- Machine learning used to study wind and solar patterns
- Research will reduce electricity costs
- Benefits include a more reliable and stable electricity grid
“Natural variations in weather makes it difficult for renewable generators to accurately forecast their short-term power generation levels and this impacts grid stability.” said Denis Marshment, Global Vice President – Data Science Customer Solutions, Worley.
It’s the perpetual challenge of generating clean energy, but a Monash University collaboration with industry may have an answer to the issue.
The research project commenced in October 2018 between Monash University’s Grid Innovation Hub, Worley and Palisade Energy, looking into the use of machine learning technology to accurately predict wind and solar power.
Specifically, it aimed to provide wind and solar power generators with more accurate and reliable five-minute ahead self-forecasting tools.
Researchers said increasing the reliability of forecasting also means a more stable and reliable grid.
“Renewable energy cannot be produced on demand, as it is bound to natural resources such as the wind and sun. Therefore, in order to achieve a stable network and enough power generation, we need a reliable short-term prediction method,” said Monash University’s Dr Chritoph Bergmeir.
“By introducing machine learning methodologies to this short-term forecasting process we’re able to apply algorithms that are trained on historical time series data,resulting in the accurate forecasting of wind and solar energy.”
Dr Chritoph Bergmeir, Monash University
There are financial benefits beyond the obvious too, Mr Marshment said, “Our forecasting solution provides immediate value to our existing renewables customers as they target lower FCAS (Frequency Control Ancillary Services) charges.”
FCAS is a payment made by generators resulting from the failure to meet forecast targets.
Not only does the research have the potential to reduce electricity bills but, “It would also make renewables more competitive, which is also a desirable outcome,” said Dr Bergmeir.
