Electricity Load Forecasting in Smart Grid Based on Residual GM (1, 1) Model
The construction of smart grid has put forward higher requirements on deployment accuracy of the energy. Power generation and electricity sectors have carried out more accurate data analysis and forecasting. In this context, a residual GM (1, 1) model is
- PDF / 116,051 Bytes
- 6 Pages / 439.37 x 666.142 pts Page_size
- 12 Downloads / 200 Views
Abstract The construction of smart grid has put forward higher requirements on deployment accuracy of the energy. Power generation and electricity sectors have carried out more accurate data analysis and forecasting. In this context, a residual GM (1, 1) model is proposed. This model can overcome the lack of traditional grey model and make accurate forecasting of electricity consumption in smart grid. Finally, numerical examples demonstrate that this method can efficiently improve the prediction accuracy. Keywords Smart grid • Electricity load forecasting • Residual GM (1, 1) model
1 Introduction Compared with the traditional power grid, smart grid is characterized by environmental protection, safety, efficiency, etc. Particularly, it assists decision-making, which is useful to the optimal allocation of power resource. Data of every terminal in power grid can be controlled real timely by advanced communication facilities in smart grid. According to the forecasting of electricity consumption, smart grid allocates electricity to make a balance between supply and demand of electricity, which realizes optimizing the usage of power energy. Prediction of too much electricity consumption will cause excess power generation and distribution. While prediction of too little electricity consumption will bring power cut due to lack of power supply, then arouse economic losses and social unrest. Therefore, it is of great significance to predict the power consumption accurately. That is to say, the prediction accuracy of electricity consumption determines the quality of smart grid.
J. Shen • H. Wang (*) • S. Yang Key Lab of Process Optimization and Intelligent Decision-making, Hefei University of Technology, Hefei, China e-mail: [email protected] W. Wang (ed.), Mechatronics and Automatic Control Systems, Lecture Notes in Electrical Engineering 237, DOI 10.1007/978-3-319-01273-5_106, © Springer International Publishing Switzerland 2014
941
942
J. Shen et al.
Data prediction ability determines the quality of smart grid. As for electricity consumption, low prediction will cause power cut due to lack of allocated electricity, while high prediction will bring unnecessary generation cost and energy waste. Therefore, it is essential to predict the electricity consumption accurately. One of the commonest electricity consumption prediction models is grey model- GM (1, 1) [1]. GM (1, 1) model can play a greater role in data forecast of smart grid. By use of its theory, prediction data accuracy can be improved to meet the requirement for data with high quality in smart grid. After 20 years of development, grey system theory has been widely applied in many areas, including social science and economics. Deng [1]created the grey system theory and system described the principle of grey system, the applications of grey system in many different fields, such as science and economy; Wang, Yang and Wang [2]used cubic spline formula to improve the background value, and constructed a novel grey forecasting model, they used this new model to f
Data Loading...
