Scholarlink

<p>Nowadays, the modern energy systems which are effectively adapting the smart grid technology as well as Electric Vehicle (EV) usage. Electric car placed a significant pressure during the charging over the distribution system based on their higher power requirements. Therefore, this study proposes a hybrid optimization framework that integrates Graph Convolution Network (GCN) with Walrus Optimization (WaO) and Sculptor Optimization-based Gradient Boost (SObGB) to enhance EV charging performance within Internet of Things (IoT)-enabled smart grids. The GCN–WaO module predicts optimal charging schedules, load conditions, and grid usage patterns, while SObGB ensures cost-effective load balancing and energy efficiency through dynamic scheduling. Simulation results demonstrate significant improvements, achieving 95.6% energy efficiency, 94.8% load balancing, and an operational cost reduction to $115.2, outperforming existing optimization techniques. The proposed model offers a scalable and intelligent solution for next-generation EV–grid integration and sustainable energy management.</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 optimized machine learning and IOT based energy efficient strategy for electric vehicle leveraging big data analytics in power grids

  • 期刊论文

  • 发表日期：

    2025年12月20日

查看全文
  • Neeraj Shrivastava,
  • Sanjiv Kumar Jain

摘要

Nowadays, the modern energy systems which are effectively adapting the smart grid technology as well as Electric Vehicle (EV) usage. Electric car placed a significant pressure during the charging over the distribution system based on their higher power requirements. Therefore, this study proposes a hybrid optimization framework that integrates Graph Convolution Network (GCN) with Walrus Optimization (WaO) and Sculptor Optimization-based Gradient Boost (SObGB) to enhance EV charging performance within Internet of Things (IoT)-enabled smart grids. The GCN–WaO module predicts optimal charging schedules, load conditions, and grid usage patterns, while SObGB ensures cost-effective load balancing and energy efficiency through dynamic scheduling. Simulation results demonstrate significant improvements, achieving 95.6% energy efficiency, 94.8% load balancing, and an operational cost reduction to $115.2, outperforming existing optimization techniques. The proposed model offers a scalable and intelligent solution for next-generation EV–grid integration and sustainable energy management.