REINFORCEMENT LEARNING WITH LOAD FORECASTING FOR SMART HOME ENERGY MANAGEMENT

Machine Learning Predictive Models in Smart Home Energy Management: Progress and Challenges

: Home Energy Management Systems (HEMS) is becoming an essential part of the low-carbon economy and smart cities due to the global energy crisis and climate change issues. Conventional Home Energy Management Systems have significant difficulties in dealing with the complexity and heterogeneity of energy data, which hinders their practicality and wide adoption. In this comprehensive paper, the survey and review the recent progress in machine learning techniques for smart home energy management applications, highlighting key developments. The systematically categorize and thoroughly analyze the performance of various machine learning models across multiple critical tasks: energy consumption prediction, user behavior analysis, demand response optimization, and Heating, Ventilation, and Air Conditioning (HVAC) control. The findings show that deep learning methods and reinforcement learning approaches consistently achieve better prediction accuracy and enhanced adaptivity; however, persistent issues exist, such as data heterogeneity, the weak generalization ability of models across different settings, and difficulties in practical real-world deployment and implementation. To address these challenges, the strongly suggest that future research should concentrate on cross-task joint optimization strategies, multi-source data fusion techniques, and long-term adaptive model frameworks to significantly facilitate practical, intelligent energy management in homes.

INTELLIGENT SCHEDULING OF PV–STORAGE–CHARGING INTEGRATED STATIONS VIA GTRXL-PPO WITH CURRICULUM LEARNING

To address the long-horizon sequential decision-making task, characterized by complex temporal dependencies, non-stationary dynamics, and high stochasticity in distribution-level PV–storage–charging systems, this paper develops a deep reinforcement learning framework that combines Gated Transformer‑XL (GTrXL) with Proximal Policy Optimization (PPO). Cross-segment memory captures long‑range temporal dependencies and time‑aware encodings reinforce intraday periodicity. Training adopts a five‑stage curriculum with adaptive KL control and auxiliary multi‑task heads to improve sample efficiency. A group‑normalized, potential‑based reward unifies economic performance, grid friendliness, and storage health. In simulation, the agent learns a structured six-phase daily policy and achieves a 94.4% charging completion rate and 92.8% PV utilization, reduces average daily electricity purchase cost by 15%, and keeps grid peak power within a 60 kW soft limit. Across five seeds, returns improve by 78.4% over a feed-forward PPO baseline and by 23.6% over a vanilla GTrXL-PPO, demonstrating the benefits of long-memory RL for coordinated PV–storage–charging operation. The framework enforces feasibility via continuous action mapping with ramp-rate/jerk constraints and supports millisecond-level inference. Uncertainty-aware shaping improves robustness; gains are statistically significant across five seeds via paired tests.

Research on Optimal Power Grid Scheduling Based on Transfer Reinforcement Learning

To enhance power grid adaptability amid rising renewable energy integration, this paper proposes M3-PPO, a meta-reinforcement learning algorithm that enables efficient the strategy transfer and rapid adaptation across tasks with varying energy mixes. Built upon a base framework (M-PPO) that integrates PPO and MAML, M3-PPO introduces two key innovations to overcome MAML’s training instability: a Mamba-based context encoder for richer task representation in the inner loop, and a global-local momentum update mechanism for smoother meta-parameter optimization in the outer loop. Experiments on the Grid2Op platform demonstrate that M3-PPO significantly outperforms baseline algorithms in generalization and scheduling efficiency, achieving robust performance even when simulating complex energy environments. The approach is particularly suitable for integration with antenna-enabled smart grid monitoring, wireless data acquisition, and edge-computing platforms, providing an engineering-oriented solution for adaptive, real-time, and robust power grid scheduling in modern renewable-rich energy systems.

Sustainable Smart Farm Networks: A Decision Theory-Guided Deep Reinforcement Learning Approach

This work designs a decision theory (DT)-guided transfer learning (TL) framework that unifying cyber resilience and energy adaptability in agricultural monitoring, advancing methodological innovation with DT-guided TL for stable DRL convergence, and providing design insights for sustainable agricultural cyber-physical systems.

DER Allocation without Load Prediction via Reinforcement Learning

A forecast-free reinforcement learning (RL) framework for DERA allocation that learns optimal policies directly from operational data, which preserves the interpretability and constraint satisfaction of DER model while adapting to stochastic demand variations through data-driven updates.

Enhancing energy management in multi-zone buildings using the on-policy reinforcement learning algorithm SARSA