Local termination criteria for Swarm Intelligence: a comparison between local Stochastic Diffusion Search and ant nest-site selection

Stochastic diffusion search (SDS) is a global Swarm Intelligence optimisation technique based on the behaviour of ants, rooted in the partial evaluation of an objective function and direct communication between agents. Although population based decision mechanisms employed by many Swarm Intelligence methods can suffer poor convergence resulting in ill-defined halting criteria and loss of the best solution, as a result of its resource allocation mechanism, the solutions found by Stochastic Diffusion Search enjoy excellent stability.
Previous implementations of SDS have deployed stopping criteria derived from global properties of the agent population; this paper examines new local SDS halting criteria and compares their performance with ‘quorum sensing’ (a termination criterion naturally deployed by some species of tandem-running ants). In this chapter we discuss two experiments investigating the robustness and efficiency of the new local termination criteria; our results demonstrate these to be (a) effectively as robust as the classical SDS termination criteria and (b) almost three times faster.