A Multiagent Genetic Algorithm for Global Numerical Optimization

Abstract

In this paper, multiagent systems and genetic algorithms are integrated to form a new algorithm, multiagent genetic algorithm (MAGA), for solving the global numerical optimization problem. An agent in MAGA represents a candidate solution to the optimization problem in hand. All agents live in a latticelike environment, with each agent fixed on a lattice-point. In order to increase energies, they compete or cooperate with their neighbors, and they can also use knowledge. Making use of these agent-agent interactions, MAGA realizes the purpose of minimizing the objective function value. Theoretical analyzes show that MAGA converges to the global optimum. In the first part of the experiments, ten benchmark functions are used to test the performance of MAGA, and the scalability of MAGA along the problem dimension is studied with great care. The results show that MAGA achieves a good performance when the dimensions are increased from 20-10,000. Moreover, even when the dimensions are increased to as high as 10,000, MAGA still can find high quality solutions at a low computational cost. Therefore, MAGA has good scalability and is a competent algorithm for solving high dimensional optimization problems. To the best of our knowledge, no researchers have ever optimized the functions with 10,000 dimensions by means of evolution. In the second part of the experiments, MAGA is applied to a practical case, the approximation of linear systems, with a satisfactory result.

A Review on Multi-Agent Technology in Micro-Grid Control

“…A Multi-Agent Genetic Algorithm is carried out in [44] , emulation results indicates that this method outperforms generatl genetic algorithms in calculation quality. Detailed information and implementation of genetic algorithm can be found in [45] . Direct particle swarm is utilized in [46,47] for economic dispatch.…”

Agent Based Evolutionary Dynamic Optimization

“…In the first competitive method [40], the information of L i,j and L max is utilized together to generate an offspring L i,j . It randomly chooses some position that L i,j differs from L max to alter the corresponding position in L i,j .…”

“…This promising technique is particularly attractive for solving operational problems in business and logistics environments, such as the production planning problems, transportation and distribution problems, and resource allocation problems [10,10,18,23]. Zhong et al [40] integrated agent systems with Genetic Algorithms(GAs) to form a new algorithm for solving the global numerical optimization problem.…”

Sequential multi-criteria feature selection algorithm based on agent genetic algorithm

“…Therefore, good search algorithm is essential for feature selection method. Here, four genetic algorithms including AGA [31], MAGA [32], SFGA [33] and SGAE [34] are adopted to be compared with CAGA within SMFCS. The reasons for choosing these genetic algorithms are: firstly, SGAE is a traditional genetic algorithm with elitism strategy, and it has been used in various areas and performs well, so it is suitable to be compared with other improved genetic algorithms.…”

“…Fourthly, MAGA is an improved genetic algorithm with lattice-like agent population structure proposed recently. In [32], the MAGA is described to perform better than some well-known algorithms such as OGA/Q, AEA, FEP, BGA, so the comparison with it can show CAGA better performance over those genetic algorithms indirectly. This group of experiments is conducted to show the satisfying search capability of CAGA for feature selection.…”