Wolves And Glowworms Swarm Optimization Algorithms And Applied Research

The wolf is a very intelligent animal. They are not alone when theyprey food, but compose a team by a few wolves. WCA(A wolf colonysearch algorithm) is a new swarm intelligence algorithm proposed on thebasis of the predatory behaviors of the wolf colony. It has a goodconvergence speed, but the solution accuracy is not high and it is easy tofall into local optimization.Artificial Glowworm Swarm Optimization algorithm is a novelbionic swarm intelligence optimization algorithm which is designed tosimulate the foraging or courtship behavior of glowworm swarm innature. Although the algorithm is highly versatile and has a fasterconvergence, but it is prone to premature precision and the searchaccuracy is not enough higher.In recent years, GSO has been paid more and more attention andbecome a new research focus in the field of computational intelligencegradually. And it also has been successfully applied in the sensor noisetest, the harmful gas leak positioning simulation robot, etc.On the basis of the shortcomings of the above two intelligentalgorithms, we explore and research deeply and mainly obtain thefollowing findings.1. Due to the wolf search algorithm exists low optimizing accuracy andpremature phenomenon, we propose a wolf search algorithm based on theleadership strategy. The algorithm derives from the following process:there exists competitions between the individual wolf, thereby, the moststrong wolf becomes the leader, then they get their food under the leadership of the leader wolf. In this way, it is more effectively for wolvesto capture prey. Wolves, which is led by the leader wolf, continue tosearch and capture prey. Using the algorithm to solve the optimizationproblem can find the global optimal solution ultimately.2. Path planning for uninhabited combat air vehicle(UCAV) is acomplicated high dimension optimization problem, which considersdifferent kinds of constrains under the complicated battle fieldenvironment. In order to solve this kinds of problem, which is convertedto a kind of constrained function optimization problem, a wolf colonysearch algorithm based on the complex method is proposed by combiningthe complex method and the wolf colony search algorithm, and it isapplied to solve the problem of UCAV path planning successfully.3. For basic artificial glowworm swarm optimization algorithm has aslow convergence rate and is easy to fall into local optimum, and thecloud model has excellent characteristics on uncertainty knowledgerepresentation, an artificial glowworm swarm optimization algorithmbased on cloud model is presented by utilizing these characteristics. Thealgorithm selects the optimal value of each generation as the center pointof the cloud model, and compares it with current cloud droplets and thenachieves the better search value of groups, which can avoid falling intothe local optimum and speed up the convergence rate of the algorithm.4. According to traditional glowworm swarm optimization algorithm, adiscrete glowworm swarm optimization algorithm is presented. Thisalgorithm apply the encoding method based on the workpiece order. InOrder to improve the performance of optimization algorithm inpermutation flow shop scheduling problem, we combine simplifieddomain search algorithm to apply into the scheduling problem ofpermutation flow successfully.