Research On Simulated Annealing Support Vector Machines Algorithms And Its Application In Electricity Load Forecasting

Accurate forecasting of electricity load has been one of the most important issues in the electricity industry. Recently, along with power system privatization and deregulation, accurate forecast of electricity load has received increasing attention. With the power system becoming more and more complex, it's demonstrated that those traditional load-forecasting technologies can't satisfy the requirement of load forecasting which becomes more and stricter. So using new technologies to accuracy, move the forecasting accuracy and stability of the load forecasting of electric power system is a new character of the load forecasting field of electric power system.This thesis carries on to the meaning and actual states of Load forecasting to say all first, analyzing the characteristic of load and Load forecasting, tallying up composition and sorts and load periodic change regulations of load, analyzing every kind of factor of load of impact.Because of the general nonlinear mapping capabilities of forecasting, artificial neural networks have played a crucial role in forecasting electricity load. Support Vector Machine (SVM) is a new and very promising classification technique. The approach is systematic and properly motivated by statistical learning theory. Training involves separating the classes with a surface that maximizes margin between them. An interesting property of this approach is that it is approximate implementation of the Structural Risk Minimization (SRM} induction principle. Support vector machines (SVMs) have been successfully employed to solve nonlinear regression and time series problems. However, SVMs have rarely been applied to forecast electricity load. Based on the review of statistical learning theory and SVM history, we focused on the parameter selection of SVM in this work. Although having statistical learning theory as theoretical foundation, the performance of SVM does depend on the concrete parameters during the implementations. Moreover, simulated annealing (SA) algorithms were employed to choose the parameters of a SVM model. Subsequently, examples of electricity load data from America were used to illustrate the proposed SVMSA (support vector machines with simulated...