期刊：
Lecture Notes in Electrical Engineering,2014年237 LNEE:325-333 ISSN：1876-1100
通讯作者：
Zhao, Y.(gsxl666@163.com)
作者机构：
[Zhao Y.] School of Electric Engineering, University of South China, Hunan, China;[Zhang Y.] Eastern Boiler Control Company Limited, Shenzhen, China;[Heguo Hu] Statistical Bureau of Hengyang City, Hunan, China
会议名称：
2013 International Conference on Mechatronics and Automatic Control Systems, ICMS 2013
会议时间：
10 August 2013 through 11 August 2013
会议地点：
Hangzhou
会议论文集名称：
Mechatronics and Automatic Control Systems
关键词：
Electric load forecasting;Electric power systems;Genetic algorithms;Radial basis function networks;Adaptive crossover and mutation probabilities;Gradient Descent method;Load forecasting;Power system operations;Pre-mature convergences;Radial basis function neural networks;Radial basis functions;Short term load forecasting;Iterative methods
通讯机构：
[Zhao, Yuhong] U;Univ South China, Inst Elect Engn, Hengyang, Hunan, Peoples R China.
会议地点：
Jilin, PEOPLES R CHINA
会议主办单位：
[Zhao, Yuhong;Cheng, Wei] Univ South China, Inst Elect Engn, Hengyang, Hunan, Peoples R China.^[Zhao, Xuecheng] Shaoyang Vocat & Tech, Dept Elect Engn & Mech, Shaoyang, Hunan, Peoples R China.
会议论文集名称：
Advanced Materials Research
关键词：
Chaos;Particle swarm;Short term load forecasting;Support vector machines
摘要：
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.
期刊：
Information Technology Journal,2013年12(21):6475-6480 ISSN：1812-5638
通讯作者：
Zhao, Y.
作者机构：
[Sheng Y.; Zhao Y.] School of Electric Engineering, University of South China, Hengyang, Hunan, China;[Lei L.] Institute of Environmental Protection and Safety Engineering, University of South China, Hengyang, Hunan, China
通讯机构：
[Zhao, Y.] S;School of Electric Engineering, University of South China, Hengyang, Hunan, China
作者机构：
[Zhao, Yuhong; Liao, Yanguo; Hu, Heping; Wang, Xiaofeng] Univ South China, Sch Elect Engn, Sch Math & Phys, Hengyang 421001, Hunan, Peoples R China.
会议名称：
2013 International Conference on Frontiers of Environment,Energy and Bioscience(ICFEEB 2013)
会议时间：
2013-10-24
会议地点：
Beijing,China
摘要：
In order to improve the efficiency of photovoltaic systems, under different temperature and irradiance conditions, intelligent control techniques for the tracking of the maximum power point were investigated in this paper. Against the problem of Step length selection of the traditional duty ratio perturbation algorithm, a duty ratio perturbation based on genetic algorithm is proposed. It is shown the excellent features of the modified algorithm by simulating this algorithm with MATLAB/SIMULINK software.
期刊：
International Journal of Applied Mathematics & Statistics,2013年48(18):347-355 ISSN：0973-1377
作者机构：
[Hu H.] School of Mathematics and Physics, University of south China, Hengyang, 421001, Hunan, China;[Zhao X.] Mechanical and Electrical Engineering Department, Shaoyang Vocational and Technical College, Shaoyang, 422000, Hunan, China;[Zhao Y.] School of Electric Engineering, University of south China, Hengyang, 421001, Hunan, China
摘要：
It is difficult to merge wind power into grid, owing to wind power's uncertainty and prediction inaccuracy. Wind speed is an important factor affecting wind power, so the accuracy of wind speed prediction has a major impact on the wind power prediction. The support vector machine (SVM) has been successfully applied in the short-term wind speed forecasting field, but its learning and generalization ability depend on 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 particles swarm optimization (PSO) algorithm in order to cope with the problems such as low search speed and local optima. Finally, we used it to optimize the support vector machines of short-term wind speed forecasting model. Through the analysis of the 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.
期刊：
Nature Environment and Pollution Technology,2013年12(4):569-575 ISSN：0972-6268
作者机构：
[Zhang Y.] Mechanical and Electrical Engineering Department, Shenzhen Polytechnic, Shenzhen, 518057, Guangdong, China;[Zhao Y.; Guang J.] School of Electric Engineering, University of South China, Hengyang, 421001, Hunan, China
摘要：
Large-scale integration of wind power has brought profound challenge to traditional power generation dispatch. It becomes necessary to effectively coordinate the operation of wind power and traditional power sources. Traditional economic dispatch tominimize the fuel cost no longer meets the need for environmental protection when emission reduction is mandatory. Based on the optimal dispatch in traditional power system, the concept of "energy-environmental efficiency" was introduced to modify the optimal dispatch model in wind power integrated system, and the multi-objective optimal dispatch model was proposed on the basis of comprehensively considering the minimum of the resource consumption, the best energy-environmental efficiency and the highest system stability. A hybrid particle swarm and simulated annealing optimization algorithm with fuzzy technology was presented to solve the optimization model. Compared with traditional economic dispatch, the model proposed in this paper is reasonable and can better protect the ecological environment.
期刊：
Information Technology Journal,2013年12(14):2719-2725 ISSN：1812-5638
通讯作者：
Zhao, Y.
作者机构：
[Zhao Y.] School of Electric Engineering, University of South China, Hengyang, 421001, Hunan, China;[Zhao X.] Mechanical and Electrical Engineering Department, Shaoyang Vocational and Technical, Shaoyang, Hunan, China
通讯机构：
[Zhao, Y.] S;School of Electric Engineering, , Hengyang, 421001, Hunan, China
期刊：
International Journal of Applied Mathematics & Statistics,2013年41(11):246-254 ISSN：0973-1377
通讯作者：
Zhao, Y.
作者机构：
[Hong, Zhennan; Zhao, Yuhong] School of Electric Engineering, University of south China, Hengyang, 421001, Hunan, China;[Hu, Heping] School of Mathematics and Physics, University of south China, Hengyang, 421001, Hunan, China
通讯机构：
[Zhao, Y.] S;School of Electric Engineering, , Hengyang, 421001, Hunan, China
