Journal
NEUROCOMPUTING
Volume 416, Issue -, Pages 47-58Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2019.03.092
Keywords
Electric vehicle; Charging station; Bayesian regularization back propagation learning; Prediction; Heuristic; Congestion
Categories
Funding
- National Natural Science Foundation of China [71601188, 61673303]
- Humanity and Social Science Youth foundation of Ministry of Education of China [16YJC630034]
Ask authors/readers for more resources
With the strong promotion of Chinese government, the number of electric vehicles is growing rapidly. Meanwhile, the development of corresponding charging infrastructure has to keep up. However, infrastructure construction is not a one-off investment, but a multi-period plan. A multi-period location and capacity expansion model of charging stations is built. A forecasting method is proposed to develop the model for estimating the parameters of electric vehicle quantities at each period. The forecasting tool is feed forward neural network based on Bayesian regularization backpropagation learning. The model also introduce the congestion rate to ensure the service quality. Then two kinds of greedy algorithms are proposed. A large number of experiments show that the two algorithms have some complementarity. Finally, the performance of our method is illustrated by a case study of Cixi city. (C) 2019 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available