Preliminary research on power demand model of high energy consumers for smart grid in China

With development of smart grid, study of power demand model of high energy consumers becomes an important topic in China. As a result of preliminary research, initial power demand model of high energy consumer is built up based on data mining. Such a model opens out the relationship of power demand and market factors, which can be applied to demand side management (DSM) for high energy consumers under Chinese market environment. A power demand forecasting method based on consumer classification and high energy consumer demand model is proposed. Such a model can also be applied to strategy making in DSM. Case study is carried out with real-life data from Guiyang city power grid where a large percentage of power demand is that from high energy consumers mainly consisting of phosphor plants and electrolytic aluminum plants. Case study results shows that demand forecasting precision is improved significantly and quantitative DSM strategies for high energy consumers can be made based on the proposed model.

[1]  R.E. Brown,et al.  Impact of Smart Grid on distribution system design , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

[2]  L. Varga.  Medium term electric load forecasting using artificial neural networks , 1999, PowerTech Budapest 99. Abstract Records. (Cat. No.99EX376).

[3]  Zhang Bo-ming.  A COMBINED MODEL FOR SHORT TERM LOAD FORECASTING BASED ON MAXIMUM ENTROPY PRINCIPLE , 2005 .

[4]  A. Paice,et al.  ADDRESS - Active Demand for the smart grids of the future , 2008 .

[5]  Chong-Ho Choi,et al.  Input Feature Selection by Mutual Information Based on Parzen Window , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Sp Power.  APPLICATION OF DEMAND SIDE MANAGEMENT TO CHINA , 2001 .

[7]  Guo Qinglai.  Hybrid Mutual Information Based Feature Selection Method as Appied To Static Voltage Stability Assessment in Power Systems , 2006 .

[8]  Tommy W. S. Chow,et al.  Estimating optimal feature subsets using efficient estimation of high-dimensional mutual information , 2005, IEEE Transactions on Neural Networks.

[9]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[10]  C. Gellings.  The special section on demand-side management for electric utilities , 1985 .

[11]  Sun Hong.  PG-HMI:Mutual Information Based Feature Selection Method , 2007 .

[12]  Wei-Jen Lee,et al.  Neural network based demand forecasting in a deregulated environment , 1999 .

[13]  C.W. Gellings,et al.  The concept of demand-side management for electric utilities , 1985, Proceedings of the IEEE.