Short-Term Power Demand Forecasting for Diverse Consumer Types to Enhance Grid Planning and Synchronisation

TL;DR

This paper develops and compares tailored AI-based short-term power demand forecasting models for different consumer groups, incorporating detailed weather and socio-economic data to improve grid stability and planning.

Contribution

It introduces new customized forecasting approaches for diverse consumer types, demonstrating superior accuracy over simpler models by integrating detailed weather and socio-economic features.

Findings

Customized models outperform generic ones in accuracy.

Incorporating weather data significantly improves forecasts.

Different consumer groups require tailored forecasting strategies.

Abstract

Ensuring grid stability in the transition to renewable energy sources requires accurate power demand forecasting. This study addresses the need for precise forecasting by differentiating among industrial, commercial, and residential consumers through customer clusterisation, tailoring the forecasting models to capture the unique consumption patterns of each group. A feature selection process is done for each consumer type including temporal, socio-economic, and weather-related data obtained from the Copernicus Earth Observation (EO) program. A variety of AI and machine learning algorithms for Short-Term Load Forecasting (STLF) and Very Short-Term Load Forecasting (VSTLF) are explored and compared, determining the most effective approaches. With all that, the main contribution of this work are the new forecasting approaches proposed, which have demonstrated superior performance compared to simpler models, both for STLF and VSTLF, highlighting the importance of customized forecasting strategies for different consumer groups and demonstrating the impact of incorporating detailed weather data on forecasting accuracy. These advancements contribute to more reliable power demand predictions, thereby supporting grid stability.