Metaheuristics and especially Swarm Intelligence represents one of the mostly used aspect of Artificial Intelligence. In fact, these algorithms are exploited in several domains from theoretical problem solving to air traffic management. The evaluation of such methods is defined by the quality of solution they provide or effectiveness and the spent time to reach this solution or efficiency. We explore, in this paper, the technology offered by the Graphic Processing Unit -GPU- to improve the efficiency of the Bees Swarm Optimization algorithm -BSO- by proposing a novel and parallel CPU/GPU version of the later algorithm. The algorithm being greedy when the problem size is important, which is almost always the case. The proposed parallel algorithm is integrated in the proposed method of clustering-solving hard problems presented in [1], adding the exploitation of GPU performance to that of data mining to improve the resolution of hard and complex problems such as Satisfiability problem.
CITATION STYLE
Hireche, C., & Drias, H. (2020). A parallel CPU/GPU bees swarm optimization algorithm for the satisfiability problem. In Advances in Intelligent Systems and Computing (Vol. 1160 AISC, pp. 564–573). Springer. https://doi.org/10.1007/978-3-030-45691-7_53
Mendeley helps you to discover research relevant for your work.