Hour-ahead wind power prediction for power systems using Hidden Markov Models and Viterbi Algorithm
- 1 July 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
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
This publication has 32 references indexed in Scilit:
- Entropy and Correntropy Against Minimum Square Error in Offline and Online Three-Day Ahead Wind Power ForecastingIEEE Transactions on Power Systems, 2009
- Wind Power Density Forecasting Using Ensemble Predictions and Time Series ModelsIEEE Transactions on Energy Conversion, 2009
- Application of wavelet and neural network models for wind speed and power generation forecasting in a Brazilian experimental wind park2009
- High Order Neural Networks for wind speed time series prediction2009
- One day ahead wind speed forecasting using wavelets2009
- Forecasting the Wind Generation Using a Two-Stage Network Based on Meteorological InformationIEEE Transactions on Energy Conversion, 2009
- Grey Predictor for Wind Energy Conversion Systems Output Power PredictionIEEE Transactions on Power Systems, 2006
- A Simplified Wind Power Generation Model for Reliability EvaluationIEEE Transactions on Energy Conversion, 2006
- One-hour-ahead wind speed prediction using a Bayesian methodology2006
- Application of wind speed forecasting to the integration of wind energy into a large scale power systemIEE Proceedings - Generation, Transmission and Distribution, 1994