No abstract

During the past few years, research in applying machine learning (ML) to design efficient, effective, and robust metaheuristics has become increasingly popular. Many of those machine learning-supported metaheuristics have generated high-quality results and represent state-of-the-art optimization algorithms. Although various appproaches have been proposed, there is a lack of a comprehensive survey and taxonomy on this research topic. In this article, we will investigate different opportunities for using ML into metaheuristics. We define uniformly the various ways synergies that might be achieved. A detailed taxonomy is proposed according to the concerned search component: target optimization problem and low-level and high-level components of metaheuristics. Our goal is also to motivate researchers in optimization to include ideas from ML into metaheuristics. We identify some open research issues in this topic that need further in-depth investigations.

INTRODUCTIONHill-climbing, simulated annealing and genetic algorithms are search techniques that can be applied to most combinatorial optimization problems. In this paper, the three algorithms are used to solve the mapping problem: optimal static allocation of Communicating processes (tasks, objects, agents) on distributed memory architectures.Each algorithm is independently evaluated and optimized according to its parameters. The parallelization of the algorithms is also considered. As an example, a massively parallel genetic algorithm is proposed for the problem, and results of its implementation on a 128-processor Supemode (reconfigurable network of transputers) are given.A comparative study of the algorithms is then carried out. The criteria of performances considered are the quality of the solutions obtained and the amount of search timeIn this paper, we are interested to the mapping problem: optimal static placement of communicating processes on the processors of a distributed memory parallel machine.The problem is known to be NP-complete [Garey79].Consequently, heuristic methods shall be used. They may find only approximations of the optimum, but they will do it in a "reasonable" amount of time.Heuristic algorithms may be divided in two main classes. First, the general purpose optimization algorithms independent of the given optimization problem and, on the other hand, the heuristic approaches especially designed for the mapping problem. As we want to avoid the intrinsic disadvantd,: of the algorithms of this second class (their limited applicability), this paper is only concerned with the first class of algorithms. used for several benchmarks. A hybrid approach consisting in a combination of genetic algorithms and hill-climbing is also proposed and evaluated.

No abstract

No abstract