USING THE SVR MODEL WITH THE HYBRID ALGORITHM TO PREDICT THE ELECTRICAL LOAD
- Authors
-
-
Assistant Lecturer. Huda Abdulsadah hashim
College of Administration and Economics, Department of Economics University of Basra, Basra, Iraq
Author
-
Prof. Dr. Sahera Hussein Zain
College of Administration and Economics, Department of Economics University of Basra, Basra, Iraq
Author
-
- Keywords:
- Support vector regression, Chaotic genetic algorithm, Chaotic particle swarm optimization algorithm.
- Abstract
-
Electrical load forecasting is an important topic in the planning and operation of power systems، It contributes to improving the efficiency of energy system management and future decision-making. Due to the nonlinear nature of the electrical load data, this study aimed to develop a prediction model based on the support vector regression (SVR) with two hybrid chaotic algorithms to optimize the selection of optimal parameters. The proposed models were compared using statistical accuracy criteria for predicting electrical load in the southern region of Iraq. The results showed that the supporting vector regression model with the chaotic genetic algorithm was superior in terms of accuracy and efficiency compared to other models.
- References
-
akkula, V. (2003). "Tutorial on Support Vector Machine (SVM)", School of EECS, Washington State University.
Chen،L.Y.; Hong،W.C.; Panigrahi،b. K.; and Wei ،S.Y. (2011). SVR with Chaotic Genetic Algorithm in Taiwanese 3G Phone Demand Forecasting،Part I, pp. (248– 256), Springer-Verlag Berlin Heidelberg.
Cheng, Y., Fu, Y., & Gong, G. (2010). "A Hybrid Support Vector Regression Based on Chaotic Particle Swarm Optimization Algorithm in Forecasting Financial Returns", School of Computer Science & Technology, Soochow University, China.
Hong, W. C., Dong, Y., Zhang, W. Y., Chen, L. Y. & Panigrahi, B. k. (2013). "Cyclic electric load forecasting by seasonal SVR with chaotic genetic
algorithm", International Journal of Electrical Power & Energy Systems, vol. 44,
Li, T., Yong.W., Zhi, GZ., Zhi, L., Chen, YG. (2014). "Short-Term Wind Power Prediction Based on Support Vector Regress Optimized by Chaos Particle Swarm Optimization", School of Electrical Engineering, Anhui Polytechnic University, China, pp (195-200).
Liu, B., Wang, L., Jin, Y. H., Tang, F. & Huang, D. X. (2005). "Improved particle swarm optimization combined with chaos", Chaos, Solitons & Fractals, vol.25, No. 5, pp (1261–1271).
Liu, Y., Qiao, N., Zhao, C., Zhuang, J. & Tian, G. (2018). "Using the AR–SVR–CPSO hybrid model to forecast vibration signals in a high-speed traintransmission system", College of Engineering and Technology, Jilin Agricultural University, China, pp (2-14), Part F: Journal of Rail and Rapid Transit.
Manurung, A.H., Suhartono, D., Hutahayan, B. & Halimawan, N. (2016). "Probability Bankruptcy Using Support Vector Regression", Management Department, Binus Business School, Bina Nusantara University.
Mishra, S. & Patra, S. K. (2008). "Short Term Load Forecasting Using Neural Network Trained with Genetic Algorithm & Particle Swarm Optimization", National Institute of Technology, First International Conference on Emerging Trends in Engineering and Technology, pp (606-611).
Perea, P. R., Ruiz, J. C., Chaparro, D.G., Venzor, J. A. P., Carreón, A.Q. & Rosiles J.G. (2013)."Support Vector Machines for Regression: A Succinct Review of Large-Scale and Linear Programming Formulations", International Journal of Intelligence Science, Vol. 3 No. 1, pp. (5-14).
Wang, Y. M., Zhang, Z., Zheng, J. B., & Tong, L. L. (2014). "Chaotic Genetic Algorithm for Mixed Integer Programming Problem", Applied Mechanics and Materials ,China ,vols. 651-653, pp(2273–2277).
Yan, X. F., Chen, D. Z. & Hu, S. X. (2003). "Chaos-genetic algorithms for optimizing the operating conditions based on RBF-PLS model",Computers & Chemical Engineering, vol. 27, No. 10, pp (1393–1404).
- Downloads
- Published
- 2026-09-03
- Issue
- Vol. 2 No. 9 (2026)
- Section
- Articles
- License
-
This work is licensed under a Creative Commons Attribution 4.0 International License.
