Research On Task Scheduling Method For Internet Of Things Based On Swarm Intelligence

To improve the quality of the application services provided by the Internet of Things(IoT),the improvement of its task scheduling efficiency should be studied in depth.For task scheduling problems,the blind search strategy used by the traditional algorithms leads to problems such as large amounts of computing resources are wasted.Hence,swarm intelligent algorithm(SI)is used to achieve the purpose of making task scheduling smarter,more accurate,more stable,and lower energy consumption.The SI contains the randomness of non-blind search and has good control of computation time,which can solve complex optimization problems.Therefore,it makes sense to solve the IoT task scheduling problem by using SI from the aspect of both practice and theory.Firstly,the chaotic map is used to improve the Coyote Optimization Algorithm(COA),which mainly involves three parts:the initialization,the social status update,and inter-group exchange.Based on that,the chaotic Coyote Optimization Algorithm(CCOA)and its application method for task scheduling in IoT are proposed.From the experiment,it is proved that the convergence speed of CCOA has been greatly improved,while its performance in task scheduling is better than that of particle swarm algorithm(PSO)and genetic algorithm(GA).Secondly,Volleyball Premier League Algorithm(VPL)is effectively improved by using the new learning phase strategy and chaotic map.The main modules of VPL are changed specifically,including initialization,competition strategy,knowledge sharing strategy,repositioning strategy,substitution strategy,winner strategy,learning phase strategy,and season transfers strategy.Accordingly,an improved algorithm named IVPL and its application method for task scheduling in IoT are proposed.And it has been verified that IVPL has been improved in terms of convergence speed and solution accuracy,by comparing experiments.In addition,the performance of IVPL in task scheduling is better than that of particle swarm algorithm(PSO)and genetic algorithm(GA).Finally,this paper designs a task scheduling algorithm named CCIV that mixes CCOA and IVPL.It makes the clusters of tasks according to the communication cost between them and completes effectively the scheduling of task clusters onto IoT computing devices,thanks to the strong space search ability,high stability,and fast convergence of SI.From the experiment,it is strongly demonstrated that CCIV is effective and feasible in reducing system total cost.