Explainable Stacked Ensemble Model for Short-Term Net Load Forecasting

Abstract

Estimating electricity load is paramount in the strategic planning and operation of power systems, ensuring the efficient and sustainable operation of contemporary electricity supply networks. This study proposes a Stacked Ensemble (SE) model to address these concerns and enhance short-term net load forecasting (STNLF) by combining bidirectional long short-term memory, support vector machine, and random forest (RF) models. An autoencoder is also used to optimise the input data, which extracts critical features from the data and enhances predictive accuracy. This SE model is designed to incorporate Explainable Artificial Intelligence (XAI) as an integral part, providing users detailed insights into input variable influences such as temperature, solar radiation, and wind speed, all interpretable and relevant, thus improving the transparency of the forecasting process. The proposed method is evaluated against real historical time-series data in Austria from 2018 and 2019 regarding hourly measurements for temperature, solar energy, wind turbine generation, and actual loads. Results indicate that the SE model can capture complex data patterns, whereby XAI features actionable insights and proves a reasonable concurrent behaviour prediction with boundary-specific realities. Remarkably, the proposed SE model surpassed traditional machine learning approaches on many performance metrics while showcasing robustness and reliability in increasingly improving STNLF accuracy.