Short-term wind speed forecasting: Application of linear and non-linear time series models

ABSTRACT

This study forecasts day-ahead wind speed at 15 minute intervals at the site of a wind turbine located in Maharashtra, India. Wind speed exhibits non-stationarity, seasonality and time-varying volatility clustering. Univariate linear and non-linear time series techniques namely MSARIMA, MSARIMA-GARCH and MSARIMA-EGARCH have been employed for forecasting wind speed using data span ranging from 3 days to 15 days. Study suggests that mean absolute percentage error (MAPE) values first decrease with the increase in data span, reaches its minima and then start increasing. All models provide superior forecasting performances with 5 days data span. It is further evident that ARIMA-GARCH model generates lowest MAPE with 5 days data span. All these models provide superior forecasts with respect to current industry practices. This study establishes that employing various linear and non-linear time series techniques for forecasting day-ahead wind speed can benefit the industry in terms of better operational management of wind turbines and better integration of wind energy into the power system, which have huge financial implications for wind power generators in India.

KEYWORDS:

• India
• MSARIMA
• MSARIMA-EGARCH
• MSARIMA-GARCH
• renewable energy
• univariate time series models
• wind speed forecasting

Notes

¹ http://www.cea.nic.in/reports/articles/god/grid_disturbance_report.pdf

² http://www.imd.gov.in/section/nhac/dynamic/Met_Glossary.htm

³ http://www.imd.gov.in/section/nhac/dynamic/NWPMAHASEN13.pdf

⁴ Mean absolute percentage error (MAPE) of MSARIMA forecasting started increasing rapidly for data span more than 15 days.

⁵ We use EVIEWs software to run the models. Due to paucity of space, correlograms have not been incorporated in the text. Correlograms will be provided on request.