Search

A standard genetic algorithm is asexual. To mimic nature more closely, this paper incorporates gender in a genetic algorithm. Two individuals from opposite sex are permitted for reproduction. Earlier researchers considered that the gender of the offspring depends on the gender of the individual removed from the population. Thus the number of males and females are kept constant. This assumption was relaxed by introducing randomness during gender assignment to the offspring after the crossover operation. However, due to the stochastic nature of the process, this may generate a population of single sex which leads to no regeneration being possible. This paper introduces adaptive gender assignment to the offspring so that the gender of the offspring is decided based on the gender density in the population. The proposed algorithm is applied to design a pressure vessel. [ABSTRACT FROM AUTHOR]

In this paper, hybrid particle swarm optimization (PSO) is proposed for solving the challenging multi-contingency transient stability constrained optimal power flow (MC-TSCOPF) problem. The objective of this nonlinear optimization problem is to minimize the total fuel cost of the system and at the same time fulfil the transient stability requirements. The optimal power flow (OPF) with transient stability constraints considered is re-formulated as an extended OPF with additional rotor angle inequality constraints, which is suitable for hybrid PSO to solve. Comparison between various existing hybrid PSO techniques is carried out by solving the New England 39-bus system. Experimental results indicate that the hybrid PSO integrated with the mutation operation of genetic algorithms is better than the other existing hybrid PSO methods in both solution quality and stability. [ABSTRACT FROM AUTHOR]

This paper presents a detailed comparison between a conventional PI controller and a variable structure controller based on a fuzzy sliding mode strategy used for speed control in direct torque control induction motor drive. Genetic algorithms are used to tune the PI controller gains to ensure optimal performance. The performance of the two controllers are investigated and compared for different dynamic operating conditions such as of reference speed and for load torque step changes at nominal parameters and in the presence of parameter variation and imprecision. Results show that the PI controller has better performance for nominal operating conditions while the fuzzy sliding mode is more robust against parameter variation and uncertainty, and is less sensitive to external load torque disturbances with a fast dynamic response. [ABSTRACT FROM AUTHOR]

In this paper we used genetic algorithms to 1 find the solution of game theory. We proposed new method foe solving game theory and find the optimal strategy for player A or player B. We can benefit from the relationship between game theory and the linear programming to find the fitness function and tested this fitness function at different examples . [ABSTRACT FROM AUTHOR]

Particle Swarm Optimization (PSO) is a stochastic and population-based search algorithm that demonstrates its effctiveness in solving complex nonlinear optimization problems. Although the original PSO is very simple and effective, how to determine appropriate values of parameters in PSO is yet to be found. This paper proposes a novel method called evolutionary PSO, which estimates values of parameters in PSO for effectively finding globally optimal parameter values by a real-coded genetic algorithm. A crucial idea here is to adopt a temporary cumulative fitness instead of instantaneous fitness in a real-coded genetic algorithm for evaluating the performance of the PSO. It provides a useful measure that efficiently determines appropriate values of parameters in PSO. To demonstrate the effectiveness of the proposed method, we implement a simple computer experiment on a 2-dimensional optimization problem, and analyze the characteristics of dependency on initial condition. [ABSTRACT FROM AUTHOR]