Genetic algorithm heuristic parameters

Keywords Meta-heuristics Genetic algorithms Firefly algorithms Hybrid Cultivation process Identification Model parameters... 

Method for optimization of the maintenance activities in the NPP applying heuristics particle swarm method is presented. The maintenance activities are optimized in order to maximize the NPP safety. The optimization parameters are the test placement times of the safety systems components. The optimization of the maintenance activities applying genetic algorithm (GA) and simulated annealing (SA) is done in order to compare the obtained results with the results from the particle swarm method. 

For example, the first genetic algorithm that was developed specifically for the optimisation of solid catalysts relied on the following heuristic parameters (Wolf et al., 2000) ... 

Table 7.2. Values of the heuristic parameters of the genetic algorithm considered when investigating the influence of those properties on the convergence speed and diversity decrease of the algorithm.

Figure 7.3. Distribution of the number of combinations of the considered values of properties used as heuristic parameters, according to the generations in which the genetic algorithm fulfilled the three considered indicators of convergence.

Figure 7.4. Example illustrating the increase of the convergence speed of the genetic algorithm with population size. The values of the remaining heuristic parameters were probability of any modification = 90%, probability ratio qualitative mutation crossover = 1, asymptotic probability ratio quantitative mutation any modification = 0.05, coefficient of quantitative mutation = 10.

Figure 7.7. Convergence of the genetic algorithm for the combinations of values of heuristic parameters suggested in Table 7.5...

---