A Case Study on Data Mining Application in a Virtual Power Plant: Cluster Analysis of Power Quality Measurements

Abstract

One of the recent trends that concern renewable energy sources and energy storage systems is the concept of virtual power plants (VPP). The majority of research now focuses on analyzing case studies of VPP in different issues. This article presents the investigation that is based on a real VPP. That VPP operates in Poland and consists of hydropower plants (HPP), as well as energy storage systems (ESS). For specific analysis, cluster analysis, as a representative technique of data mining, was selected for power quality (PQ) issues. The used data represents 26 weeks of PQ multipoint synchronic measurements for 5 related to VPP points. The investigation discusses different input databases for cluster analysis. Moreover, as an extension to using classical PQ parameters as an input, the application of the global index was proposed. This enables the reduction of the size of the input database with maintaining the data features for cluster analysis. Moreover, the problem of the optimal number of cluster selection is discussed. Finally, the assessment of clustering results was performed to assess the VPP impact on PQ level.

Clustering Methods for Power Quality Measurements in Virtual Power Plant

“…The measurement dataset consists of 10 min of classical power quality parameters with a measurement period of 26 weeks, recorded from 1 May to 29 October 2020. In previous research [32], the application of the global index was proposed to reduce the size of the input dataset from all PQ parameters to maintain the data features for cluster analysis. However, this article is a further development of the reference study [32].…”

“…In previous research [32], the application of the global index was proposed to reduce the size of the input dataset from all PQ parameters to maintain the data features for cluster analysis. However, this article is a further development of the reference study [32]. This study only deals with analyzing a part of the measured data from PQ recorders to obtain comparative results between two clustering algorithms.…”

“…The research object of this article is to study the power quality problem in a virtual power plant operating in Lower Silesia, Poland. The studied subject refers to reference research [32], which concerns a case study of a VPP that analyzed medium voltage (MV) distribution networks. The real VPP consists of a 1.25 MW hydroelectric power plant (HPP) connected to a 0.5 MW battery energy storage system (ESS), which relies on a 20 kV distribution network connected to the HV/MV substation via an MV line (1-MV).…”

“…The first object of study includes the power quality measurement data from PQ recorders at the measurement points 2HPP-MV and 2EES-MV, presented in Figure 1. They are treated as one point but reported as two for PQ issues because the hydropower plant and the energy storage system are connected to one node, and their PQ recorders are connected to the same voltage transformer [32]. However, the active power level of 2ESS-MV and 2HPP-MV is measured separately.…”

“…In terms of a non-hierarchical approach, reference [32] introduces cluster analysis with the K-means algorithm on the long-term measurement of power quality data in the real virtual power plant that operates in Poland. The research aimed to identify the different working conditions of the VPP based on data features.…”