An Improved Dragonfly Optimization Algorithm for Solving Numerical and Three-bar Truss Optimization Problems

Abstract

The Dragonfly Algorithm(DA) is a burgeoning swarm intelligence algorithm based on the theory of dragonflies avoiding natural enemies and hunting their food. This algorithm has the benefits of a powerful search ability and ease of implementation, but it also has drawbacks like low solution accuracy and sluggish convergence time. Simulated Annealing (SA) is a Monte-Carlo iterative solution strategy-based random optimization technique. It can viably dodge falling into a nearby least and in the long run tend to the global optimum. So as to decrease the visual deficiency of dragonfly algorithm, progress it’s solution exactness and meeting speed, and maintain a strategic distance from dragonfly algorithm from falling into nearby optimal solution. A dragonfly algorithm based on simulated annealing mechanism (SADA) is proposed in this paper. In each iteration, if the new position has better adaptability, it will directly replace the original position. Otherwise, the Metropolis acceptance criteria will be utilized to decide whether to accept the unused solution. Therefore, while improving the solution accuracy and convergence speed, it can successfully dodge the dragonfly algorithm from falling into the nearby optimum. The viability of the calculation is confirmed by 22 benchmark test functions and three-bar truss engineering problems. Test comes about appear that SADA has way better execution in optimizing functions and can discover superior solutions in building applications.