Electric Load Movement Evaluation and Forecasting Based on the Fourier-Series Model Extend in the Least-Squares Sense

摘要

Analysis of electric load movement is of increasingly importance for the industry on both economic operation and control of power systems. From the perspective of time-series analysis, in this study, with daily periodic extension for hourly electric load movement, an evaluation model employing finite Fourier series is proposed for describing its movement. As the conventional Fourier analysis cannot be directly used for prediction, in conjunction with the least-squares method to obtain the optimum Fourier coefficients in the least-squares sense based on limited hourly load data observations, the proposed Fourier-series model is extended to predict the load future movement. Experiments and result analysis indicate potentiality of the proposed method. It is shown that daily 24-h load movement is well described by the proposed Fourier-series evaluation model with about 12-term harmonics, and the extended Fourier-series forecast model in the least-squares sense predicts its movement most fitting with about 4-term harmonics...