Swarm Intelligence with Clustering for Solving SAT

Swarm intelligence is a major research field that contributed these last years to solve complex problems. In this paper, we show that bio-inspired approaches augmented with data mining techniques such as clustering, may bring more efficiency to problem solving. In fact, we aim at exploring judiciously the search space before seeking for solutions and hence reducing the complexity of the problem large instances. We consider for this purpose the approach of Bee Swarm Optimization (BSO) and propose two ways to integrate clustering in it. The first one consists in incorporating clustering in the design of BSO. This leads us to suggest an advanced version of BSO. The second one performs clustering on the data before launching BSO. This proposal was implemented for the satisfiability problem known widely as SAT. The complexity of the problem is reduced in this case by clustering clauses and hence variables and afterwards solving the clusters that have a smaller number of variables.