# In Search of Deep Learning Architectures for Load Forecasting: A Comparative Analysis and the Impact of the Covid-19 Pandemic on Model Performance

## TL;DR

This paper compares deep learning models for short-term load forecasting in power grids, analyzing their accuracy, sustainability, and robustness during the COVID-19 pandemic, with implications for energy market participation and grid reliability.

## Contribution

It provides a comparative analysis of N-BEATS, LSTM, and TCN architectures for load forecasting, including their performance during distribution shifts caused by the COVID-19 pandemic.

## Key findings

- N-BEATS outperforms other models in accuracy.
- COVID-19 significantly impacts model performance.
- LSTM and TCN show varying robustness to distribution shifts.

## Abstract

In power grids, short-term load forecasting (STLF) is crucial as it contributes to the optimization of their reliability, emissions, and costs, while it enables the participation of energy companies in the energy market. STLF is a challenging task, due to the complex demand of active and reactive power from multiple types of electrical loads and their dependence on numerous exogenous variables. Amongst them, special circumstances, such as the COVID-19 pandemic, can often be the reason behind distribution shifts of load series. This work conducts a comparative study of Deep Learning (DL) architectures, namely Neural Basis Expansion Analysis Time Series Forecasting (N-BEATS), Long Short-Term Memory (LSTM), and Temporal Convolutional Networks (TCN), with respect to forecasting accuracy and training sustainability, meanwhile examining their out-of-distribution generalization capabilities during the COVID-19 pandemic era. A Pattern Sequence Forecasting (PSF) model is used as baseline. The case study focuses on day-ahead forecasts for the Portuguese national 15-minute resolution net load time series. The results can be leveraged by energy companies and network operators (i) to reinforce their forecasting toolkit with state-of-the-art DL models; (ii) to become aware of the serious consequences of crisis events on model performance; (iii) as a high-level model evaluation, deployment, and sustainability guide within a smart grid context.