Krischan A. Keitsch's research while affiliated with International School of Management, Germany and other places

Considering the changing European power market, accurate electric load forecasts are of significant importance for power traders to reduce costs for ancillary services by leveling their position on continuous intradaypower markets. The first part of the following case study, based on publicly available load data, focuses on a novel approach to combine different forecasting methodologies and techniques from the area of computational intelligence. The proposed hybrid model blends input forecasts from artificial neuronal networks, multi variable linear regression and support vector regression machine models with fuzzy sets to intraday and day-ahead forecasts. The forecasts are evaluated with commonly used metrics (mean average percentage error - MAPE & normalized rooted mean square error - NRMSE) to allow comparisons with other case studies. Results from input forecasting models range from a yearly MAPE of 2.36% for the linear regression model to 2.1%for the support vector machine. Blended forecast from proposed hybrid models results in a MAPE of 1.46%for one hour and a MAPE of 1.72% for 24 hours ahead forecasts. In the outlook section of the paperwe show how to use blended forecasts as an input source for automatized intraday power trading with algorithms. Besides outlining use cases, model structure of trading algorithms and back testing approaches, the paper offers a state of the art insight on algorithmic trading in the power industry.

Die europäischen Energiemärkte unterliegen aktuell tiefgreifenden Veränderungen. Eine Automatisierung des Handels stellt eine Möglichkeit dar, diesen Umwälzungen zu begegnen. Im Fokus der Öffentlichkeit steht dabei insbesondere der Algorithmische Handel. Daneben ist ein sicherer Betrieb maßgebliche Voraussetzung für einen Einsatz im Rahmen der Digitalisierung der Energiewirtschaft.

Accurate electrical load forecasts are of vital interest to power companies. Short term load forecasts for next hours in particular are important for power dispatch, power trading and system operation. This paper analyzes the conjectures that a self-adaptive weighting algorithm (SAW), blending different standard load forecasting approaches, such as a dynamic standard load profile model, a linear regression model and an artificial neuronal network model, can increase forecasting performance on micro grids for one hour intraday to 24 hours day ahead forecasts. The SAW methodology and forecasting models are applied to a publicly available smart meter data set. Common evaluation metrics such as the mean average percentage error (MAPE) and the normalized rooted mean square error (NRMSE) are used to evaluate the performance of this new hybrid approach and allow a comparison to other studies. Self-adaptive weighing leads to a significant improvement of intraday and day ahead forecasts from 50%–54% and 30%–35% (MAPE improvement for 1h and 24h compared to input forecasts). The resulting intraday and day ahead load SAW forecasts range from 3.19% 1h MAPE to 4.50% 24h MAPE in this case study.

Accurate electrical short term load forecasts play an important role for grid operation, power plant scheduling and power trading. The need for precise forecasts rises as energy markets are in a phase of transition due to severe changes in the energy system for European countries. This transition is mainly caused by rising shares of renewable energies, increasing energy efficiency and consumption pattern changes. This paper presents a case study based on publicly available data, on how selection of weather and economic data, the historic availability of training data and regional aspects affect the quality of short term load forecasts. By using evaluation metrics, such as the normalized rooted mean square error (NRMSE) and the mean average percentage error (MAPE), forecasting results may be compared to other case studies. Furthermore, the case study is based on a novel model framework utilizing e. g. artificial neuronal network (ANN), support vector regression (SVR) and similar day models. By selecting optimized training data sets we increase forecasting accuracy for supported models up to 11%. Forecasting results of supported models for a whole year, including holidays and weekends, range from 2.1% to 2.38% MAPE.

Die Energiewende birgt für Energieversorgungsunternehmen (EVU) eine Reihe von Risiken. Die sich ihnen daraus ergebenden Chancen lassen sich jedoch nur schwer greifen. Insbesondere mit dem Gesetz zur „Digitalisierung der Energiewende“ eröffnen sich interessante Möglichkeiten zur Bewertung innovativer Geschäftsmodelle. Die anfallenden elektrischen Verbrauchsdaten aus Smart Metern können in Verbindung mit bereits im Unternehmen vorhandenen Daten aus der Vertriebsstatistik die Grundlage bilden, welche die Evaluation von neuen Geschäftsmodellen in der Energiewirtschaft möglich macht. Voraussetzung ist jedoch die Klärung der entscheidenden Frage: „Wer sind meine Kunden?“

In the face of a changing European power market, accurate electric load forecasts are of significant importance for power traders, power utility and grid operators to reduce costs for ancillary services. The following case study, based on publicly available load data, focuses on a novel approach to combine different forecasting methodologies and techniques from the area of computational intelligence. The proposed hybrid model blends input forecasts from artificial neuronal networks, multi variable linear regression and support vector regression machine models with fuzzy sets to intraday and day ahead forecasts. The forecasts are evaluated with commonly used metrics (mean average percentage error — MAPE & normalized rooted mean square error — NRMSE) to allow a comparison to other case studies. The results from the input forecasting models range from a yearly MAPE of 3.1% for the artificial neuronal network to 2.51% for the support vector machine. The blended forecast from the proposed hybrid model results in a MAPE of 1.2% for one hour and a MAPE of 2.03% for 24 hours ahead forecasts.

Die Transformation des Energiesystems setzt das Geschäftsmodell klassischer Energieversorger zunehmend unter Druck. Die Flexibilität der Kunden, die frei aus Angeboten auf dem Strommarkt wählen können, lässt sich kaum in die heutige Unternehmensplanung einbeziehen. Das Schweizer Versorgungsunternehmen IWB Industrielle Werke Basel setzt deshalb auf ein innovatives Modellkonzept und will sich zu einem Anbieter und Dienstleister von Energiemanagement weiterentwickeln.

The roll out of smart meters introduces “Time of Use” tariffs to incentive demand response for household customers. This paper describes a methodology to identify the impact of demand response in customer load profiles and applies it to a smart meter data set. The smart meter data for residential household is from the Irish CER Smart Metering Project. The profiles are segmented via kmeans clustering and good clustering results are identified by the silhouette coefficient. One should expect that “Time of Use” tariffs influence the demand behaviour in such a way that the resulting profile changes would lead to separate clusters. This hypothesis can not be verified in this paper for the CER data set.