Title :
Hour-ahead wind power prediction for power systems using Hidden Markov Models and Viterbi Algorithm
Author :
Jafarzadeh, Saeed ; Fadali, Sami ; Evrenosoglu, Cansin Yaman ; Livani, Hanif
Author_Institution :
Electr. & Biomed. Eng. Dept., Univ. of Nevada Reno, Reno, NV, USA
Abstract :
This paper presents a new stochastic method for very short-term (1 hour) wind prediction in electrical power systems. The method utilizes Hidden Markov Models (HMM) and the Viterbi Algorithm (VA). Past wind farm power production data are required to develop the HMM model. The accuracy of the predictions improves drastically if hourly weather forecast data are used as pseudo-measurements. Computer simulations using Northwestern weather recordings from the Bonneville Power Administration (BPA) website show good correlation between our predictions and the actual data.
Keywords :
hidden Markov models; maximum likelihood estimation; wind power plants; Bonneville Power Administration website; HMM; Northwestern weather recordings; VA; Viterbi algorithm; computer simulations; electrical power systems; hidden Markov models; hour-ahead wind power prediction; short-term wind prediction; stochastic method; wind farm power production data; Hidden Markov Model; Viterbi; power system operation; statistical analysis; wind forecasting; wind power prediction;
Conference_Titel :
Power and Energy Society General Meeting, 2010 IEEE
Conference_Location :
Minneapolis, MN
Print_ISBN :
978-1-4244-6549-1
Electronic_ISBN :
1944-9925
DOI :
10.1109/PES.2010.5589844
