A Hybrid Cross-Entropy Guided Genetic Algorithm for Scheduling Multi-Energy Systems

This investigation develops a novel hybrid fast converging Cross-Entropy Genetic Algorithm technique for scheduling of multi-energy system (MES). The scheduling problem is a mixed integer non-linear programming problem with non-linear and non-convex constraints, due to switching and non-linear dynamics exhibited by the MES devices. A hybridization of cross entropy and genetic algorithm termed as CE-mGA is proposed for the betterment of search space exploration as well as exploitation with fast convergence. In addition, a constraint-driven mutation strategy is also introduced in GA framework for tackling the non-linear and non-convex constraints. The investigation illustrates that the proposed algorithm is able to provide a stand-0ff between exploration and exploitation with an improvement in convergence speed than hybrid real-coded genetic algorithm upon validation at Cleantech building, Singapore.