Open Access

ARTICLE

Optimal Planning of Electric Vehicle Charging Stations Considering Load Rates Based on SMS-EMOA

Ji Wang^1,2, Yuanweiji Hu³, Bo Yang^3,*
1 CSG Electric Power Research Institute Co., Ltd., Guangzhou, China
2 Guangdong Provincial Key Laboratory of Intelligent Measurement and Advanced Metering of Power Grid, Guangzhou, China
3 Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming, China
* Corresponding Author: Bo Yang. Email:
(This article belongs to the Special Issue: Artificial Intelligence in Energy Systems: Challenges, Opportunities, and Emerging Applications)

Energy Engineering https://doi.org/10.32604/ee.2026.080317

Received 06 February 2026; Accepted 24 March 2026; Published online 13 April 2026

Abstract

With the rapid proliferation of electric vehicles (EV), charging demand has surged substantially, prompting widespread deployment of EV charging stations (EVCS) within distribution networks. However, uncoordinated EV charging behavior poses significant challenges to grid stability, operational safety, and economic efficiency. To mitigate these adverse impacts, this paper proposes a multi-objective optimal planning model for integrated EVCS–battery energy storage system (BESS) infrastructure. The model explicitly integrates empirically derived EV user charging behavior patterns and jointly optimizes three interdependent objectives: minimizing the total life-cycle cost of the integrated EVCS–BESS system subject to distribution network loading limits; reducing average user waiting time; and mitigating voltage deviations and active power losses in the distribution network—thereby improving equipment utilization efficiency and enhancing grid resilience. To validate the proposed approach, we construct a semi-realistic test case integrating the actual road network topology of Chenggong University Town (Kunming) with an extended IEEE 69-bus distribution system. The model is solved using the Strength Pareto Evolutionary Algorithm based on SMS-EMOA. Numerical results demonstrate that, relative to the baseline scenario without coordinated planning, the proposed strategy reduces voltage deviation by 32.73% and total system active power loss by 2.32%.

---

Keywords

Electric vehicle; energy storage system; charging demand forecasting; load rates; SMS-EMOA

---