Short-term Load Forecasting Based On Hybrid Intelligent Optimum Technology And Software Implementation

Power system load forecast, which is the base of power market technique supporting system, is an essential part of power system operation, control and planning. Short-term load forecast includes day load forecast and week load forecast. With the development of power system market and the power system automation, practical research of short-term load forecast is much more important.The dissertation consists of four parts as follows:(1) Based on the history data from a practical power system in some city, the characteristics of load data and influencing factors are analyzed. Based on statistics, "disorder data" can be removed and accurate and effective load forecasting can be ensured. The influencing factors are processed by normalization, and the conception of "similar degree" of characteristic variables is used for training data selection.(2) Three typical models (linear extrapolation model based on similar day, support vector machine model, combined forecasting model) were introduced.(3) It is considered that there is no model to forecast any day load exactly now, a new model based hybrid intelligent optimized technology was presented, that is tried to seek the best model for the forecasted day automatically. The model needs less experience of human experts. The application results indicated that precision is well, and has good performance.(4) Software of Short-term load forecasting has been developed.