Application of Adaptive PSO and GA Algorithms for Voltage Optimization and Reduction of Power Loss

Modern electric power systems (EPS) are complex, multiply connected, spatially separated hierarchical objects that function under conditions of the variability in their structure, parameters and operating modes under numerous external and internal disturbances, both systematic and random. The optimal management of normal EPS modes is to ensure a reliable supply of electricity to consumers with the required quality at minimum costs. Today we know a lot of optimization methods for various problems arising in the energy sector. This paper presents solving technical problems with the help of methods of artificial intelligence, fuzzy logic, artificial neural networks and evolutionary algorithms. The concept of Particle Swarm Optimization (PSO) is based on the use of decentralized systems consisting of many simple monotonous elements (agents), indirectly interacting with each other and with the environment. The genetic algorithm GA is a combined method in which two groups of optimization methods are combined: search and iterative. The results of calculation of electrical circuits allow us to assume that the developed adaptive PSO and GA algorithms are applicable for obtaining effective solutions to the problem of selecting optimal modes of the equipment operation in EPS.