Swarm intelligence solution to large scale thermal power plant Load Dispatch

Economic Load Dispatch is one of the major functions of modern Energy Management System (EMS), which determines the optimal real power settings of generating units with an objective of minimizing the total fuel cost. All industrial practice, the fuel cost of generators can be treated as a quadratic function of real power generation. In fact, valve point loading effect in thermal power plants calls discontinuity. The classical optimization methods require continuous differentiable objective functions; therefore they fail to provide global minima. The evolutionary computation methods can handle non-differential and non-convex objective functions and give global or near global optimum solutions. Evolutionary techniques such as Genetic Algorithm (GA), Evolutionary Programming (EP) are applied to economic dispatch problem. Similar to evolutionary computation, social behaviour artificial intelligence called swarm intelligence is applied in many fields. Use of swarm intelligence not only avoids coding and monotonous decoding as prevalent transformations of GA and also results in less burden on parameter settings, population size and number of iterations. In this paper, swarm intelligence is applied to solve large scale economic load dispatch problem with valve point loading. Particle Swarm Optimization (PSO) algorithm is tested on a 13 and 40 unit test system. Results obtained show that PSO algorithm has a great potential in handling large size complex optimization problems and capable to produce results in very less time.