KIT | KIT-Bibliothek | Impressum

Neural Network-based Load Forecasting in Distribution Grids for Predictive Energy Management Systems

Sauter, Patrick; Karg, Philipp; Pfeifer, Martin; Kluwe, Mathias; Zimmerlin, Martin; Leibfried, Thomas; Hohmann, Soeren

In this paper we present a new approach for load forecasting in distribution grids based on neural networks. The application focus of the method are predictive energy management systems with a model predictive control (MPC) approach. These control algorithms need predictions of load profiles from 15 minutes up to several days. Due to the moving horizon principle of MPC, the short-term prediction values are of higher importance than the long-term prediction values. Hence, our prediction method focuses in particular on the short-term prediction by taking instantaneous measurement values into account. With this approach, the method yields significantly better results than state of the art forecasting methods. This is shown by means of a case study with one year data from a German distribution grid, where the root-mean-squared error of the prediction can be reduced by 40-80 %.

Zugehörige Institution(en) am KIT Institut für Regelungs- und Steuerungssysteme (IRS)
Institut für Elektroenergiesysteme und Hochspannungstechnik (IEH)
Publikationstyp Proceedingsbeitrag
Jahr 2017
Sprache Englisch
Identifikator ISBN: 978-3-8007-4505-0
ISSN: 0341-3934
KITopen ID: 1000080539
HGF-Programm 37.06.01; LK 01
Erschienen in Die Energiewende : Blueprints for the New Energy Age, Proceedings of the International ETG Congress 2017, World Conference Center, Bonn, 28th - 29th November 2017
Verlag VDE Verlag GmbH, Berlin
Seiten 13-18
Serie ETG-Fachbericht ; 155
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft KITopen Landing Page