This is the Final Report for Advisian’s Short-term Forecasting project, Application of Advanced Short Term Power Generation Forecasting. It discusses the project datasets, forecast model performance, benefits from the project, key lessons learnt, and future work.
Report extract
Advisian is a participant in the ARENA funding initiative for improving 5-minute ahead self- forecasting for wind and solar farms operating in the National Electricity Market (NEM). Advisian partnered with Monash University and Palisade to develop the forecasting models. Both Models are machine learning models which draw on SCADA data as inputs to the model.
Two semi-scheduled generators were chosen for the study. The Waterloo Wind Farm (WWF) in South Australia, comprising thirty-seven V-90 and six V-117 Vestas Wind Turbines with a total installed capacity of 130.8 MW, and the 116 MW Ross River Solar Farm (RRSF) in Queensland.