The Application of Chaotic Particle Swarm Optimization Algorithm in Power System Load Forecasting

Abstract:

The support vector machine (SVM) has been successfully applied in the short-term load forecasting area, but its learning and generalization ability depends on a proper setting of its parameters. In order to improve forecasting accuracy, aiming at the disadvantages like man-made blindness in the parameters selection of SVM, In this paper, the chaos theory was applied to the PSO (particles swarm optimization) algorithm in order to cope with the problems such as low search speed and local optimization. Finally, we used it to optimize the support vector machines of short-term load forecasting model. Through the analysis of the daily forecasting results, it is shown that the proposed method could reduce modeling error and forecasting error of SVM model effectively and has better performance than general methods.

• Periodical: Advanced Materials Research (Volumes 614-615)
• Pages: 866-869
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.614-615.866
• Online since: December 2012
• Authors: Yu Hong Zhao, Xue Cheng Zhao, Wei Cheng
• Keywords: Chaos, Particle Swarm, Short Term Load Forecasting, Support Vector Machine (SVM)

References

[1] Sinha A K. In Proc IEEE internationalConference on IndustrialTechnology, 2000; 548—553

[2] AfzelNoore, Liang Tian. International Journal of Neural Systems, 2004, 14(5): 2342-2347.

[3] Cherkassky V, Ma Yunqian. Neural Networks,2004,17(1):113-126.

[4] Ding Junwe,i Sun Yaming. Automation ofElectric Power Systems, 2000: 32—35

[5] BashirZ A, El-Hawary M E. 2007 Canadian Conference on Electrical and Computer Engineering, CCECD, 2007: 272—275.