A robust hybrid machine learning framework for short-term load forecasting: integrating multi-linear regression, long short-term memory, and feed-forward neural networks for enhanced accuracy and efficiency

Abstract

• Novel Hybrid Model : Developed a novel hybrid machine learning model (MLR-LSTM-FFNN) for short-term load forecasting, integrating statistical regression with deep learning for enhanced predictive performance. • Comprehensive Performance Evaluation : Conducted extensive experiments on real-world datasets (Qatar and Panama City) across multiple time resolutions (5 min, 15 min, 30 min, 1 hour), demonstrating superior accuracy and efficiency. • Empirical Hyperparameter Optimization : Utilized Bayesian optimization for hyperparameter tuning, ensuring optimal performance while balancing computational efficiency. • Model Explainability and Interpretability : Applied LIME to interpret the contributions of key features in the forecasting model, enhancing transparency in AI-driven decision-making. • Statistical Validation of Model Superiority : Employed the Diebold-Mariano test to statistically validate the significant improvements of the hybrid model over traditional approaches. • Efficiency-Accuracy Trade-off : Analyzed computational complexity and training duration, demonstrating that MLR-LSTM-FFNN achieves high accuracy with reduced computational cost compared to alternative hybrid models. Efficient energy management and grid stability strongly rely on accurate Short-Term Load Forecasting (STLF). Existing forecasting models, unfortunately, are often inaccurate and computationally demanding. To overcome these challenges, a novel hybrid model, combining both linear regression and machine learning techniques, is proposed in this study. The hybrid model, MLR-LSTM-FFNN, captures both temporal and non-linear dependencies in load data by integrating multi-linear regression (MLR) with long short-term memory (LSTM) networks and feed-forward neural networks (FFNN). Using datasets from Qatar, with 5-minutes, 15-minutes, 30-minutes, and 1-hour time intervals and from Panama City with a 1-hour interval, experiments were conducted to thoroughly test the robustness of the model. The results showed that the MLR-LSTM-FFNN hybrid model outperformed the baseline and state-of-the-art hybrid models for each of the datasets, in terms of lower RMSE, MAE, and MAPE values along with a faster training time. This superior performance across different datasets underscores the model’s scalability and reliability as an STLF approach, providing a practical solution to energy demand prediction tasks. The improvement in short-term forecasting accuracy provides utilities with a practical tool to optimize demand-side management, reduce operational costs, and enhance grid reliability. Proposed hybrid framework for STLF, integrating MLR, LSTM, and FFNN.

Topics & Concepts