Title :
Aggregate static load modeling in power grid with environmental characteristics
Author :
Ao Pei ; Mu Long-hua
Author_Institution :
Sch. of Electron. & Inf. Eng., Tongji Univ., Shanghai, China
Abstract :
In practice, there are many defects that underground load model is built by using the traditional static load model in coal mine. To enhance the accuracy of load model, a new clustering method based on improved PSO algorithm is presented in this paper. This new clustering method is used to classify the load data in order to reduce the number of load model before modeling. Then, RBF neural network based on improved PSO algorithm is proposed to establish aggregate load model. Verified by an example, compared with traditional static load model, the method in this paper can greatly improve the accuracy of the model.
Keywords :
coal; environmental factors; mining; particle swarm optimisation; pattern classification; pattern clustering; power grids; radial basis function networks; RBF neural network; aggregate static load modeling; clustering method; coal mine; environmental characteristics; improved PSO algorithm; load data classification; power grid; underground load model; Aggregates; Algorithm design and analysis; Approximation algorithms; Clustering algorithms; Clustering methods; Data models; Load modeling; K-means clustering algorithm; aggregate static load model; particle swarm clustering algorithm; radial basis neural network; subtractive clustering algorithm;
Conference_Titel :
Power Engineering and Automation Conference (PEAM), 2011 IEEE
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-9691-4
DOI :
10.1109/PEAM.2011.6135049
