Hourly Short Term Load Forecasting for Residential Buildings and Energy Communities

TL;DR

This paper evaluates various short-term load forecasting models for residential buildings and energy communities, introducing simpler domain-specific models that outperform traditional methods in hourly predictions.

Contribution

It introduces and compares domain-specific persistence models tailored for hourly load forecasting, demonstrating their superior accuracy over standard machine learning approaches.

Findings

Hourly models improve accuracy by 15-30%.

Domain-specific models outperform black-box models.

Models extend previous day-ahead forecasts to hourly predictions.

Abstract

Electricity load consumption may be extremely complex in terms of profile patterns, as it depends on a wide range of human factors, and it is often correlated with several exogenous factors, such as the availability of renewable energy and the weather conditions. The first goal of this paper is to investigate the performance of a large selection of different types of forecasting models in predicting the electricity load consumption within the short time horizon of a day or few hours ahead. Such forecasts may be rather useful for the energy management of individual residential buildings or small energy communities. In particular, we introduce persistence models, standard auto-regressive-based machine learning models, and more advanced deep learning models. The second goal of this paper is to introduce two alternative modeling approaches that are simpler in structure while they take into account domain specific knowledge, as compared to the previously mentioned black-box modeling techniques. In particular, we consider the persistence-based auto-regressive model (PAR) and the seasonal persistence-based regressive model (SPR), priorly introduced by the authors. In this paper, we specifically tailor these models to accommodate the generation of hourly forecasts. The introduced models and the induced comparative analysis extend prior work of the authors which was restricted to day-ahead forecasts. We observed a 15-30% increase in the prediction accuracy of the newly introduced hourly-based forecasting models over existing approaches.