Final colloquium Bob van der Woude

Learning-Based Control of Microgrids with Transformers and Model Predictive Control

Supervisor: Prof.dr.ir. Bart De Schutter

In the evolving landscape of energy systems, microgrids have emerged as a key solution for enhancing energy efficiency and sustainability. Capable of operating independently or alongside the main power grid, microgrids integrate renewable energy sources and ensure local energy distribution.This makes them instrumental in reducing dependencies on centralised power supplies and improving resilience against disruptions.This research addresses the unit commitment problem, a mathematical optimisationchallengewhere the objective is to coordinate a group of energy production units to meet demand at minimal cost. We model the microgrid as a mixedlogicaldynamical(MLD)system, incorporating both the continuous and discrete variables involved in the microgrid. Model Predictive Control (MPC) is selected as the control strategydue to its suitability for solving the unit commitment problem, controllinghybrid systems, andits ability to handle complex constraints.

However, the application of MPC is challenged by the need to solve computationally demanding mixed-integer linear programming (MILP)problems at each control iteration, which are combinatorial. This research proposes integrating a learning-based method to enhance MPC in microgrids to address this challenge.Weproposeusing transformers to learn and predictthe binary decisions in MILP, thereby reducing the problem to a more tractable linear programming(LP)problem.Transformers are particularlychosen fortheir ability to recognise patterns in sequential data, a key aspect of the decision-making process in MPC. Furthermore, their capability for parallel processing allows for more efficient training and scalabilityto larger problems, making them highly suitable for handling the dynamic and complex optimisation tasks found in microgrid control.Simulation experiments show that the integration reducesthe computational load with only a slight loss of optimality and, therefore, improves the online applicability of MPC in microgrid control.