Short-Term Load Forecasting And Its Application System Of Power System

With the development of Power Systems and Electricity Market, the management of modern Power Networks becomes more and more complete. The application of EMS (Energy Management System) has been widely applied. Short-term load forecasting (STLF) system is an important module of EMS and critical component of Electricity Market Operation System. Studying theory and algorithms of STLF and employing an effective and applicable STLF system are becoming an important task. The algorithms of STLF and its application software system are studied elementarily in this paper.According to characteristics of STLF, the Artificial Neural Network (ANN) model is introduced to STLF. It brings forward a new model based on Resource Distributing Network (RAN), whose characteristics and modeling course are discussed thoroughly. The model is first applied on the domain of STLF and is validated with a high precision by actual examples. Expert System is introduced to modify the results of RAN and has a higher precision in the thing of fluctuation of weather.According to the practical demands of electric department, a whole STLF system based on Dispatching Automation System for district power networks is successfully developed. The system integrating with Dispatching Automation System has advantage of real-time, economy and practicality. Client/Server mode is used in the system. MS SQL Server with safety and stability is employed as background database platform. Core program and GUI are developed by C++ Builder, which is an OOP and visual programming tool. Multiple methods, such as Least Mean Squares, linear regression, time series, similar day, artificial neural networks and their combination are integrated in the STLF system. Method library is coming into being. Abundant forecasting models and methodologies are provided to validate different forecasting results. It has been proved by practical data that this system can commendably satisfy demands of load forecasting of district power networks planning, and can present accurate future load magnitudes and increase planner's work efficiency, with friendly man-machine interfaces, convenient accesses and complete graphical functions.