Evaluation of Competitiveness of Power Plants Based on Optimized SVM Using GA and AIS

Abstract

With the development of electricity market reformation in China, it is especially important to evaluate the competition competence of power generating enterprises. Based on the characteristics of their, this paper bring forwards an index system to evaluate the competition competence of power generating enterprises. SVMs are widely used in load forecasting and bioinformatics systems. Conventional methods are usually used in the parameter estimation process of SVMs. However, these methods can yield to local optimum parameter values. In this work, we use artificial techniques such as Artificial Immune Systems (AIS) and Genetic Algorithms (GA) to estimate SVM parameters. These techniques are global search optimization techniques inspired from biological systems. Also, the hybrid between genetic algorithms and artificial immune system was used to optimize SVM parameters to evaluate the competitivity of power plants.