Research On The Application Of Artificial Intelligence Techniques In Short Term Load Forecasting In Power System

Based on the discussions of the conventional and recent methods of short term load forecasting such as time series,multiple regression approaches and artificial intelligence technologies,this paper presents a hybrid short term forecasting model which combines the artificial neural network (ANN) and Genetic algorithm (GA) .In order to improve the convergence speed and precision of the Back-propagation (BP),a new improved algorithm-the adapted learning algorithm based on quasi-Newton method is given. In order to improve the shortcoming of the BP-local convergence,which affects the efficiency,and precision of BP,we present an improved Genetic Algorithms. Then,a hybrid short-term load forecasting model is built by combining the above two algorithms. At last,based on the analysis of electric load,we build 24-hour forecasting models according the type of the date and the weather. With all above the discussions,we build the software. At the end of this paper,we applied it to a certain electric network and obtained a satisfied result.