Research On Offloading Decision Algorithm In Edge Computing Of Internet Of Things

With the continuous innovation of Internet of Things(Io T)technology and the widespread popularity of Io T mobile terminal devices,emerging mobile applications continue to emerge.Although the related physical design of CPU and memory of Io T mobile terminal devices continues to evolve,a single device is limited by its own conditions such as CPU,battery,and memory,making it difficult to handle large applications.Edge computing technology can effectively solve the above problems.However,with the growing demand for offloading computing of tasks to be processed,how to weigh the decision of computing task offloading plays a positive role in the performance indicators such as energy consumption and task latency of Io T mobile terminal devices.Based on the above questions,the main research contents in this paper are as follows:Firstly,aiming at the problem that smart mobile devices are not enough to handle compute-intensive tasks,the task offloading decision with the goal of reducing the energy consumption of smart mobile devices is studied.Firstly,in the scenario of a single edge server and multiple intelligent mobile devices,a system model and a mathematical calculation model are established.Then,with the goal of reducing the energy consumption of smart mobile devices,a functional model on latency and energy consumption is formulated,and the problem is described as a nonlinear constraint optimization problem.Finally,in order to overcome the advantages and disadvantages of genetic algorithm and binary particle swarm algorithm,a new algorithm is proposed: GA-BPSO algorithm,which uses GA-BPSO algorithm to solve the constraint optimization problem,and obtains the calculation offloading decision of the optimization problem,so as to find the lowest energy consumption of smart mobile devices under the constraint of latency threshold.The simulation experiment was carried out using the Matlab R2016a tool software,and various parameters were set,and the experimental verification showed that the unloading decision obtained by the GA-BPSO algorithm produced lower energy consumption compared with other algorithms.Secondly,aiming at the problem of minimizing the execution time of computing tasks and the energy consumption of terminal devices in multi-device mobile edge computing systems,the optimization problem of edge computing offloading decision is formulated with the goal of maximizing the system utility of mobile terminal devices.Firstly,a network model of a multi-user single edge server is built.Then,by constructing the communication model and related calculation model,a system utility function is constructed in order to balance the latency and energy consumption,and the system utility function is formulated according to the system utility function Optimize the objective function.Finally,combine the binary artificial bee colony algorithm and the binary differential evolution algorithm,and improve the mutation operation and crossover probability factor to obtain a new algorithm: binAD algorithm,which is used to iteratively update the edge computing offloading decision.According to the offloading decision obtained,the optimization objective function is solved.The binAD algorithm expands the range of feasible solutions,and has a strong global search ability,and can achieve better results in terms of system utility in simulation experiments.