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 implementations 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. This work performs a comparative study on the problem of Short-Term Load Forecast, by using different classes of state-of-the-art Recurrent Neural Networks. The authors test the reviewed models first on controlled synthetic tasks and then on different real datasets, covering important practical cases of study. The text also provides a general overview of the most important architectures and defines guidelines for configuring the recurrent networks to predict real-valued time series.
About the Author
Dr. Filippo Maria Bianchi is a postdoctoral researcher in the Department of Physics and Technology at the Arctic University of Norway, Tromsø, Norway. Dr. Michael C. Kampffmeyer is a research fellow at the same institution. Dr. Robert Jenssen is an associate professor at the same institution. Dr. Enrico Maiorino is a research fellow in the Channing Division of Network Medicine at Harvard Medical School, Boston, MA, USA. Dr. Antonello Rizzi is an assistant professor in the Department of Information Engineering, Electronics and Telecommunications at the Sapienza University of Rome, Italy.
Table of Contents
Properties and Training in Recurrent Neural Networks
Recurrent Neural Networks Architectures
Other Recurrent Neural Networks Models
Synthetic Time Series
Real-World Load Time Series