A Method Based on K-Means and Fuzzy Algorithm for Industrial Load Identification

At present, electrical energy becomes more and more important, and the shortage of electrical energy becomes serious. In order to develop power efficiency and alleviate the problem, people have planned the methods of load identification. This paper is on the basis of many different kinds of methods, and used K-means classification and fuzzy algorithm. This kind of method also needs to store the templates in database in advanced, and compare the features of samples which are extracted from the experiment with templates. Then it utilizes K-means classification to classify and uses fuzzy algorithm to calculate the closeness degree of every cluster. The industrial environment is very complex. E.g. the number of load types, states, some interference factors etc. This method we proposed can handle large amount of data and has another key of advantage. It is the capability to identify major industrial loads accurately. The results are presented in this paper. All in all, industrial load identification needs to be consummated.

[1]  Xiaohua Xia,et al.  Active power residential non-intrusive appliance load monitoring system , 2009, AFRICON 2009.

[2]  A. Schoofs,et al.  Real-Time Recognition and Profiling of Appliances through a Single Electricity Sensor , 2010, 2010 7th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks (SECON).

[3]  Jian Liang,et al.  Automatic appliance load signature identification by statistical clustering , 2009 .

[4]  Friederich Kupzog,et al.  Automatic electric load identification in self-configuring microgrids , 2009, AFRICON 2009.

[5]  K. El Khamlichi Drissi,et al.  State of art on load monitoring methods , 2008, 2008 IEEE 2nd International Power and Energy Conference.

[6]  Jane Yung-jen Hsu,et al.  Applying power meters for appliance recognition on the electric panel , 2010, 2010 5th IEEE Conference on Industrial Electronics and Applications.

[7]  Hong-Tzer Yang,et al.  Design a Neural Network for Features Selection in Non-intrusive Monitoring of Industrial Electrical Loads , 2007, 2007 11th International Conference on Computer Supported Cooperative Work in Design.

[8]  Tohru Hoshi,et al.  A method of appliance detection based on features of power waveform , 2004, 2004 International Symposium on Applications and the Internet. Proceedings..

[9]  Mark Lucente,et al.  Exploration on Load Signatures , 2004 .