Identyfikatory
Warianty tytułu
Hybrydowe połączenie funkcji PSO i RVM jako narzędzie do krótkoterminowego prognozowania obciążenia sieci energetycznej
Języki publikacji
Abstrakty
This paper presents a new hybrid method for the short-term load forecasting in electric power systems based on particle swarm optimization (PSO) and relevance vector machine (RVM). In this method, we firstly develop a type of kernel as the kernel function of the RVM model, and then its parameter is optimized by the PSO, finally the established RVM forecast mode is applied to short-term load forecasting in electric power systems in a city. The simulation results show the parameter of the wavelet kernel is well optimized using the PSO, and the acquired RVM model is more sparse and can obtain higher forecast accuracy compared with the RVM model with Gaussian kernel, so the proposed method is effective for forecasting the short-term load in electric power systems.
W artykule zaprezentowano nową hybrydową metode krótkoterminowego prognozowania obciążeń sieci energetycznej bazująca na algorytmie mrówkowym PSO i narzędzia RVM (relevance vector machine). W pierwszym etapie wyznaczane jest falkowe jądro (kernel) jako RVM co znacznie poprawia skuteczność algorytmu PSO.
Wydawca
Czasopismo
Rocznik
Tom
Strony
146--149
Opis fizyczny
Bibliogr. 10 poz., rys., tab., wykr.
Twórcy
autor
autor
- College of Hydropower, Hebei University of Engineering, Handan 056021, China, 2000wangly@163.com
Bibliografia
- [1] Md. Khairul Hasan†, Mohammad Asif A Khan, Suman Ahmmed, Ahmed Yousuf Saber. An Efficient Hybrid Model to Load Forecasting. International Journal of Computer Science and Network Security, (2010)10:8, 61-68
- [2] Yongli Wang, Dongxiao Niu, Xiaoyong Ma. Optimizing of SVM with Hybrid PSO and Genetic Algorithm in Power Load Forecasting. Journal of Networks, VOL. 5, NO. 10, (2010)5:10,1192-1200
- [3] Belousov AI, Versakov SA, Von Frese J. A flexible classification approach with optimal generalization performance: support vector machines. Chemon. Intell. Lab. Syst. (2002)64, 15–25
- [4] Belousov AI, Versakov SA, Von Frese J. Application aspects of supports vector machines. J. Chemom., (2002)16, 482–489
- [5] Abdulaziz Alshareef. Next 24-Hours Load Forecasting for the Western Area of Saudi Arabia Using Artificial Neural Network and Particle Swarm Optimization. Journal of Engineering and Computer Sciences, (2010)3:2, 97-117
- [6] Tipping ME. The relevance vector machine. Advances in Information Processing System, (2000)2, 652-658
- [7] Kennedy, J., Eberhart, R.C. Particle swarm optimization. Proc. IEEE Int'l. Conf. on Neural Networks, (1995), 1942-1948
- [8] Noslen Hernández, Isneri Talavera, Angel Dago, Rolando J. Biscay, Marcia M. Castro Ferreira, Diana Porro. Relevance vector machines for multivariate calibration purposes. Chemometrics, (2008)22, 686–694
- [9] YANG Liu1, ZHANG Lei, ZHANG Shaoxun, LIU Jianwei. Comparison Research of Single Kernel and Multi-kernel Relevance Vector Machine, Computer Engineering, (2010)36:12,195-197
- [10] Pan Duan, Kaigui Xie, Tingting Guo,Xiaogang Huang. Short- Term Load Forecasting for Electric Power Systems Using the PSO-SVR and FCM Clustering Techniques. Energies, (2011) 4, 173-184
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-article-BPOB-0049-0033