A Local Search Algorithm Based on Clonal Selection and Genetic Mutation for Global Optimization

Abstract

The purpose of this paper is to show a local search algorithm mixing features of Hill-Climbing, Clonal Selection and Genetic Algorithms. Hill climbing is considered because only the best solution is used. Clonal Selection because the best solution is cloned. Afterwards, individuals are muted using random mutation or non-uniform mutation of genetic algorithms. Four different ways of producing neighborhood solutions have been used in the mutation operator. In the first one (HR), the number of elements are randomly chosen based on the current generation number and muted using random mutation in a certain domain. In the second one (HNU), the number of elements are randomly chosen and muted using non-uniform mutation. In the third one (HRNU), the number of elements are chosen in the same previous way, however the random mutation is used in the initial generations and non-uniform mutation is applied in the last generations. Finally (HNURT), a random number of the elements are muted based on the current generation number, using non-uniform mutation. The performance of the hybrid algorithms is evaluated by means of six multimodal benchmark functions. The results show that HNU and HNURT have better performance. A comparison between the hybrid algorithms and traditional ones, such as, evolutionary strategies, genetic algorithms, particle swarm optimization and differential evolution is presented, as well.

A Parametric Framework for Cooperative Parallel Local Search

“…For instance, a mechanism where the probability of a configuration being selected from the EP is tied to its cost. We may even create a mutation mechanism on the EP, inspired in genetic algorithms [25,5], aspiring to improve the quality of the current configurations.…”

Maintenance strategies for wireless sensor networks: from a reactive to a proactive approach

“…In this step, each offspring allele is flipped by CPMS, with a probability p m , to a random maintainer robot identity. The mutation probability is typically chosen between 1 ∕ ( population size ) and 1 ∕ ( chromosome length ) . In Figure , we present an example of the selection, crossover and mutation operators used by CPMS strategy.…”

Symbol Mapping Optimization for Cooperative Systems with a Hybrid Search Algorithm

“…Thus, more efficient optimization techniques should be employed to improve the system performance with the use of uniform constellations. In this context, this paper proposes the use of a hybrid search algorithm [11], which uses genetic mutation and clonal selection to perform the symbol mapping optimization on uniform constellations.…”

“…The hybrid algorithm combines three search techniques to improve its performed: hill-climbing, clonal selection and genetic algorithm. It was originally proposed in [11] and aims to improve the quality of the solutions found by combining the best features of each of the three techniques: the choice of the best solution for the next generation from the hillclimbing algorithms; the cloning of the best solution from the clonal selection algorithm; and the mutation operation from the genetic algorithms. This algorithm belongs to a class of solutions of optimization problems called evolutionary strategies, since it is based on the process of natural evolution of the species to search for satisfactory solutions Similarly to the genetic algorithms [13], in the hybrid algorithm each solution in the search space should be encoded as a chromosome.…”

“…To reduce the search space of the signal constellations optimization problem, different heuristics have been proposed in the literature [6], [8], [9] considering uniform constellations (i.e., equally spaced points) and non-uniform constellations. In this context, this paper proposes the use of a hybrid search algorithm [11], based on clonal selection and genetic mutation, to perform the optimization of the symbol mapping on uniform constellations. The performance evaluation of the technique has shown that a good performance is achieved when compared to other approaches outlined in the literature.…”