Wind energyProject Wind Forecasting for the NEM
The Fulcrum3D Wind Forecasting Lessons Learnt Report outlines the key learnings Fulcrum 3D has learnt in the period between October 2019 – April 2020.
- Our forecasting model continues to be more accurate than AWEFS such that it has passed AEMO’s accuracy requirements with respect to RMSE and MAE on 5-minute power production.
- MP5F API status for the three Pacific Hydro wind farms involved in this project:
- Clements Gap – submitting unsuppressed forecasts
- Taralga – submitting unsuppressed forecasts in the assessment phase o Crowlands – registered.
- Sodars have been installed at the prevailing upstream locations at all three wind farms and have demonstrated forecast windows of 30mins at site mean wind speeds.
- The MP5F API is increasingly robust. Further streamlining of the API connection process is an area for improvement.
- Overall forecast refinement is ongoing.
- Remote SCADA access is streamlining the forecast system (discussed further below).
- Pacific Hydro continue to be excellent project partners, we would like to acknowledge their invaluable contribution.
- There is currently minimal value in using forecasts for FCAS participation or export control but further increases in FCAS costs may strengthen the case for using forecasting for these services.
- Other completed activities:
- Accuracy assessment on forecasts to date
- Cost-benefit analysis for Clements Gap forecasts o Explored factors affecting accuracy
- Explored viability of other forecasts
- The project is on track to meet its outcomes.