Study of Daily Peak Load Forecasting by Structured Representation on Genetic Algorithms for Function Fitting - The local system with the local power generation facilities

摘要

In recent years, the user who introduces the small-scale power generation facilities (Solar photovoltaic generation, wind power generation, micro gas turbine, and fuel cell) increases with the power system deregulation. Electric power system becomes more and more complication. Therefore, we thought that the electric power demand forecasting was required in order to operate economically and high efficient. This paper presents a method of short-term load forecasting by STROGANOFF (i.e. STructured Representation On Genetic Algorithms for NOn-linear Function Fitting). The STROGANOFF is a hierarchical technique of multiple regression analysis method and GA-based search strategy that approximate the value of predictive to the future data by the past data is obtained. Considering local information, the examination was carried out using the electric demand data of this campus with the power generation facilities.