A Comprehensive Literature Review of Optimization Algorithms for Intelligent Load Scheduling in Home Energy Management Systems

Abstract

The increasing complexity of residential energy systems, driven by rising electricity demand, renewable energy integration, and dynamic pricing mechanisms, has intensified the need for intelligent load scheduling within Home Energy Management Systems (HEMSs). This paper presents a comprehensive literature review of optimization algorithms applied to residential load scheduling, based on an analysis of 78 peer-reviewed studies published between 2020 and 2025. The analysis reveals a clear shift from conventional deterministic optimization toward adaptive and data-driven approaches capable of operating in uncertain and dynamic environments. Metaheuristic methods are widely used for solving complex scheduling problems, while Machine Learning and Deep Learning (DL) techniques primarily support forecasting tasks related to energy demand and renewable generation. Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) approaches enable autonomous real-time decision-making, although challenges related to scalability, computational cost, and practical deployment remain unresolved. The review identifies hybrid architectures that combine forecasting, optimization, and control mechanisms as the most promising direction for future HEMS development. Finally, the paper highlights key research gaps, including limited real-world validation, insufficient consideration of physical infrastructure constraints, and the need for scalable distributed control frameworks for future smart grids and energy communities.