Scholarlink

The increasing adoption of renewable energy sources (RES), Plug-in Electric Vehicles (PEVs), and Battery Energy storage systems (BESS) along with smart appliances by prosumers’ has led to the development of sophisticated Smart home Energy Management Systems (SHEMS). Energy Scheduling is an integral part of SHEMS. Reinforcement learning (RL) is a key energy scheduling strategy in SHEMS, effectively balancing energy needs, and cost reduction while ensuring user comfort. The objective of this review is to highlight recent advancements in RL-based energy scheduling strategies for SHEMS to address pertinent issues and advantages. These strategies are compared based on objectives such as cost reduction, RES and PEV adoption, Real-Time Management, and Battery Degradation cost to draw potential research direction. Pertinent works addressing significant challenges, including computational complexity, uncertainties, and real-time management are also discussed. The review concludes that these strategies for SHEMS are promising from sustainability, energy efficiency, and overall prosumers’ cost-saving perspective.

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

A Review on Reinforcement Learning-Based Energy Scheduling Strategies for Smart Home Energy Management System

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Verendra Singh Kharkwal,
  • S. C. Gupta

摘要

The increasing adoption of renewable energy sources (RES), Plug-in Electric Vehicles (PEVs), and Battery Energy storage systems (BESS) along with smart appliances by prosumers’ has led to the development of sophisticated Smart home Energy Management Systems (SHEMS). Energy Scheduling is an integral part of SHEMS. Reinforcement learning (RL) is a key energy scheduling strategy in SHEMS, effectively balancing energy needs, and cost reduction while ensuring user comfort. The objective of this review is to highlight recent advancements in RL-based energy scheduling strategies for SHEMS to address pertinent issues and advantages. These strategies are compared based on objectives such as cost reduction, RES and PEV adoption, Real-Time Management, and Battery Degradation cost to draw potential research direction. Pertinent works addressing significant challenges, including computational complexity, uncertainties, and real-time management are also discussed. The review concludes that these strategies for SHEMS are promising from sustainability, energy efficiency, and overall prosumers’ cost-saving perspective.