This project focuses on combining and linking data from multiple sources to reduce energy use and support the development of new services, firms and business models.

At a glance

Energy system modelling has been driven, at best, by annual data series at national or regional level. The roll-out of smart meters, along with the increasing availability of new forms of user data from crowdsourced platforms - such as social media, mobile phones and apps - offers an immense opportunity to improve our understanding of consumer's energy behaviours and preferences. It also allows us to see in near real-time and at a low geographical resolution the UK's changing energy mix.

Combining this data with that collected from other non-energy domains and the use of techniques like machine learning and hierarchical analytic methods means that future energy system research can recognise tripping points, emerging patterns, interdependencies and end-user behaviours in near real time. Beyond creating a world leading, state-of-the-art research programme, generating such insights is important both for industry and policy.

Understanding consumer demand patterns and the evolution of the UK’s energy mix in near real time would enable a more effective operation of the networks in a future energy system supplied by intermittent renewable resources. This is particularly important as the trajectory of this low carbon transition is highly uncertain, as characterised by a large number of future energy system scenarios.

Moreover, combining and linking data from multiple sources can support the development of new services, firms and business models. These new approaches can help develop a more nuanced policy approach to respond to consumer behaviours, whilst utilising differences across the energy system in terms of diversity of actors (including suppliers, prosumers, network operators), socio-economic, geographic and network characteristics, demand patterns and interdependencies of energy sector with other sectors such as transport. This is crucial; otherwise we risk widening existing socio-economic differences and tipping points, leading to major bottlenecks on the networks and exacerbating social inequalities.