Genetic and Swarm Optimization for Effective Planning of Microgrids

Planning of microgrids has been a difficult problem, due to the fact that this planning requires considerations of different kinds of loads, channels and sources. Due to such a complex structure, it is recommended to use machine learning algorithms to solve the planning issues. In this paper, we have demonstrated the design of a genetic algorithm and a particle swarm optimization algorithm for planning of micro-grids. This planning takes into consideration the standard 26-bus system as proposed by the American Electric Power Association (AEPA). Results indicate that Genetic Algorithm outperforms Particle Swarm Optimization in terms of planning. Thereby GA must be used for planning of micro-grids as it improves the power and load performance by more than 10%