Research project ideas for students
We have developed a learning-augmented P2P–DSO interface that predicts the DSO’s response to the proposed P2P trades, allowing prosumers to self-assess and refine their trading decisions. A supervised transformer-based regression model is trained to enable MGs to locally predict the DSO’s response without sharing their proposed trades, thereby reducing transaction overhead, alleviating DSO burden, and preserving information privacy.
We have developed an advanced Machine Learning (ML)-based Load Forecasting Tool designed to assist distribution utilities in achieving better market planning and reduced DSM penalties. Currently, we are in the deployment phase of this tool with one of a utility in New Delhi.
Relevant work: <add paper 1 link>, <add paper 2 link>, <add paper 3 link>
We are developing a framework to utilize inverter-based distributed energy resources (DERs) to provide volt/var ancillary services to the grid. Thousands of smart DER devices can be seen as geographically distributed local VAR devices which have potential to enhance grid flexibility if aggregated and controlled properly. See this publication for preliminary results.
We are working on adaptive smart inverter controls for inverter based DERs to make their parameter selection self-adaptive in a wide range of operating conditions while ensuring the control stability and steady-state performance. See this publication for details.
We are developing a integrated transmission-distribution co-simulation platform to simulate realistic large-scale 3 phase unbalanced coupled T&D system using GridlabD and MATLAB interface. This platform will help us to assess true impact of DERs and active distribution systems on the grid performance.
We are also assessing the impact of DER and distribution system loadability limits on the long-term stability margin of the grid. See this publication for preliminary results.