Title :
Short-term wind speed forecasting using Support Vector Machines
Author :
Pinto, Tiago ; Ramos, Sergio ; Sousa, Tiago M. ; Vale, Zita
Author_Institution :
GECAD - Knowledge Eng. & Decision Support Res. Center of the Inst. of Eng., Polytech. of Porto, Porto, Portugal
Abstract :
Wind speed forecasting has been becoming an important field of research to support the electricity industry mainly due to the increasing use of distributed energy sources, largely based on renewable sources. This type of electricity generation is highly dependent on the weather conditions variability, particularly the variability of the wind speed. Therefore, accurate wind power forecasting models are required to the operation and planning of wind plants and power systems. A Support Vector Machines (SVM) model for short-term wind speed is proposed and its performance is evaluated and compared with several artificial neural network (ANN) based approaches. A case study based on a real database regarding 3 years for predicting wind speed at 5 minutes intervals is presented.
Keywords :
electricity supply industry; load forecasting; neural nets; power engineering computing; power generation planning; renewable energy sources; support vector machines; weather forecasting; wind power plants; ANN; SVM model; artificial neural network; distributed energy sources; electricity generation; electricity industry; planning; renewable sources; support vector machine model; weather condition variability; wind power forecasting models; wind speed forecasting; Artificial neural networks; Forecasting; Kernel; Support vector machines; Wind forecasting; Wind power generation; Wind speed; Artificial neural networks; short-term forecasting; support vector machines; wind speed forecasting;
Conference_Titel :
Computational Intelligence in Dynamic and Uncertain Environments (CIDUE), 2014 IEEE Symposium on
Conference_Location :
Orlando, FL
DOI :
10.1109/CIDUE.2014.7007865
