A comparative assessment of deep learning models for day-ahead load forecasting: Investigating key accuracy drivers

TL;DR

This study compares various deep learning models for day-ahead load forecasting in Portugal, identifying key factors affecting accuracy and highlighting N-BEATS as the most effective model.

Contribution

It provides a comprehensive comparison of deep autoregressive models for STLF and investigates the impact of external factors on model accuracy.

Findings

N-BEATS outperforms other models in accuracy.

MLP performs competitively, suggesting simpler models can be effective.

Calendar and weather features significantly influence forecasting accuracy.

Abstract

Short-term load forecasting (STLF) is vital for the effective and economic operation of power grids and energy markets. However, the non-linearity and non-stationarity of electricity demand as well as its dependency on various external factors renders STLF a challenging task. To that end, several deep learning models have been proposed in the literature for STLF, reporting promising results. In order to evaluate the accuracy of said models in day-ahead forecasting settings, in this paper we focus on the national net aggregated STLF of Portugal and conduct a comparative study considering a set of indicative, well-established deep autoregressive models, namely multi-layer perceptrons (MLP), long short-term memory networks (LSTM), neural basis expansion coefficient analysis (N-BEATS), temporal convolutional networks (TCN), and temporal fusion transformers (TFT). Moreover, we identify factors that significantly affect the demand and investigate their impact on the accuracy of each model. Our results suggest that N-BEATS consistently outperforms the rest of the examined models. MLP follows, providing further evidence towards the use of feed-forward networks over relatively more sophisticated architectures. Finally, certain calendar and weather features like the hour of the day and the temperature are identified as key accuracy drivers, providing insights regarding the forecasting approach that should be used per case.