The innovative new project explores the potential for artificial intelligence to help improve the forecasting method used by the grid for solar generation.
Partnering with non-profit start-up Open Climate Fix (OCF) the National Grid Electricity System Operator (ESO) aims to create a first-of-its-kind prediction model for its national control room. The tool, called “nowcasting”, analyses satellite images to calculate where sunlight will fall on solar panels based on cloud movement. Rather than relying on current technology, which can only give predictions limited to days ahead, this machine learning model aims to provide accurate information about the future minutes and hours. This system of “nowcasting” has historically been used for rainfall prediction, however, the OCF and ESO believe a similar approach can also be used to predict sunlight.
Recent developments in machine learning in the ESO’s control room have already improved solar forecast accuracy by 33%. However, short-term swings in solar generation due to cloud cover have been impossible to predict, requiring the ESO to keep reserve power on the grid to respond to unexpected changes in supply or demand. Typically, this takes the form of flexible gas plants that pollute heavily and are expensive. A more confident forecast of solar output could, therefore, reduce the number of carbon-emitting generators held in reserve and lead to savings in balancing costs. Additionally, a more efficient system would greater benefit consumers and aid the shift to a net-zero system.
Carolina Tortora, Head of Innovation Strategy and Digital Transformation at National Grid ESO, stated: “Accurate forecasts for weather-dependent generation like solar and wind are vital for us in operating a low carbon electricity system. The more confidence we have in our forecasts, the less we’ll have to cover for uncertainty by keeping traditional, more controllable fossil fuel plants ticking over.”
Co-founded by former DeepMind researcher Jack Kelly, OCF recently received a £500,000 award for its solar power forecast technology from Google.org as part of its Impact Challenge on Climate programme. “We’re over the moon to be collaborating with one of the world’s most innovative system operators – National Grid ESO,” said Kelly. “We plan to adapt the amazing work done by the global machine learning community to solar electricity forecasting. All our work will be open-source, so others will be free to use the technology to help reduce emissions globally as rapidly as possible.”
To speak to a member of the team regarding your energy efficiency requirements, please do get in touch:
Call: 01252 560 373