National Grid ESO has teamed up with the University of Sheffield’s PV_Live initiative to map out ‘invisible’ solar panels and improve its forecasting.
The project is aimed at improving forecasting through data captured from a network of solar PV on thousands of residential and commercial buildings, as well as ground-mounted systems in fields, the system operator said.
PV_Live mines both Sheffield’s Microgen database and a data stream from energy tech firm PassivSystems to get generation data from a sample of systems for a given half-hourly settlement period. This is then scaled up to show representative real-time PV performance across the country.
Forecasting is big on the system operator’s agenda, having boosted the accuracy of its irradiance forecasting by 33% through a new AI-based method developed in conjunction with the Alan Turning Institute earlier this year.
A separate forecasting method utilising AI and Internet of Things-styled technology was launched by Meniscus earlier this month.
The importance of mapping out the UK’s ‘invisible’ solar panels was recently highlighted after distribution network operator Western Power Distibution discovered around 15,000 solar installs and electric vehicles previous unknown to the distribution network operators as part of The Low Carbon Technologies Detection Project.
The PV_Live initiative is funded through Ofgem’s Network Innovation Allowance, much like the ESO’s project with the Alan Turning Institute.
Kevin Tilley, project manager for the ESO, said the data from PV_Live is “critical” to the management of the transmission system.
“We use the PV data to help forecast and monitor the national power requirements on the network in real time, and shortly after the first delivery of the data, we were able to improve our forecasts of these flows for the first time in years.”