Batch and sequential forecast models for photovoltaic generation
Faranak Golestaneh, Hoay Beng Gooi · 2015
The worldwide increase in the integration of photovoltaic generation has necessitated improvements in the forecasting approaches. Two models are proposed to cater for PV generation forecasts for few minutes to several hours look-ahead times. A very fast and accurate prediction model based on extreme learning machine is deployed for day-ahead prediction. Moreover, an adaptive and sequential model is introduced for intra-hour and high frequency forecasting in the PV sites with highly intermittent generation and without availability of clouds forecasts. The efficiency of the proposed models are verified on three sites with different generation patterns and sampling resolutions.