Very Short to Medium-term Demand and Generation Forecast: A Study Case in Austria

Santos, M; Huo, D; Resch, M; Wade, N; Greenwood, D

doi:10.1049/icp.2021.2125

Very Short to Medium-term Demand and Generation Forecast: A Study Case in Austria

Lookup NU author(s): Dr Marcos Santos, Da Huo ORCiD, Dr Neal Wade ORCiD, Dr David Greenwood

Downloads

Accepted version [.pdf]

Licence

This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by IET, 2021.

For re-use rights please refer to the publisher's terms and conditions.

Abstract

Modern electricity networks are increasing in complexity due to the integration of variable renewable energy sources at both transmission and distribution levels. As part of the daily operation and scheduling of such systems, the very short to medium-term forecasts are a crucial element, providing the expected demand and generation output over a requested period. Artificial neural networks techniques promise to deliver adaptability which overcome the source's variability if the inputs are properly selected. This paper proposes demand and generation forecasting models for distribution systems, each employing a different artificial neural networks architecture. The models are demonstrated on real data from Energie Güssing distribution system. The adaptability of the models to changes in demand during the Covid-19 lockdown is investigated.