Notice of Violation of IEEE Publication Principles: User Power Interaction Behavior Clustering Analysis That is Based on the Self-Organizing-Center K-Means Algorithm

Shiyu Zhang,Shaoyun Ge

doi:10.1109/access.2019.2957922

Shiyu Zhang, Shaoyun Ge

Open Access

https://doi.org/10.1109/access.2019.2957922

Copy DOI

Abstract

Notice of Violation of IEEE Publication Principles “User Power Interaction Behavior Clustering Analysis That is Based on the Self- Organizing-Center K-Means Algorithm” by Shiyu Zhang and Shaoyun Ge in IEEE Access, Volume 7, December 2019 After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE’s Publication Principles. This paper translated and copied content from the original content from the paper cited below. The original content was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without permission. Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following article: “Clustering Analysis of User Power Interaction Behavior Based on Self-organizing Center K-means Algorithm” by Bingyu Zhou, Bo Liu，Dan Wang，Yu Lan，Xiran Ma，Dongdong Sun, Qiuyi Huo in Electric Power Construction, Vol 40, No 1, January 2019 The participation of power users in grid-side interactive power and auxiliary services has attracted increasing attention. The analysis of users' interaction power behaviors is a core task. By combining the self-organizing map (SOM) neural network and the K-means clustering algorithm, a self-organizing-center K-means algorithm is developed in this paper for conducting a cluster analysis of users' interaction electricity consumption behaviors. This approach can realize more accurate recognition and fast clustering. First, the principle of K-means algorithm in the self-organizing center is analyzed, and its advantages in the clustering analysis of electricity consumption over the traditional clustering algorithm are demonstrated. Then, in the context of peak-to-valley time-of-use electricity pricing, the adjustment potential index, which is based on user psychology, is developed, and a cluster analysis of users' electricity consumption behaviors that is based on load data and the adjustment potential index is conducted. Finally, the daily load data of users within the jurisdiction of a power company are studied, and the two-stage clustering results that are obtained via the self-organizing-center K-means algorithm are compared with the clustering results that are obtained via the K-means algorithm, which demonstrates the advantages of the self-organizing-center K-means algorithm that is based on the adjustment potential index in the accurate recognition and accurate clustering of users.

Highlights

Power resources are characterized by plug-and-play performance and the inability to be stored in large amounts
The core process of the self-organizing-center K-means algorithm is as follows: First, the data are entered into the self-organizing map (SOM) network for initial clustering, and the objects with approximation values on the selected clustering standard are aggregated near feature points to obtain the preliminary accurate clustering result
ANALYSIS OF POWER USAGE BASED ON THE SELF-ORGANIZING-CENTER K-MEANS ALGORITHM Two major types of user electricity behavior clustering analysis methods are employed in this paper: direct clustering analysis that is based on user daily load data and clustering analysis that is based on adjustment potential indicators

Summary

Introduction

Power resources are characterized by plug-and-play performance and the inability to be stored in large amounts. The core process of the self-organizing-center K-means algorithm is as follows: First, the data are entered into the SOM network for initial clustering, and the objects with approximation values on the selected clustering standard are aggregated near feature points to obtain the preliminary accurate clustering result.

Results

Conclusion