Cluster-Based Approach to Estimate Demand in the Polish Power System Using Commercial Customers’ Data
Tomasz Ząbkowski,
Krzysztof Gajowniczek,
Grzegorz Matejko,
Jacek Brożyna,
Grzegorz Mentel,
Małgorzata Charytanowicz,
Jolanta Jarnicka,
Anna Olwert,
Weronika Radziszewska,
Jörg Verstraete
Affiliations
Tomasz Ząbkowski
Institute of Information Technology, Warsaw University of Life Sciences-SGGW, Nowoursynowska 159, 02-787 Warsaw, Poland
Krzysztof Gajowniczek
Institute of Information Technology, Warsaw University of Life Sciences-SGGW, Nowoursynowska 159, 02-787 Warsaw, Poland
Grzegorz Matejko
Polskie Towarzystwo Cyfrowe, Krakowskie Przedmieście 57/4, 20-076 Lublin, Poland
Jacek Brożyna
Department of Quantitative Methods, The Faculty of Management, Rzeszow University of Technology, Aleja Powstańców Warszawy 10/S, 35-959 Rzeszow, Poland
Grzegorz Mentel
Department of Quantitative Methods, The Faculty of Management, Rzeszow University of Technology, Aleja Powstańców Warszawy 10/S, 35-959 Rzeszow, Poland
Małgorzata Charytanowicz
Systems Research Institute, Polish Academy of Sciences, Newelska 6, 01-447 Warsaw, Poland
Jolanta Jarnicka
Systems Research Institute, Polish Academy of Sciences, Newelska 6, 01-447 Warsaw, Poland
Anna Olwert
Systems Research Institute, Polish Academy of Sciences, Newelska 6, 01-447 Warsaw, Poland
Weronika Radziszewska
Systems Research Institute, Polish Academy of Sciences, Newelska 6, 01-447 Warsaw, Poland
Jörg Verstraete
Institute of Fluid-Flow Machinery, Polish Academy of Sciences, Fiszera 14, 80-231 Gdańsk, Poland
This paper presents an approach to estimate demand in the Polish Power System (PPS) using the historical electricity usage of 27 thousand commercial customers, observed between 2016 and 2020. The customer data were clustered and samples as well as features were created to build neural network models. The goal of this research is to analyze if the clustering of customers can help to explain demand in the PPS. Additionally, considering that the datasets available for commercial customers are typically much smaller, it was analyzed what a minimal sample size drawn from the clusters would have to be in order to accurately estimate demand in the PPS. The evaluation and experiments were conducted for each year separately; the results proved that, considering adjusted R2 and mean absolute percentage error, our clustering-based method can deliver a high accuracy in the load estimation.
