Optimal energy management strategy for plug-in hybrid electric vehicles based on a combined clustering analysis
| Autor: | Chong Guo, Xu Wang, Zhang Jianan, Zicheng Fu, Di Zhao, Liang Chu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Mathematical optimization
Fitness function business.product_category Energy management Computer science Applied Mathematics Initialization 02 engineering and technology Division (mathematics) 01 natural sciences Dynamic programming Artificial bee colony algorithm 020303 mechanical engineering & transports 0203 mechanical engineering Modeling and Simulation 0103 physical sciences Electric vehicle business Cluster analysis 010301 acoustics |
| Zdroj: | Applied Mathematical Modelling. 94:49-67 |
| ISSN: | 0307-904X |
| DOI: | 10.1016/j.apm.2020.12.023 |
| Popis: | Based on the optimization results of dynamic programming, this paper proposes an optimal rule design method for a series-parallel plug-in hybrid electric vehicle mode division strategy combining K-means clustering and improved artificial bee colony. The improved artificial bee colony algorithm uses the average of the sum of the squares of the distances method to initialize the colony to overcome the randomness of initialization and best utilize the useful information, constructs a fitness function adapted to the clustering analysis, and introduces an acceleration factor into the search equation to dynamically adjusted search scope. Combining the improved artificial bee colony algorithm with the K-means clustering algorithm, the clustering performance is improved and the optimal rule-based mode division strategy is obtained. The simulation results show that the new strategy reduces fuel consumption by 4.78% and electricity consumption by 1.81% comparing with the original strategy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect