Delft University of Technology researcher Bart De Schutter has been named a recipient of the EU’s ERC Advanced Grant. The grant, valued at 2.5 million euros, is being awarded for his work on smart controlled transportation and energy networks. According to the researcher, hybrid dynamics – the combination of both gradual and sudden changes in the networks – make these systems hard to control by traditional solutions, which are oversimplified and lacking a structured approach.
In his proposal, De Schutter lays out a two-pronged approach. First, using optimization-based control systems, where control actions are proposed and calculated to determine what the outcome should be. Based on that, new proposals are made, similar to what a chess computer does when calculating a new move. The second leg of his suggested approach utilizes a learning-based control. This method relies on self-learning systems that respond to a control action and, depending on whether the response is in the right direction or not, are rewarded or punished. Thus, they gradually learn what is the right approach.
According to De Schutter, the combined use of these two systems can greatly improve the energy and transportation networks. “Both methods have their advantages, but until recently, the combination proved difficult,” he describes. “I want to bridge this gap with the special knowledge and experience I have in both optimization-based control and learning-based decision-making. One of the key elements here are piecewise linear approximations to non-linear curves, as well as the development of models that can work with them and the smart use of the network structures that are already present.”