Scholarlink

<p>As the shift to electric mobility intensifies, unpredictable EV charging challenges grid stability. This study proposes a multi-layered machine learning framework balancing grid optimization and user service. First, session-level prediction models estimated energy and cost; XGBoost achieved the highest energy accuracy (<InlineEquation ID="IEq1"><EquationSource Format="TEX">\(R^2=0.59\)</EquationSource></InlineEquation>), while Random Forest best predicted cost (<InlineEquation ID="IEq2"><EquationSource Format="TEX">\(R^2=0.80\)</EquationSource></InlineEquation>). Second, a station-level forecasting model using XGBoost demonstrated exceptional precision for daily demand (<InlineEquation ID="IEq3"><EquationSource Format="TEX">\(R^2=0.95\)</EquationSource></InlineEquation>, MAE=0.90 kWh). Finally, K-Means clustering segmented drivers, revealing a user base dominated by Heavy Energy Users (43.5%) and Occasional Visitors (38.8%). This segmentation enables Charge Point Operators to design personalized services and demand response strategies. Overall, the framework integrates prediction, forecasting, and behavioral segmentation to support scalable, data-driven decisions. Ultimately, these insights equip utility providers and operators with the necessary tools to proactively manage load congestion and optimize capital expenditure planning.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An integrated machine learning framework for EV charging management

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月9日

查看全文
  • Nandith Sreekumar,
  • Rahul Satheesh,
  • G. S. Asha Rani,
  • Sheik Mohammed Sulthan

摘要

As the shift to electric mobility intensifies, unpredictable EV charging challenges grid stability. This study proposes a multi-layered machine learning framework balancing grid optimization and user service. First, session-level prediction models estimated energy and cost; XGBoost achieved the highest energy accuracy (\(R^2=0.59\)), while Random Forest best predicted cost (\(R^2=0.80\)). Second, a station-level forecasting model using XGBoost demonstrated exceptional precision for daily demand (\(R^2=0.95\), MAE=0.90 kWh). Finally, K-Means clustering segmented drivers, revealing a user base dominated by Heavy Energy Users (43.5%) and Occasional Visitors (38.8%). This segmentation enables Charge Point Operators to design personalized services and demand response strategies. Overall, the framework integrates prediction, forecasting, and behavioral segmentation to support scalable, data-driven decisions. Ultimately, these insights equip utility providers and operators with the necessary tools to proactively manage load congestion and optimize capital expenditure planning.