Research On Offloading Scheme Of Computing Task For Edge Computing Network

Mobile edge computing technology is considered to be one of the key technologies for the fifth generation mobile communications(5G).By deploying edge servers at the radio access network side to provide computing and storage resources for mobile devices,the computing delay,energy consumption and computing pressure of mobile devicescan be greatly reduced.With the increase in the number of mobile devices and the intensive deployment of edge nodes,the problem of excessive cost caused by the increasing energy consumption of task computing has gradually attracted people's attention.Facing the vision of communication system to improve cost efficiency,this thesis studies the problem of excessive energy cost in mobile edge computing,and uses the economic cost of energy loss as a measurement indicator to propose a corresponding low energy cost task offloading scheme.Firstly,this thesis models from three perspectives: computing,communication,and energy supply.For the computation model,the analysis is performed from two parts:local computation and node computation.For the communication model,the task transmission mode based on time division multiple access is considered,and the transmission energy consumption and delay of the task are mainly considered.The system's energy supply model has been improved,and a hybrid energy supply method combining new energy supply and traditional energy supply is used to supply energy to the edge nodes.Secondly,aiming at the problem of excessive energy cost in mobile edge computing,considering the relationship between the amount of offload computing tasks and energy cost,a cost-efficient distributed task offloading computing scheme was proposed.In the multi-edge node model,the task is offloaded through the mutual cooperation between edge nodes,taking into account the constraints of computing power and delay,with the goal of maximizing the cost efficiency of each user,and developing the most economical offload for each user.Simulation results show that compared with the traditional task calculation scheme,the cost-efficient distributed task offloading algorithm can effectively reduce the calculation delay of tasks and reduce the energy cost of the system.Finally,aiming at the solution process of the offloading scheme,the calculation complexity of the traversal algorithm is too high and the solution efficiency is low.The optimization problem of the task offloading scheme under the single-node system model is analyzed.By applying the immune cloning algorithm and taking the energy cost of the system as the goal,a centralized task offloading algorithm is proposed to solve the optimal offloading decision.The influence of different influencing factors in the algorithm on the convergence is analyzed based on simulation,and the energy cost and time delay are compared to prove the effectiveness of the offloading scheme.