Nowcasting based on spatio-temporal string-level power measurements in utility-scale photovoltaic power plants

A novel method is proposed to estimate cloud motion vectors (CMVs) from endogenous photovoltaic (PV) power plant energy yield time-series data. The method is tested using three months of 1-min mean aggregated power output data collected from 8000+ string-sets in a 150+ MW p PV power plant. The CMVs are used as input to a cloud speed persistence PV power forecast which is benchmarked against a smart persistence PV power forecast. Forecasts issued for the entire power plant achieve an overall forecast skill of 0.16 at a forecast horizon of 1-min. If the forecast is issued for smaller sections of the power plant with foresight provided by the remaining sections, an increase in forecast skill up to 0.47 is demonstrated. The results emphasize the potential that can be unlocked if highly resolved spatio -temporal energy-yield time-series data are coupled with exogenous data, for instance, captured through satellite imagery and all-sky imagers. • A novel method estimates cloud motion vectors (CMVs) from string-level PV power measurements. • The method is tested using 1-min data from 8000+ string-sets in a 150+ MW p PV plant. • CMVs enable cloud-speed persistence forecasting of PV power output. • Plant-level forecasts achieve a skill score of 0.16 at a 1-min horizon. • Sub-plant forecasts with foresight show improved skill and potential of coupling with satellite/ASI data.