A Research into Probabilistic Electricity Load Prediction Based on Demand Response Feature under Smart Grid Environment

Ning Lu; Ying Liu

doi:10.4028/www.scientific.net/AMM.380-384.3098

Paper Titles

Research of Heat Transfer Performance on Tablet Microstructure Heat Exchanger Used for LED Lamps
p.3082

Performance Comparison between HEV with Three Different Battery-Ultracapacitor Systems
p.3086

Application Boundary Element Approach to Compute the Electric Field Intensity of the Thirteen-Needle Electrodes in Vacuum
p.3089

Design of DVB-S2 LDPC Coder and Decoder Implemented in FPGA
p.3093

A Research into Probabilistic Electricity Load Prediction Based on Demand Response Feature under Smart Grid Environment
p.3098

Design of Large Consumer Electric Quantity Settlement System
p.3103

The Stability and the Computed Speed of Application Boundary Element Numerical Method to Compute the Electric Field Intensity Generated of One Hundred and Fifty-Needle Electrodes
p.3107

Study on Project of Photovoltaic Power Plant Connecting to the Grid
p.3111

Design of On-Chip Debug System Based on IEEE Protocol
p.3115

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 380-384A Research into Probabilistic Electricity Load...

A Research into Probabilistic Electricity Load Prediction Based on Demand Response Feature under Smart Grid Environment

Abstract:

The construction of grid plays an important role in national economic development, social stability and peoples life. In case that electricity market adopts real time electricity price, users active participation and real time response to electricity price will change the traditional load prediction from rigid forecasting to flexible forecasting which takes electricity demand response into consideration. By using wavelet analysis and error characteristics analysis, the researches into the probabilistic predicting method for demand changes under the real time electricity pricing is carried out. The probabilistic load prediction result shall enable decision makers to better understand the load change range in the future and make more reasonable decision. Meanwhile, it shall provide support to electricity system risk analysis.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 380-384)

Pages:

3098-3102

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.380-384.3098

Citation:

Cite this paper

Online since:

August 2013

Authors:

Ning Lu, Ying Liu

Keywords:

Confidence Level, Probabilistic Prediction, Real-Time Electricity Price, Short-Term, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Information on http: /www. smartgrids. eu.

Google Scholar

[2] C.Q. Kang，Q. Xai，M. Liu: Power system load forecasting (China Electric Power Press, Beijing 2007).

Google Scholar

[3] A. Allcott. Real time pricing and electricity markets, Working Paper, Harvard Univ. Feb. (2009).

Google Scholar

[4] Y. Zhang, Q. Zhou, C.X. Sun, S.L. Lei, Y.M. Liu, Y. Song . IEEE Transaction on Power Systems Vol. 23(2008), p.853.

Google Scholar

[5] V.N. Vapnik: The nature of statistical learning theory (Springer Press，New York 1995).

Google Scholar

[6] N. Lu, B.L. Wu, Y. Liu. Power system protection and control Vol. 39(2011), p.43.

Google Scholar

[7] W.J. Yang, C.Q. Kang, Q. Xia, et al. Automation of Electric Power Systems Vol. 30(2006), p.47.

Google Scholar

[8] R.C. Fang, J.Z. Zhou, Y.C. Zhang,　L. Liu. Huazhong Univ. of Sci. & Tech. Vol. 37(2009), p.125.

Google Scholar