A Scalable Ensemble Learning-Based Model for Optimal Placement of Circuit Breaker and Sectionalizer in Power Distribution Systems with the Aim of Reliability Improvement

The number and location of switching devices (e.g., circuit breakers and sectionalizers) should be optimally determined in power distribution systems to reduce system interruptions and associated costs. However, existing mathematical optimization algorithms, such as classic and metaheuristic methods, cannot solve the optimal switch placement problem for large-scale systems. In this paper, a scalable model is proposed based on machine learning methods to determine the optimal number and location of switching devices according to system conditions. This paper proposes employing ensemble learning methods and explainable artificial intelligence tools to build an accurate data-driven model. Consequently, power distribution operators can determine the optimal number and location of circuit breakers, remote-controlled sectionalizers, and manual switches in large-scale systems without mathematical optimization algorithms. To validate its accuracy and scalability, the proposed model and a classic-based model are implemented on a real power distribution system in Fars province. The numerical results demonstrate that the proposed data-driven model can find a solution close to the globally optimal solution quickly, using a limited range of system data.