1. Research on Peak and Valley Periods Partition and Distributed Energy Storage Optimal Allocation Considering Load Characteristics of Industrial Park
- Author
-
Xianyan Zhang and Xianyun Li
- Subjects
Set (abstract data type) ,Mathematical optimization ,ComputingMethodologies_PATTERNRECOGNITION ,Fuzzy clustering ,business.industry ,Computer science ,Distributed generation ,Computer data storage ,Particle swarm optimization ,business ,Cluster analysis ,Fuzzy logic ,Partition (database) - Abstract
Time-of-use price is an important means of demand side management, how to accurately divide peak and valley periods is an important problem to be solved. In this paper, an improved fuzzy c-means (FCM) clustering algorithm is proposed to solve the problem that traditional FCM clustering algorithm is sensitive to the initial clustering center and easy to fall into local optimal. This algorithm combines an improved particle swarm optimization (PSO) based on support vector machine regression (SVR) with FCM algorithm, makes full use of the strong global search ability of PSO, replaces FCM to find the clustering center at the beginning of iteration, makes it out of the local optimal, realizes fuzzy clustering, and thus classifies more accurate peak and valley periods. Finally, the improved algorithm is applied to an example of an industrial park, and a distributed energy storage system is set up. The effectiveness of the proposed method is verified by simulation.
- Published
- 2021
- Full Text
- View/download PDF