Artificial intelligence (AI) could help manage local grids, to ensure that they are not overloaded by rapid growth in demand.
A pilot project run by Evergreen Smart Power, Energy Assets Networks and Myenergi, and backed with funding from Innovate UK, has now been launched to demonstrate how AI can safeguard network integrity.
Project DINO (Domestic Infrastructure and Network Optimisation) will be the first of its kind in the UK, and will see Evergreen Smart Power develop a two-way communication system. This will enable networks to communicate with devices like EV chargers, so that when the network is constrained, devices can be automatically turned down and the bandwidth managed.
The project will be run over two years at a new build housing scheme, where the consumption and flow of power will be monitored in real time at both the substation and feeder levels. The data collected will be combined with models of electric vehicle charging and heat pump usage, to help the group develop a new algorithm that would allow AI to manage the power.
Additionally the data will be used for a proof of concept for equipment capable of responding to system stress at a feeder level.
“There is growing realisation that local power networks may not be able to cope with the huge increase in demand for electricity as we transition to electric vehicles, battery storage/charging and air source heat pumps alongside traditional household appliances,” says Jayson Whitaker, managing director of Energy Assets Networks.
“The DINO project aims to demonstrate how a network-to-device AI interface can manage loads dynamically by enabling appliances to automatically dial down consumption at peak times to relieve network stress and safeguard power to homes. Without such a solution, the country would need to invest in a hugely costly network reinforcement programme to increase capacity.”
As the UK pushes towards net zero, there is likely to be a huge growth in the number of EVs and electrified heat solutions, such as heat pumps. In particular, given the upcoming ban on the sale of internal combustion engine vehicles which is likely to be brought forward to 2035 or sooner, more people are likely to turn to EVs.
While these are undoubtedly necessary steps for decarbonisation, they will increase the demand on the energy network significantly. For example, housing developments are currently only designed for an average peak load of 2kW per household. With the installation of heat pumps and EV charging, this could exceed 10kW, and as such poses a risk of power outages.
Beyond modelling for heat pumps and EV chargers, the project will be expanded to also examine the impact of domestic battery storage.
