Machine-Learning-aided Optimal Transmission Switching
The design of new strategies that exploit methods from Machine Learning to facilitate the resolution of challenging mathematical optimization problems has recently become an avenue of promising research. In this paper, we propose a novel learning approach to assist in the solution of a well-known optimization problem in power systems: The Direct Current Optimal Transmission Switching (DC-OTS). The DC-OTS problem takes the form of a mixed-integer program, which is NP-hard in general. Its solution has been approached by way of exact and heuristic methods. The proposed approach in this paper leverages known solutions to past instances of the DC-OTS problem to speed up the mixed-integer optimization of a new unseen model. Although it does not offer optimality guarantees, the numerical experience shows that it features a very high success rate in identifying the optimal grid topology (especially when compared to alternative competing strategies), while rendering remarkable speed-up factors.
Keywords: Machine Learning Mathematical Optimization Mixed-Integer Programming Optimal Transmission Switching Optimal Power Flow