Improved optimization technique using hybrid ACO-PSO

In this paper, an optimization algorithm build on combination of ant colony optimization (ACO) and particle swarm optimization (PSO) is proposed. Here genetic algorithm(first stage) is used to create an initial population from the existing population applied in the hybrid ACO-PSO(second stage). This paper deliver a combination of algorithms ACO-PSO. Unlike the traditional ACO-PSO, the new optimization algorithm makes complete use of parameter of both algorithms. In the given algorithm, the PSO is used to enhance the attributes in the ACO, which define that the selection of parameter doesn't depends on artificial experience, but relies on the robust search on the particles in the PSO. This paper also used an enhance utilization of ACO, by this technique it found the shortest path or routes of ants. The output of the experiment show that the optimize algorithm not only reduce the number of paths in the ACO. But also finding the shortest path at the place of largest path. The simulation result shows that combination of ACO-PSO performs better than ACO and PSO.