The Delicate Analysis of Short_Term Load Forecasting

[摘要] This paper proposes a new method for short-term load forecasting based on the similar day method, correlation coefficient and Fast Fourier Transform (FFT) to achieve the precision analysis of load variation from three aspects (typical day, correlation coefficient, spectral analysis) and three dimensions (time dimension, industry dimensions, the main factors influencing the load characteristic such as national policies, regional economic, holidays, electricity and so on). First, the branch algorithm one-class-SVM is adopted to selection the typical day. Second, correlation coefficient method is used to obtain the direction and strength of the linear relationship between two random variables, which can reflect the influence caused by the customer macro policy and the scale of production to the electricity price. Third, Fourier transform residual error correction model is proposed to reflect the nature of load extracting from the residual error. Finally, simulation result indicates the validity and engineering practicability of the proposed method.

[发布机构] Key Laboratory of Power System Intelligent Dispatch and Control, Ministry of Education, Shandong University, Jinan, China^1;State Grid Jiangxi Electric Power Company Jiujiang Electric Power Supply Company, China^2

[效力级别] 电工学

[关键词] Correlation coefficient;Correlation coefficient method;Electricity prices;Linear relationships;Load characteristics;Precision analysis;Scale of production;Short term load forecasting