LSTM-based Energy Management for Electric Vehicle Charging in Commercial-Building Prosumers

Huayanran Zhou, Yihong Zhou, Junjie Hu, Guangya Yang, Dongliang Xie, Yusheng Xue, Lars Nordström

Research output: Contribution to journalJournal articlepeer-review

2 Downloads (Pure)


As typical prosumers, commercial buildings equipped with electric vehicle (EV) charging piles and solar photovoltaic panels require effective energy management method. However, the conventional optimization model-based building energy management system faces significant challenges regarding prediction and calculation in online execution. To address this issue, a long short-term memory (LSTM) recurrent neural network-based machine learning algorithm is proposed in this study to schedule the charging and discharging of numerous EVs
in commercial building prosumers. Under the proposed system control structure, the LSTM algorithm can be separated into an offline and online stage. In the offline stage, the LSTM is used to map states (inputs) to decisions (outputs) based on the network training. In the online stage, once the current state is input, the LSTM can quickly generate a solution without any additional prediction. A preliminary data processing rule and an additional output filtering procedure are designed to improve the decision performance of LSTM network. The simulation results demonstrate that the LSTM algorithm can generate near-optimal solutions in milliseconds and significantly reduce the prediction and calculation pressure compared to the conventional optimization algorithm.
Original languageEnglish
JournalJournal of Modern Power Systems and Clean Energy
Number of pages13
Publication statusAccepted/In press - 2021


  • Building energy management system (BEMS)
  • Electric vehicles (EVs)
  • Long short-term memory (LSTM) recurrent neural network
  • Machine learning
  • Prosumer


Dive into the research topics of 'LSTM-based Energy Management for Electric Vehicle Charging in Commercial-Building Prosumers'. Together they form a unique fingerprint.

Cite this