Deep Learning for Energy Time-Series Analysis and Forecasting

TL;DR

This paper reviews deep learning methods applied to energy time-series analysis and forecasting, emphasizing their use in the Greek Energy Market to improve prediction accuracy and practical application.

Contribution

It provides a comprehensive overview of DL techniques for energy forecasting and offers insights specific to the Greek Energy Market, aiding practical implementation.

Findings

Deep learning models outperform traditional methods in energy forecasting.

Application of DL in Greek Energy Market improves prediction accuracy.

Guidelines for applying DL methods in energy time-series analysis.

Abstract

Energy time-series analysis describes the process of analyzing past energy observations and possibly external factors so as to predict the future. Different tasks are involved in the general field of energy time-series analysis and forecasting, with electric load demand forecasting, personalized energy consumption forecasting, as well as renewable energy generation forecasting being among the most common ones. Following the exceptional performance of Deep Learning (DL) in a broad area of vision tasks, DL models have successfully been utilized in time-series forecasting tasks. This paper aims to provide insight into various DL methods geared towards improving the performance in energy time-series forecasting tasks, with special emphasis in Greek Energy Market, and equip the reader with the necessary knowledge to apply these methods in practice.