An evolutionary algorithm and acceleration approach for topological design of distributed resource islands

In response to the ongoing discussion on how electric power distribution systems should evolve under the Smart Grid Initiative, an optimization problem is defined to simultaneously determine optimal locations for Distributed Generation (DG) and feeder interties in a legacy radial distribution system to improve reliability in the islanded mode of operation. For that purpose, an evolutionary approach using the Multi Objective Genetic Algorithm (MOGA) is formulated. The choice of an evolutionary algorithmic approach is justified due to the intractability of the problem associated with optimal location of DGs and feeder interties for large distribution systems. Furthermore, we present a filtering technique using machine learning (ML) for improving performance by avoiding expensive simulations for potentially suboptimal inputs. The algorithm is applied to a test system in which two methods of expressing the load are explored. In both cases, similar satisfactory design solutions are obtained.