Research On Particle Swarm Optimization In Fuzzy Control Of Power System

Control theory is a branch of engineering and mathematics, that deals with the behavior of dynamical systems. The desired output of a system is called the reference. When one or more output variables of a system need to follow a certain reference over time, a controller manipulates the inputs to a system to obtain the desired effect on the output of the system. Artificial intelligence (AI) is the intelligence of machines and the branch of computer science. Someone defines the field as "the study and design of intelligent agents," where an intelligent agent is a system that perceives its environment and takes actions which maximize its chances of success. John McCarthy defines it as "the science and engineering of making intelligent machines." The field was founded on the claim that a central property of humans, intelligence can be so precisely described that it can be simulated by a machine. Artificial intelligence has become an essential part of the technology industry, providing the heavy lifting for many of the most difficult problems in computer science. Intelligent control is a class of control techniques, that use various intelligence approaches like neural networks, fuzzy logic, evolution computation.Particle swarm optimization (PSO) is an algorithm modeled on swarm intelligence that finds a solution to an optimization problem in a search space, or model and predict social behavior in the presence of objectives. The PSO is a stochastic -based computer algorithm modeled on swarm intelligence. Swarm intelligence is based on social-psychological principles and provides insights into social behavior, as well as contributing to engineering applications. The particle swarm optimization algorithm was first described in 1995 by James Kennedy and Russell C. Eberhart. The PSO belongs to the class of direct search methods used to find an optimal solution to an objective function in a search space. Direct search methods are usually derivative-free, meaning that they depend only on the evaluation of the objective function. The particle swarm optimization algorithm is simple, in the sense that even the basic form of the algorithm yields results, it can be implemented by a programmer in short duration, and it can be used by anyone with an understanding of objective functions and the problem at hand without needing an extensive background in mathematical optimization theory.Power system is a complicated large system and it is getting larger. The researchers of power system are facing with more and more parameters optimization and system control problems. With the rising of dependence on power of society, it is getting more important to insure the power system being safe, economic and stable. We prefer less controlling parameters and optimization method. Decentralized controllers is designed and optimized for multi-area overlapping interconnected power system so that the quality of power system frequency is ensure and the plan bargain exchanging power of tie line is abided. Particle Swarm Optimization and its application to parameter optimization in interconnected power systems are discussed in this thesis. Firstly, Particle Swarm Optimization algorithm is discussed and some progresses are made for the algorithm. PSO is fast to converge, but it has some disadvantages as low precision at the early stage, being easy to divergent, all the particle tending to be the same activity at the later stage, which makes the speed of convergence slow. At the same time, when the algorithm is convergent with some precision, optimum searching will not continue. Aiming at overcoming the disadvantage of being weak at local searching which use the method of linear inertia, many improved strategies such as initialization strategy with distributing uniformity, and the mutation of particle position and velocity decrease the probability of dropping into the local optimum point, increase the optimization speed sharply. The last, a fuzzy control strategy based on Particle Swarm Optimization and neural network controller combining particle swarm algorithm is applied into the load frequency control, which is with the ability of self-control. Stimulation result shows that optimized controller has improved dynamic response to the stochastic load disturb.So, in thesis, the coevolution method, initialization uniformly and mutation are combined into a whole frame to solve multi-dimensional optimization problems. Finally the future work and direction are pointed out.