Hybrid deep learning based load forecasting and AI-driven energy management for grid-connected multi-microgrids

Microgrids offer a promising paradigm for sustainable and decentralized energy management; however, they face operational challenges due to fluctuating load profiles and the intermittency of renewable energy sources. This paper proposes a two-phase framework to address these challenges through accurate short-term load forecasting (STLF) and an advanced energy management system (EMS) for grid-connected multi-microgrids. In Phase I, STLF was performed using residential metering infrastructure data from the PRECON dataset. A hybrid deep learning model, Prophet -Long Short-Term Memory (PLSTM), was developed and outperformed benchmarks, including LSTM, XGBoost, SARIMA, and Prophet, reducing the error by 12%–18%. In Phase II, an AI-enhanced EMS is introduced, integrating PLSTM-based load forecasting, ANN-based photovoltaic generation prediction, adaptive self-learning weights, and deep Q-learning for forecast margin tuning. This robust hierarchical model predictive control strategy eliminates reliance on demand-side management and preserves user comfort. The simulation results demonstrate that the proposed framework outperforms conventional baseline EMS methods in terms of energy efficiency, reducing grid imports by 28%, adaptability with average SoC tracking improvement of 15%, and resilience indicated by a 22% increase in battery cycle longevity under uncertainties in load consumption and solar energy generation, offering a scalable solution for microgrid deployment in dynamic environments.