My main research focuses on developing and applying data driven methods to industry problems, often where there is limited data or a lack of domain knowledge. These applications have been right across power systems from generation (nuclear, solar and wind), through networks (both transmission and distribution) out to end use and supply. The resulting software solutions have been used to automate and predict condition assessment, detect anomalous conditions and simulate future behaviours to support asset management and future planning business objectives. Translating this to other fields, I was co-founder of the spin out company Silent Herdsman Ltd, who developed an intelligent precision livestock management platform for the dairy industry.
I am currently principal investigator on the EPSRC funded Analytical Middleware for Informed Distribution Networks (AMIDiNe) project working to develop data driven power systems models that provide a more accurate view of uncertainties surrounding loads on unmonitored distribution networks in order to better inform where barriers to Net Zero may exist. Previously, I was an investigator on the EU FP7 Orchestrating Renewable Integrated Generation in Neighbourhoods (ORIGIN) project and co-investigator on the EPSRC BuildTEDDI Aging Population Attitudes to Sensor Controlled Home Energy (APAtSCHE), Aggregators as diGital Intermediaries in Local Electricity markets (AGILE) and Transactive Energy Supply Arrangements projects.
AMIDiNe sets out its analytics objectives in 3 interrelated areas, those of understanding how to incorporate analytics into existing network modelling strategies, how go from individual to group demand behavioural anticipation and the inverse problem: how to understand the constituent elements of demand aggregated to a common measurement point.
Current research broadly involving Smart Metering focuses on speculative developments of future energy delivery networks and energy management strategies. Whether the objective is to provide customer analytics or automate domestic load control, the primary issue lies with understanding then acting on these data streams. Challenges that are presented by customer meter advance data include forecasting and prediction of consumption, classification or segmentation by customer behaviour group, disambiguating deferrable from non-deferrable loads and identifying changes in end use behaviour.
Moving from a distribution network with enhanced visibility to augmenting an already 'smart' transmission system will need understanding of how lower resolution and possibly incomplete representations of the distribution network(s) can inform more efficient operation and planning for the transmission network in terms of control and generation capacity within the context of their existing models. Improving various distribution network functions such as distribution system state estimation, condition monitoring and service restoration is envisaged to utilise analytics to extrapolate from the current frequency of data, building on successful machine learning techniques already used in other domains. Strategic investment decisions for network infrastructure components can be made on the back of this improved information availability. These decisions could be deferred or brought forward in accordance with perceived threats to resilience posed by overloaded legacy plant in rural communities or in highly urbanised environments; similarly, operational challenges presented by renewable penetrations could be re-assessed according to their actual behaviour and its relation to network voltage and emergent protection configuration constraints.