About this role
To combat climate change and achieve the UK's target of Net Zero, it is expected that the integration of renewable energy sources (RESs) at the distribution/consumption level will keep increasing. The volatile and intermittent nature of RESs causes significant difficulties for the network operator to balance generation with demand and maintain power quality, which makes the network prone to instability and blackouts. In addition to their volatile nature, RESs cannot provide the ancillary services (such as voltage and frequency control) that conventional synchronous generators naturally deliver, exacerbating the situation as the penetration of RES increases, especially at the distribution level.
In this context, microgrids (MGs) refer to clusters of consumers, prosumers (consumers + producers), energy storage systems (ESSs), and electric vehicles (EVs) that collectively form a local energy community (EC). ECs are supposed to facilitate direct peer-to-peer (P2P) energy trading mechanisms to optimize objectives such as reduced bills, reduced emissions, or minimization of the exchanged energy with the grid. Such ECs can also potentially provide ancillary services to the grid, such as power balancing, peak shaving/shifting, voltage and frequency support, and virtual inertial response.
Due to the volatile and intermittent nature of RESs, in this project, machine learning (ML) methods are used to accurately forecast local generation and demand. To do so, historic local data (e.g., the active buildings in Swansea University) and Met Office data will be used to train and validate the proposed ML model. These forecasted data will then be used to propose and optimize an energy management strategy for an EC comprising a number of prosumers, consumers, ESSs, and EVs. Different vehicle-to-home and vehicle-to-community energy trading strategies will also be proposed and investigated to achieve optimized P2P trading within the EC.
The project will be done using MATLAB coding and modelling in Simulink environment.
Funding:
Covers full tuition, £20,780 stipend (2025/26), plus an enhanced stipend payment of £3000 per annum
Please apply via the ‘Apply’ button above.