Papers by Author: Feng Kong

Abstract: TOPSIS has been in use for more than 20 years in many fields. However, few researches have studied its defect of rank reversal. This paper, by studying the fundamental cause for the rank reversal problem in TOPSIS, put forward an improvement on TOPSIS based on the decision maker’s subjective preferences, which can, proved by a numerical example, overcome the rank reversal problem and lead to more scientific decision result that is in more agreement with the decision makers’ subjective intensions.

Abstract: This paper describes the main contents of the evaluation of technical efficiency of electric power industry at home and abroad, the evaluation methods, and the development of it, and conducts an empirical analysis of the technical efficiency of the Grid in North China for the first time. This paper introduces the DEA to evaluate the technical efficiency of the Grid Corporations, and application of PSO to optimize on the DEA model. From the results of the evaluation of the technical efficiency of Sample Grid Corporation of China, We can conclude that you can better evaluate the technical efficiency of power companies by the combination of two ways, and can make clearer on their own to improve non-efficiency factors, thus conduct a comprehensive monitoring in the technical indicators and management indicators

Abstract: Due to the variety and the randomicity of its influencing factors, the electricity demand forecasting is a difficult problem for a long time. In order to improve the forecast accuracy, the paper proposes a new load forecast model based on GM(1,1) and support vector machine. First, the GM(1,1) is used to forecast the load data in the model. And then according to factors and historical load vector, support vector machine load forecast model is established to forecast the residuals of GM(1,1) and modified the forecast results of GM(1,1). Case analysis shows that the forecast method is suitable and effective, improving prediction precision compared with GM(1,1) and support vector machine, and has better utility value in mid-log term load forecast.

Abstract: According to the features of stock price change, a new forecast model, based on the regression analysis and SVM, is proposed to solve the problem of the stock price prediction. First, the regression analysis model is used to forecast stock prices, and then SVM was established to forecast and correct the error. The combined predictive values are obviously better than single method. Empirical analysis shows that the stock price based model based the regression analysis and SVM model significantly improved the forecast accuracy, it shows that the method in this paper is worth to be extended and applied.