Deep learning-based energy optimization for electric vehicles integrated smart micro grid

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragen


Applying renewable energy in a smart micro grid (MG) is increasingly receiving attention to reduce greenhouse gas emissions. However, the mismatch between supply and demand hinders the realization of this process. With the widespread use of plug-in electric vehicles (EVs) and the development of emerging mobile edge cloud (MEC), intelligent energy optimization becomes a way to address the challenge. Therefore, in this paper, we propose a novel two-stage approach based on deep learning (DL) to reduce overall energy cost for sharing EVs integrated MG by forecasting its state and optimizing EVs scheduling. Our simulation results show that the joint design of forecasting and optimization reduces the overall energy consumption and the payment to the external grid.


TitelProceedings of the IEEE International Conference on Communications (ICC); Green Communication Systems and Networks Symposium (GCSN Symposium)
ISBN (elektronisch)9781538683477
PublikationsstatusVeröffentlicht - 17 Mai 2022

Externe IDs

Scopus 85136383746
Mendeley 8eaf2939-601f-3fbc-ba5d-2dc739d5584c
dblp conf/icc/ZhangWBBF22
unpaywall 10.1109/icc45855.2022.9838771


Ziele für nachhaltige Entwicklung


  • deep learning, electric vehicles, micro grid, mobile edge cloud, renewable energy