Electrical Engineering  2016, Vol. 17 Issue (1): 46-50    DOI:
Research & Development Current Issue| Next Issue| Archive| Adv Search |
Research of Short-Term Load Forecasting Model for Electrical Vehicle Charging Stations based on PSO-SNN
Wang Zhe1, Dai Bingqi1, Li Xiangdong2
1. Qingdao University, Qingdao, Shandong 266071;
2. Maintenance Company of Shandong Power Company, Ji’nan 250000

Download: PDF (11972 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The load characteristic of the electric vehicle charging station is analyzed based on the weather forecast data and measured power data. A short-term load forecasting model for electrical vehicle charging stations based on particle swarm optimized spike neural network is built in this paper. Spike neural network encode information in the timing of single spike, making it with strong calculating ability, large information capacity and good real time capability. Verifies with simulation example, the errors of prediction model proposed in this paper are less than the traditional BP-NN model for 8.59%、9.28%、12.06% and 8.72% respectively in four seasons, so the model has a better prediction accuracy.
Key wordselectric vehicle charging stations      short-term load forecasting      spike neural network      particle swarm optimized     
Published: 13 January 2016
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Wang Zhe
Dai Bingqi
Li Xiangdong
Cite this article:   
Wang Zhe,Dai Bingqi,Li Xiangdong. Research of Short-Term Load Forecasting Model for Electrical Vehicle Charging Stations based on PSO-SNN[J]. Electrical Engineering, 2016, 17(1): 46-50.
URL:  
https://dqjs.cesmedia.cn/EN/Y2016/V17/I1/46
Copyright © Electrical Engineering
Supported by: Beijing Magtech