Many evolutionary techniques such as genetic algorithms employ parameters that facilitate user control of search dynamics. However, these parameters require time-consuming tuning processes to avoid problems such as premature convergence. In order to solve the problem, in this study, we propose a novel technique ``analysis based on the Distribution of Inferior Individuals in the local neighborhood (DII analysis)''. First of all, we show the effectiveness of DII analysis, then we introduce DII analysis to Parameter-less Population Pyramid (P3) which is one of the excellent Evolutionary Computation and proposed the method as ``P3-DII''. The computational experiments were carried out taking several combinational problems as examples. According to our experimental results, we demonstrated that P3-DII found several optimal solutions that P3 failed to find.
This paper considers application of a particle swarm optimization algorithm to the maximum power point tracking in photovoltaic systems. The cost function of a terminal voltage is time-variant in dynamic environment and the voltage corresponds to a particle. Since the terminal voltage can take one value at an instant, it is difficult to construct plural particles. In order to overcome this difficulty, our algorithm uses imaginary particles consisting of sampled values of the terminal voltage. In order to adapt to the dynamic cost function, the algorithm uses a flexible reset method of the personal best. In order to escape from a trap of local solution, the algorithm accelerates particles periodically. Performing basic numerical experiments, the algorithm efficiency is investigated.
Evolutionary algorithms (EAs) are optimization algorithms inspired by biological evolution and have been widely applied for solving various optimization problems. When EAs are applied to solve optimization problems, it is very important to set adequate parameters taking into account the characteristics of an objective function. Among the characteristics of the objective function, landscape modality is particularly important. For example, if the landscape is unimodal, the efficiency of EAs can be improved by tuning control parameters to local search. In contrast, if the landscape is multimodal, the robustness of the EAs can be improved by tuning control parameters to global search. However, in a black-box optimization problem, the function is unknown. In this study, we propose a novel method that estimates the modality of landscape being searched: simple unimodal or not. In our method, two rankings according to the fitness and distance are given for each individual of EAs. Next, Spearman's rank correlation coefficient is calculated using the two rankings. The value of rank correlation coefficient becomes different, depending on the landscape modality. Using this feature, we classify the type of function modality being searched by population. Through experiments using basic benchmark problems, we show that the proposed method can correctly perform modality estimation.
This paper presents an analysis of an optimization process in asynchronous evolutionary algorithms from the viewpoint of influence of the relationship between characteristic of solutions and their evaluation time. An asynchronous evolutionary algorithm continuously evolves solutions without waiting for evaluations of other solutions, and consequently an asynchronous evolutionary algorithm is effective in the situation where the evaluation times of solutions differ from each other. This paper focuses on optimization problems in which the evaluation time of solutions depends on their characteristics. In particular, this paper considers two relationships; (a) the evaluation time relates to the evaluation value of solutions; and (b) the evaluation time relates to design variables of solutions. In each relationship, four correlation settings are defined; (1) uniform evaluation time setting where all solutions have the same evaluation time; (2) no-correlation setting where the evaluation time is not uniform but does not depend on characteristic of solutions; (3) positive correlation setting where the evaluation time increases by getting close to the optimal solution; and (4) negative correlation setting where the evaluation time increases by getting far awary from the optimmal solution. Experiments on the defined correlation settings are conducted on three conventional asynchronous evolutionary algorithms and four benchmark problems. The analytical results reveal the following implications; (1) in the case where the evaluation time relates to the evaluation value of solutions, when a lot of local optima exists in the search space such as multi-modal problems, a number of evaluations to escape from local optima is needed and the evaluation time of solutions close to local optima influences the computational time of search process. On the other hand, when it is hard to converge to the optimal solution, the evaluation time of solutions close to the optimal solution influences the computation time of search process; and (2) in the case where the evaluation time relates to the design variable of solutions, when the evaluation time of solutions decreases by getting close to the optimal solution, the computation time decreases because the search direction is biased toward the optimal solution.