Short-Term Wind Speed and Power Prediction Using Fuzzy Information Granulation-Support Vector Machine

Xiao Fu; Dong Xiang Jiang

doi:10.4028/www.scientific.net/AMR.608-609.814

Paper Titles

Adequacy Evaluation of Wind-PV-ES Hybrid Power System
p.790

Study on the Active Power Output Control of Wind Energy for Power Balance
p.796

Practical Calculation Method of Downburst Wind Profiles for Engineering Applications
p.803

Design and Implementation of Wind-Solar Hybrid Street Light Management System Based on ZigBee
p.808

Short-Term Wind Speed and Power Prediction Using Fuzzy Information Granulation-Support Vector Machine
p.814

Analysis on Operation Characteristics of Wind Source Heat Pump System
p.818

Assesment of Quality Classification of Green Pellets for Nuclear Power Plants Using Improved Levenberg-Marquardt Algorithm
p.825

Design on Optimization Database of Radiation Protection for Nuclear Facilities Maintenance
p.835

Parallel Particle-Grid Hybrid Method for Nuclear Power System Accident Analysis
p.839

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 608-609Short-Term Wind Speed and Power Prediction Using...

Short-Term Wind Speed and Power Prediction Using Fuzzy Information Granulation-Support Vector Machine

Abstract:

The power fluctuation of wind turbine often causes serious problems in electricity grids. Therefore, short term prediction of wind speed and power as to eliminate the uncertainty determined crucially the development of wind energy. Compared with physical methods, support vector machine (SVM) as an intelligent artificial method is more general and shows better nonlinear modeling capacity. A model which combined fuzzy information granulation with SVM method was developed and implemented in short term future trend prediction of wind speed and power. The data, including the daily wind speed and power, from a wind farm in northern China were used to evaluate the proposed method. The prediction results show that the proposed model performs better and more stable than the standard SVM model when apply them into the same data set.