Load Prediction and Deployment Optimization of Electric Vehicles Based on CNN-LSTM Model

Yipu Wang

doi:10.47297/taposatWSP2633-456933.20250603

PDF
Export
Share
Collection
Album

Load Prediction and Deployment Optimization of Electric Vehicles Based on CNN-LSTM Model

Volume 6, Issue 3

Views: 0 Downloads: 0

Load Prediction and Deployment Optimization of Electric Vehicles Based on CNN-LSTM Model
Load Prediction and Deployment Optimization of Electric Vehicles Based on CNN-LSTM Model
Electrical and Electronic Engineering school, Nanyang Technological University, Zibo, Shandong, China, 255000
Vol. 6, Issue 3, Pages: 175-181(2025)
Published：25 March 2025
DOI：10.47297/taposatWSP2633-456933.20250603
Accepted：

Scan QR Code

Wang Yipu.Load Prediction and Deployment Optimization of Electric Vehicles Based on CNN-LSTM Model[J].Theory and Practice of Science and Technology,2025,06(03):175-181.
DOI：

Wang Yipu.Load Prediction and Deployment Optimization of Electric Vehicles Based on CNN-LSTM Model[J].Theory and Practice of Science and Technology,2025,06(03):175-181. DOI： 10.47297/taposatWSP2633-456933.20250603.

摘要

Abstract

The development of new energy vehicles in China is currently progressing swiftly. As the number of electric vehicles (EV) increases rapidly

the charging demand has also increased significantly. Numerous electric vehicles linked to the electrical grid at one time can increase power grid's operating pressure

enlarge the variance in power load between peak and valley

making it more difficult for scheduling for the power grid's functioning and upkeep. Therefore

accurate prediction of EV charging is helpful to scientifically plan charging scheme

and is significant to maintain the smooth operation of the grid. This paper use the hybrid neural network model for short-term prediction of charging load

build CNN-LSTM-Attention model

supplemented by attention mechanism and residual connection to optimize the neural network model

introduce the GRU unit to reduce the number of parameters and calculation

make it easier to be deployed on the embedded equipment of charging station.

关键词

Keywords

references

Pang Songling, Fan Kaidi, Chen Chao, et al. Multi-time-scale prediction model of EV charging load based on LightGBM algorithm and travel chain theory [J]. Automotive Technology, 2024,(06):9-16.DOI:10.19620/j.cnki.1000-3703.20230993.

A hybrid model based on convolutional neural network and long short-term memory for short-term load forecasting

Zhang Yanyu, Zhang Zhiming, Liu Chunyang, et al. Charging load prediction of EVs based on a dynamic adaptive graph neural network [J]. Automation of Electric Power System, 2024,48 (07): 86-93.

Lin Xiang, Zhang Hao, Ma Yuli, et al. Charging load prediction of electric vehicles based on the improved LSTM neural network [J]. Modern Electronic Technology, 2024,47 (6): 97-101.

Rui Yan, Jiaqiang Liao, Jie Yang, Wei Sun, Mingyue Nong, Feipeng Li,

Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering,Expert Systems with Applications,Volume 169,2021,114513,ISSN 0957-4174.

Alzubaidi, L., Zhang, J., Humaidi, A.J. et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8, 53 (2021).

Alex Sherstinsky, Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network, Physica D: Nonlinear Phenomena, Volume 404, 2020, 132306, ISSN 0167-2789, https://doi.org/10.1016/j.physd.2019.132306.

M. Alhussein, K. Aurangzeb and S. I. Haider, "Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting," in IEEE Access, vol. 8 , pp. 180544 - 180557 , 2020, doi: 10.1109/ACCESS.2020.3028281.

HUANGFU Xiao-ying, QIAN Hui-min, HUANG Min. A Review of Deep Neural Networks Combined with Attention Mechanism[J]. Computer and Modernization, 2023, 0(02): 40-49.

Zheng Zheng, et al. " Power load prediction based on multi-head attention convolution network. "Journal of Nanjing University of Information Science & Technology (Natural Science Edition)/Nanjing Xinxi Gongcheng Daxue Xuebao (ziran kexue ban) 14.5 (2022).

Wang Jin, et al. " named entity identification based on hierarchical residue connection LSTM. "Journal of Jiangsu University (Natural Science Edition)/Jiangsu Daxue Xuebao (Ziran Kexue Ban) 43.4 (2022).

Shewalkar, Apeksha, Deepika Nyavanandi, and Simone A. Ludwig. "Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU." Journal of Artificial Intelligence and Soft Computing Research 9.4 (2019): 235-245.

Alert me when the article has been cited

Submit

Prediction of the Flight Delay Based on Neural Network and Support Vector Machine: A Comparative Study

Two Multi-Unit Artificial Intelligence Decision Modes in Video Games：A Comparison

A CNN-based Physical Layer Design for Communications System

Related Author

Yuxin Huang

Qisen Lin

Xinyi Li

Related Institution

Tan Kah Kee College of Xiamen University

School of Information Engineering, Wuhan University of Technology