Feeder Load Balancing Using Genetic Algorithms and Artificial Neural Network

Low voltage power distribution system problems such as planning, energy loss minimization and restoration usually involve proper load balancing or network reconfiguration procedures. To achieve an appreciable level of phase balance, feeder using appropriate switching control strategy as: Simulated Annealing, Tabu Search, Particle Swarm Optimization, heuristic algorithms are viable preferences. However, the systematic solution to can be greatly enhanced optimally through implementation combinatorial optimization procedure Genetic Algorithms Artificial Neural Network. Accordingly, this paper presents a genetic enhance then train artificial neural automate loads, thus ensuring optimal in system. An Intel® 2.0 GHz, 4GB RAM HP255 computer-based MATLAB® 14 was used for training, testing, algorithms. The outputs sequence balanced network. parameters ΔIph (max - min) Δ(Iph – Imax) which is maximum difference between currents, ideally zero if there no imbalances network, shows considerable improvement when compared with other literatures. This work application examples proposed methods real test data.