An online distribution feeder optimal reconfiguration algorithm for resistive loss reduction using a multi-layer perceptron

This paper presents an online distribution feeder optimal reconfiguration algorithm for resistive loss reduction. Artificial neural networks (ANNs) were used to assure the application feasibility in real-time. The demand variation used during the ANN training is represented by samplings via Monte Carlo simulation. A consolidated heuristic algorithm is utilized to obtain the demand topologies. An integer formulation is used to guarantee the solution optimality from the initial solution supplied by the ANN. We also present the application of results to a demonstrative test system, indicating applications in real systems where topological alterations are required