Abstract
Clustering electric load curves is an important part of the load data mining process. In this paper, we propose a clustering algorithm by combining singular value decomposition and KICIC clustering algorithm (SVD-KICIC) for analyzing the characteristics of daily load curves to mitigate some of the traditional clustering algorithm problems, such as only considering intra-class distance and low computational efficiency when dealing with massive load data. Our method identifies effective daily load curve characteristics using the singular value decomposition technique to improve dimensionality reduction, which improves low computational efficiency by reducing the number of dimensions inherent in big data. Additionally, the method performs SVD on the load data to obtain singular values for determination of weight of the KICIC algorithm, which leverages intra-class and inter-class distances of the load data and further improves the computational efficiency of the algorithm. Finally, we perform a series of simulations of actual load curves from a certain city to validate that the algorithm proposed in this paper has a short operation time, high clustering quality, and solid robustness that improves the clustering performance of the load curves.
Highlights
In recent years, with growing demand for electricity and the popularized use of smart electricity meters, electric power systems have accumulated increasingly massive load data [1,2]
Considering all the reviewed clustering methods, we propose a clustering algorithm based on singular value decomposition (SVD)-KICIC to deal with the problems of low clustering quality and poor efficiency caused by blurred boundary samples in traditional clustering techniques for daily load curves
They is compared against three clustering algorithms that do not consider inter-class distance, traditional K-means, SVD-weighted K-means, and KICIC algorithms, to verify the effectiveness and accuracy of the algorithm proposed in this paper
Summary
With growing demand for electricity and the popularized use of smart electricity meters, electric power systems have accumulated increasingly massive load data [1,2]. In [13], six daily load characteristic indexes are selected as dimensionality reduction indexes to express the original load curves before clustering, improving clustering efficiency These methods only consider minimizing intra-class distance for improving the intra-class compactness and ignore the effects of the inter-class distance on the clustering results when they use distance as the daily load curve similarity measure for clustering. The measured daily load data from a city are used as a sample here They is compared against three clustering algorithms that do not consider inter-class distance, traditional K-means, SVD-weighted K-means, and KICIC algorithms, to verify the effectiveness and accuracy of the algorithm proposed in this paper
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
