Public Funding for Alian Ltd

The UK is committed to achieving Net Zero emissions by 2050 (BEIS, 2019). Achieving this requires extensive reconfiguration of our energy system from 'top-down' to 'bottom-up', integrating new low-carbon technologies (e.g. generation sources, electric vehicle charge points and heat pumps) and new energy services. One of the greatest challenges in achieving this transformation is poor visibility of the loads and capacity of the electricity grid, particularly in the last mile where a significant proportion of technologies need to be deployed (ESC, 2020).Farad AI (FAI) has developed an AI-powered digital-twin of the UK's electricity grid, providing stakeholders with significantly better visibility of energy demand and network constraints. The platform has integrated machine learning algorithms that model local energy demand to predict substation constraints. Our Phase II project builds on the work achieved in Phase I to improve our regional coverage, integrate new data sets and increase the accuracy of our model predictions. The project activities include significant additional user research / testing, front- and back-end development, DevOps and commercial exploitation.

Farad AI (FAI) has developed a digital twin of the UK's low voltage electricity grid at substation level, providing Low Carbon Technology project developers (such as electric vehicle charge point or renewable energy developers) with significantly better visibility of their grid connection opportunities. Based on customer research, business development activities to date and the research outputs of prior MEDA winners, our users would greatly benefit from the integration of a series of other non-energy datasets to provide them with a more holistic picture of their connection opportunities. Building on the work undertaken during by previous MEDA competition winners, we are proposing to integrate a series of new datasets into our platform to provide our users with visibility of the above variables. In doing so, we will enable our users to better assess connection probabilities and project risk.