Named the Envision project, UK Power Networks is simulating how power is travelling through its networks across London, the South and South East of England, allowing the company to have better view on how its network is performing. The distribution network operator (DNO) suggests that this added visibility could potentially unlock additional energy capacity equivalent to 1,371 new rapid electric car chargers by 2028.
Experts predict that Envision could release almost 70MW of electricity capacity by 2028, allowing for more EV chargers and low carbon heat pumps. The outcome means that engineers won’t need to physically upgrade the network to release capacity, saving up to £4 million in total over the next 5 years.
UK Power Networks is using machine learning to enable low-cost energy capacity increases and to aid in upgrading its networks to reach net zero. In fact, the firm has announced a £4.5 billion plan that will see its network decarbonised.
The company has more EV chargers connected than any other, and is still working to increase connections. Over the past year, it has seen connections of new EV chargers rise by 42%.
Envision is creating new predictive models that will combine UK Power Networks’ 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 develop it across the entire network. Engineers will then compare the simulation to the actual monitors, feeding the software more and better data so the algorithm becomes more precise.
Ian Cameron, head of customer services and innovation at UK Power Networks, said, “Our customers rightly expect us to do everything we can to make the switch to electric cars and low carbon heating as affordable as possible. Through Envision, we’re thinking outside the box and re-imagining traditional ways of working, to make it happen.”
Simone Torino at CKDelta, which is collaborating on the project, said: “The aim of the Envision model 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.”
Share
