Optimizing Smart Grid Load Forecasting via a Hybrid LSTM-XGBoost Framework: Enhancing Accuracy, Robustness, and Energy Management

As renewable energy sources and distributed generation become more integrated into modern power systems, accurate short-term electricity load forecasting is increasingly critical for effective smart grid management. Most statistical techniques used in the analysis of time series models, conventional statistical models often fail to account for temporal dependencies and inherent nonlinear patterns found in real-world energy time series. Methods: To this end, merging the power of both the ML approaches, namely Long Short-Term Memory (LSTM) networks and XGBoost, into hybrid frame-works has come as a powerful solution. This work aims to develop a new compound model of LSTM for time series pattern extraction from the temporal data and XGBoost for outstanding predictive performance. To assess the performance of the proposed model, we used the Elia Grid dataset from Belgium, which includes load data recorded every 15 minutes throughout 2022. Results: When compared to individual models, this hybrid approach outperformed them, achieving a Root Mean Square Error (RMSE) of 29.45 MW, a Mean Absolute Percentage Error (MAPE) of 2.87%, and a coefficient of determination (R²) of 0.945. Discussion: In addition, the study also investigates the po-tential integration of attention mechanisms and ensemble learning strategies to im-prove model interpretability and stability. The results extend the literature on the de-velopment of fusion-based machine learning models for time series forecasting, and the future work of energy consumption analysis, anomaly detection, and resource al-location in SMs grids.