Transfer learning for day-ahead load forecasting: a case study on European national electricity demand time series

TL;DR

This study explores transfer learning for day-ahead electricity demand forecasting across European countries, showing that clustering-based transfer learning improves prediction accuracy over traditional neural network models.

Contribution

It introduces and compares clustering-based transfer learning approaches for short-term load forecasting using neural networks on European demand data.

Findings

Transfer learning outperforms traditional neural network training.

Clustering enhances the effectiveness of transfer learning.

Transfer learning with clustering yields more accurate forecasts.

Abstract

Short-term load forecasting (STLF) is crucial for the daily operation of power grids. However, the non-linearity, non-stationarity, and randomness characterizing electricity demand time series renders STLF a challenging task. Various forecasting approaches have been proposed for improving STLF, including neural network (NN) models which are trained using data from multiple electricity demand series that may not necessary include the target series. In the present study, we investigate the performance of this special case of STLF, called transfer learning (TL), by considering a set of 27 time series that represent the national day-ahead electricity demand of indicative European countries. We employ a popular and easy-to-implement NN model and perform a clustering analysis to identify similar patterns among the series and assist TL. In this context, two different TL approaches, with and without the clustering step, are compiled and compared against each other as well as a typical NN training setup. Our results demonstrate that TL can outperform the conventional approach, especially when clustering techniques are considered.