Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means
In this work, an innovative methodology for the strategic placement of electric vehicle (EV) charging stations is presented, considering both population density and proximity to the stations, in order to optimize accessibility. This approach synergistic leverages the advantages of genetic algorithms...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10798449/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850121992778285056 |
|---|---|
| author | Rafael Monteagudo Edgardo D. Castronuovo Ramon Barber |
| author_facet | Rafael Monteagudo Edgardo D. Castronuovo Ramon Barber |
| author_sort | Rafael Monteagudo |
| collection | DOAJ |
| description | In this work, an innovative methodology for the strategic placement of electric vehicle (EV) charging stations is presented, considering both population density and proximity to the stations, in order to optimize accessibility. This approach synergistic leverages the advantages of genetic algorithms (GAs) and weighted K-means clustering, creating a phased process that circumvents the typical constraints presented by the two methods in developing efficient EV charging infrastructures. Initially, a GA is used to obtain a spectrum of potential locations, setting a preliminary distribution of charging stations. Then, a K-means clustering method is used to refine this distribution and obtain the most advantageous sites. The number of charging stations is modulated by variable <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula>, which adjusts the influence of the GA and K-means in the final solution. The outcome is a more effective and realistic distribution of EV charging stations that can adapt to the actual patterns of urban population distribution, the economy of resources and EV demand. The proposed methodology is applied to an urban environment in two Spanish cities. The solution decreases between 60.60 and 95 % the number of the charging stations relative to those obtained by using k-mean and between 38.09 and 70 % those obtained using GAs, resulting in an economic and efficient grid of charging stations. |
| format | Article |
| id | doaj-art-7b35d60aeddf4a0da038d33c17ca00b5 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7b35d60aeddf4a0da038d33c17ca00b52025-08-20T02:34:56ZengIEEEIEEE Access2169-35362024-01-011219107119108510.1109/ACCESS.2024.351694110798449Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-MeansRafael Monteagudo0https://orcid.org/0009-0008-4297-2859Edgardo D. Castronuovo1https://orcid.org/0000-0003-2292-4928Ramon Barber2https://orcid.org/0000-0003-2800-2457FCC, Madrid, SpainElectrical Engineering Department, Universidad Carlos III of Madrid, Leganés, SpainSystems Engineering and Automation, Universidad Carlos III of Madrid, Leganés, SpainIn this work, an innovative methodology for the strategic placement of electric vehicle (EV) charging stations is presented, considering both population density and proximity to the stations, in order to optimize accessibility. This approach synergistic leverages the advantages of genetic algorithms (GAs) and weighted K-means clustering, creating a phased process that circumvents the typical constraints presented by the two methods in developing efficient EV charging infrastructures. Initially, a GA is used to obtain a spectrum of potential locations, setting a preliminary distribution of charging stations. Then, a K-means clustering method is used to refine this distribution and obtain the most advantageous sites. The number of charging stations is modulated by variable <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula>, which adjusts the influence of the GA and K-means in the final solution. The outcome is a more effective and realistic distribution of EV charging stations that can adapt to the actual patterns of urban population distribution, the economy of resources and EV demand. The proposed methodology is applied to an urban environment in two Spanish cities. The solution decreases between 60.60 and 95 % the number of the charging stations relative to those obtained by using k-mean and between 38.09 and 70 % those obtained using GAs, resulting in an economic and efficient grid of charging stations.https://ieeexplore.ieee.org/document/10798449/Genetic algorithmsweighted K-means clusteringEV charging stations placementoptimization |
| spellingShingle | Rafael Monteagudo Edgardo D. Castronuovo Ramon Barber Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means IEEE Access Genetic algorithms weighted K-means clustering EV charging stations placement optimization |
| title | Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means |
| title_full | Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means |
| title_fullStr | Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means |
| title_full_unstemmed | Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means |
| title_short | Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means |
| title_sort | optimal evs charge station allocation considering residents dispersion using a genetic algorithm and weighted k means |
| topic | Genetic algorithms weighted K-means clustering EV charging stations placement optimization |
| url | https://ieeexplore.ieee.org/document/10798449/ |
| work_keys_str_mv | AT rafaelmonteagudo optimalevschargestationallocationconsideringresidentsdispersionusingageneticalgorithmandweightedkmeans AT edgardodcastronuovo optimalevschargestationallocationconsideringresidentsdispersionusingageneticalgorithmandweightedkmeans AT ramonbarber optimalevschargestationallocationconsideringresidentsdispersionusingageneticalgorithmandweightedkmeans |