Title: Energy consumption prediction of new energy vehicles in smart city based on LSTM network
Authors: Shulong Wu; Fengjun Wang; Maosong Wan
Addresses: Wuxi Vocational Institute of Commerce, Wuxi 214000, Jiangsu, China ' Wuxi Vocational Institute of Commerce, Wuxi 214000, Jiangsu, China ' College of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, Jiangsu, China
Abstract: In order to overcome the traditional problems such as large prediction error and long prediction time, this paper proposes a new energy consumption prediction method of smart city new energy vehicles based on LSTM network. By analysing the energy operation process of new energy vehicles in smart city, the energy consumption prediction parameters such as vehicle battery energy, resistance energy consumption, rolling resistance and air resistance are determined. On this basis, the energy consumption prediction model of new energy vehicles is constructed, and the LSTM network is used to solve the energy consumption prediction model of new energy vehicles, and the energy consumption prediction results are obtained. Experimental results show that the prediction error of the proposed method is always less than 2%, and when the number of iterations is 50, the prediction time of the proposed method is only about 0.95 s, which is relatively short.
Keywords: LSTM network; smart city; new energy vehicle; prediction parameters; prediction model.
International Journal of Global Energy Issues, 2022 Vol.44 No.5/6, pp.484 - 497
Received: 05 Mar 2021
Accepted: 19 Jun 2021
Published online: 08 Sep 2022 *