An overview and comparative analysis of Recurrent Neural Networks for Short Term Load Forecasting

TL;DR

This paper reviews and compares various state-of-the-art Recurrent Neural Network architectures for short-term load forecasting, highlighting their effectiveness and providing guidelines for configuration in real-world applications.

Contribution

It offers a comprehensive overview and comparative analysis of different RNN architectures specifically for short-term load forecasting, including experimental validation on synthetic and real datasets.

Findings

Recurrent Neural Networks outperform static models in load forecasting.

Different RNN architectures have varying strengths depending on the dataset.

Guidelines for configuring RNNs for real-valued time series are provided.

Abstract

The key component in forecasting demand and consumption of resources in a supply network is an accurate prediction of real-valued time series. Indeed, both service interruptions and resource waste can be reduced with the implementation of an effective forecasting system. Significant research has thus been devoted to the design and development of methodologies for short term load forecasting over the past decades. A class of mathematical models, called Recurrent Neural Networks, are nowadays gaining renewed interest among researchers and they are replacing many practical implementation of the forecasting systems, previously based on static methods. Despite the undeniable expressive power of these architectures, their recurrent nature complicates their understanding and poses challenges in the training procedures. Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet. In this paper we perform a comparative study on the problem of Short-Term Load Forecast, by using different classes of state-of-the-art Recurrent Neural Networks. We test the reviewed models first on controlled synthetic tasks and then on different real datasets, covering important practical cases of study. We provide a general overview of the most important architectures and we define guidelines for configuring the recurrent networks to predict real-valued time series.