Day-Ahead Short-Term Forecasting Electricity Load via Approximation

5th International Conference: Modern Technologies For Non-Destructive Testing

材料科学;物理学

Khamitov, R.N.^1 ; Gritsay, A.S.^1 ; Tyunkov, D.A.^1 ; Sinitsin, G.E.^2

Omsk State Technical University, Omsk, Russia^1

Electricity Markets Department, LLC, Omsk Energy Retail Company, Omsk, Russia^2

关键词: Electric power;    Electrical supply;    Function coefficients;    Metering devices;    Power supply company;    Short-term forecasting;    Sinusoidal functions;    Wholesale markets;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/189/1/012005/pdf
DOI  :  10.1088/1757-899X/189/1/012005

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

The method of short-term forecasting of a power consumption which can be applied to short-term forecasting of power consumption is offered. The offered model is based on sinusoidal function for the description of day and night cycles of power consumption. Function coefficients - the period and amplitude are set up is adaptive, considering dynamics of power consumption with use of an artificial neural network. The presented results are tested on real retrospective data of power supply company. The offered method can be especially useful if there are no opportunities of collection of interval indications of metering devices of consumers, and the power supply company operates with electrical supply points. The offered method can be used by any power supply company upon purchase of the electric power in the wholesale market. For this purpose, it is necessary to receive coefficients of approximation of sinusoidal function and to have retrospective data on power consumption on an interval not less than one year.