Efficient predictive control strategy for mitigating the overlap of EV charging demand and residential load based on distributed renewable energy

Yiqun Li, Ziyuan Pu, Pei Liu, Tao Qian, Qinran Hu, Junyi Zhang and Yinhai Wang

Renewable Energy, 2025, vol. 240, issue C

Abstract: The escalating charging demands driven by the rapid expansion of electric vehicles (EVs) can lead to overlap with residential load, impacting power system instability. Therefore, mitigating the overlap between the EV charging load and the residential load is necessary in the development of EVs. In this context, efficient energy management is proposed in this work to reduce the overlap between the EV charging load and the residential load. First, a self-sustained transportation energy system (STES) is introduced in this work by equipping with photovoltaic (PV) power, to ensure the energy demand of EVs. Moreover, an effective three-stage predictive control approach is elaborately developed in this STES, aiming to reduce the reliance on the power grid and optimize the consumption of PV power. The control algorithm of the three-stage predictive approach operates as follows: Stage I focuses on optimizing day-ahead electricity purchases based on supply and demand predictions, Stage II allocates charging power to stations, and Stage III executes real-time control leveraging energy storage system (ESS) capabilities. Meanwhile, an ensemble deep learning model is well-designed in this proposed method to capture the long-term dependence and the underlying periodic pattern of PV power and the charging demand, called ensemble temporal convolutional network-bidirectional long short-term memory network (ETCN-BiLSTM). The integration of ETCN is achieved by a weight fusion mechanism that calculates the contribution of different TCN layers. Then, this work employs ESS as a ”mitigator” to balance the energy supply and demand. Experimental validation and comparative analysis highlight the efficacy of both prediction and control components in optimizing energy management. Through comprehensive testing, the proposed approach demonstrates its capability to efficiently manage energy in charging stations while maintaining economic feasibility.

Keywords: Transportation electrification; Electric vehicles; Predictive control algorithm; Deep ensemble learning model; Transportation energy system; Energy storage system (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148124022225
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:240:y:2025:i:c:s0960148124022225

DOI: 10.1016/j.renene.2024.122154

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().