A £2m project is underway to create a simulation of the South East’s electricity network which will allow more low carbon technologies to be installed.
UK Power Networks’ Envision project will use a first of its kind machine learning based software tool to help simulate how power is moving through its networks across London, the South and South East of England.
Collecting data about what is happening on the company’s network at any given time will provide the ‘visibility’ required to meet the growth in low carbon technologies like heat pumps and EV chargers.
UKPN believes Envision could release almost 70MW of electricity capacity by 2028, which will remove the need to physically upgrade the network to release capacity. This could lead also to savings of up to £4m over the next five years.
There are over 150,000 electric cars and 20,000 heat pumps in UKPN’s catchment area, but company analysis forecasts over 2.6 million electric vehicles and 712,000 heat pumps by 2030.
Envision’s new predictive models will combine UKPN’s data with external and real-time data from monitoring devices connected to substations. The machine learning algorithm will create a simulation of the electrical load in specific areas and expand it across the entire network. Engineers will compare the simulation to real life physical monitors; providing the software more and better data over time to increase the accuracy of the algorithm.
According to Simone Torino, head of product and business development at collaboration partner CKDelta, the aim of Envision is to generate a ‘virtual sensing network’ that uses advanced data capabilities and machine learning to simulate the behaviour of the network at scale, accurately estimating changing network load profiles.
He added that the uptake of new distributed energy resources and the increasing electrification of transport are impacting electrical demand and distribution network constraints.
Envision runs until August 2022 and will be delivered in two work packages. UKPN expects Envision to provide new insights into its Low Voltage (LV) network by establishing software tools that can be used for forecasting, which will assist forward planning and strategic investments.