Effects of population size and relative elitism on optimization speed and reliability of genetic algorithms
نویسندگان
چکیده
A good selection of the internal parameters of a genetic algorithm may reduce the optimization speed considerably. We studied the effects of two key parameters, namely population size and relative elitism, on the optimization speed and reliability. We found that changing one parameter can be compensated for changing another. By penalizing for the unreliability of the genetic algorithm the optimum combination of the parameters shifted. By using a meta-GA we found relationships between the total population size, relative elitism, and the penalty parameter.
منابع مشابه
Participative Biogeography-Based Optimization
Biogeography-Based Optimization (BBO) has recently gained interest of researchers due to its simplicity in implementation, efficiency and existence of very few parameters. The BBO algorithm is a new type of optimization technique based on biogeography concept. This population-based algorithm uses the idea of the migration strategy of animals or other species for solving optimization problems. t...
متن کاملGENETIC AND TABU SEARCH ALGORITHMS FOR THE SINGLE MACHINE SCHEDULING PROBLEM WITH SEQUENCE-DEPENDENT SET-UP TIMES AND DETERIORATING JOBS
This paper introduces the effects of job deterioration and sequence dependent set- up time in a single machine scheduling problem. The considered optimization criterion is the minimization of the makespan (Cmax). For this purpose, after formulating the mathematical model, genetic and tabu search algorithms were developed for the problem. Since population diversity is a very important issue in ...
متن کاملKinetic Mechanism Reduction Using Genetic Algorithms, Case Study on H2/O2 Reaction
For large and complex reacting systems, computational efficiency becomes a critical issue in process simulation, optimization and model-based control. Mechanism simplification is often a necessity to improve computational speed. We present a novel approach to simplification of reaction networks that formulates the model reduction problem as an optimization problem and solves it using geneti...
متن کاملOptimal Reconfiguration of Distribution Network for Power Loss Reduction and Reliability Improvement Using Bat Algorithm
In power systems, reconfiguration is one of the simplest and most low-cost methods to reach many goals such as self-healing, reliability improvement, and power loss reduction, without including any additional components. Regarding the expansion of distribution networks, communications become more complicate and the number of parameters increases, which makes the reconfiguration problem infeasib...
متن کاملFormation of manufacturing cell using queuing theory and considering reliability
In this paper, a stochastic cell formation problem is studied using queuing theory framework and considering reliability. Since cell formation problem is NP-Hard, two algorithms based on genetic and modified particle swarm optimization (MPSO) algorithms are developed to solve the problem. For generating initial solutions in these algorithms, a new heuristic method is developed, which always cre...
متن کامل