning parameters, generating a normal distribution model by using the updated second parameter, obtaining at least two new sub-populations by using the normal distribution model, determining a third parameter, wherein the third parameter represents the fitness corresponding to the current population, determining a fourth parameter, wherein the fourth parameter represents the fitness corresponding to the new sub-population, and determining the next generation from the current population and the new sub-population by using the third parameter and the fourth parameter.
  5. 5. An electronic device comprising a processor and a memory for storing a computer program capable of running on the processor, Wherein the processor is adapted to perform the steps of the method of any of claims 1 to 3 when the computer program is run.
  6. 6. A storage medium having stored thereon a computer program, which when executed by a processor performs the steps of the method of any of claims 1 to 3.

Description

Site location determination method, apparatus, electronic device and storage medium Technical Field The present application relates to the field of evolutionary algorithms, and in particular, to a method and apparatus for determining a site location, an electronic device, and a storage medium. Background In recent years, shared resources have begun to appear in people's lives, such as sharing resources for bicycles, express cabinet sites, and the like. The occurrence of shared resources can improve the utilization rate of the resources, reduce the waste of the resources and bring convenience to the life of people. Therefore, how to reasonably set the site position of the shared resource to maximize and guarantee the coverage of the shared resource and reduce the scheduling distance becomes a problem to be solved. In the related art, it is proposed to use a distribution estimation algorithm (EDA, estimation of Distribution Algorithm) to determine the location of a resource site. EDA builds a probability distribution model through global distribution information of the population, iterates the population through the probability distribution model to select an optimal solution in the population as a site position of a resource, and in the process, the problem of low solving accuracy exists. Disclosure of Invention In order to solve the related technical problems, the embodiment of the application provides a station position determining method, a station position determining device, electronic equipment and a storage medium. The technical scheme of the embodiment of the application is realized as follows: The embodiment of the application provides a station position determining method, which comprises the following steps: generating a first population in a random manner, wherein each individual in the population corresponds to a group of sites in different positions; Processing the first population by utilizing a redundant pole technology to obtain a second population; using the second population, the locations of the different sites are determined based on EDA. In the above scenario, in determining the location of the different sites based on EDA using the second population, Determining a first parameter, wherein the first parameter characterizes an adaptability distribution value and a mean square error of the current population; Dividing the current population into at least two sub-populations, and determining a second parameter, wherein the second parameter characterizes the fitness distribution value and the mean square error corresponding to each sub-population in the at least two sub-populations; generating a normal distribution model by using the first parameter and the second parameter; obtaining at least two new sub-populations by using the normal distribution model; and determining a next generation population by using the current population and the new sub population. In the above scheme, the dividing the current population into at least two sub-populations includes: determining the relevance of the fitness of each group of sites in the current population to other groups of sites; dividing the current population into at least two sub-populations based on the determined relevance. In the above scheme, the determining the correlation degree with the fitness degree of other groups of sites includes: and determining the relevance of the fitness of each group of sites and other groups of sites by using the Pearson coefficient. In the above solution, the generating a normal distribution model by using the first parameter and the second parameter includes: determining learning parameters corresponding to each sub-population in at least two sub-populations; updating the second parameter based on the first parameter and the corresponding learning parameter; and generating a normal distribution model by using the updated second parameters. In the above scheme, the determining the next generation population by using the current population and the obtained new sub population includes: determining a third parameter, wherein the first parameter represents the adaptability of the current population; Determining a fourth parameter, wherein the third parameter characterizes the adaptability of the new sub-population; And determining a next generation population from the current population and the new sub-population by using the third parameter and the fourth parameter. In the above solution, the determining the first parameter includes: Determining, for each individual in the current population, location information and fitness of a site of the respective individual, and determining a fitness distribution value of the respective individual based on the determined location information and fitness of the site; and determining the mean square error of the corresponding individual by utilizing the fitness distribution value of the corresponding individual and the position information of the corresponding individual site