Research On Inter-User Collaborative Computing Offloading Strategy And Resource Allocation In Edge Computing

Mobile Cloud Computing(MCC),as an emerging computing paradigm,provides powerful computing and storage capabilities for Smart Mobile Devices(SMDs)by offloading computationally intensive tasks to the cloud for processing.However,MCC brings high latency problems while solving intensive computing problems and does not meet the needs of latency-sensitive applications.To solve this problem,mobile edge computing(MEC)is proposed as a supplement to MCC.Different from MCC,MEC offloads tasks to nearby edge servers for computing,which not only provides computing services,but also has ultra-low latency.Considering the relationship between users in a multi-user MEC system in practical scenarios,this thesis studies the problem of user collaborative computing offloading and resource allocation in edge computing.The main research contents are as follows:1.Summarized the existing research goals of edge computing and introduced the necessity of reducing latency and energy consumption for resource constrained SMDs.Existing research mainly considers the computing offloading problem of single-threaded and multi-threaded dependent tasks,and rarely considers the relationship between the computing offloading process of tasks among users,and generally considers that users are independent of each other.2.Aiming at the problem of user collaborative computing offloading in edge computing,an Iterative Algorithm based on One-time Offloading Principle(IOTO)is proposed.The problem of minimizing the delay and the weighted sum of energy consumption in the case of user collaborative computing is constructed.In the process of collaborative computing offloading,data transmission needs to be performed between users,so the offloading strategy between users must be jointly optimized.When the offloading strategy is given,the problem can be transformed into a convex optimization problem,and the optimal solution can be obtained according to the Lagrangian dual method and the KKT condition.The algorithm is simulated and analyzed,and the numerical results show that the proposed method can effectively reduce the weighted sum of user delay and energy consumption.3.Considering the influence of user mobility on computing offloading,an Iterative Algorithm based on Delay Constraint and One-time Offloading Principle(IDCOO)is proposed to minimize the weighted sum of user collaborative computing delay and energy consumption in mobile systems.The user movement affects the transmission rate of the wireless channel,and the free space loss model is used to represent the change of the channel state.When the user moves out of the coverage area of the wireless access point(AP),data transmission with the AP cannot be performed,resulting in the failure of task offloading calculation or collaborative calculation.Aiming at this problem,the corresponding delay constraints are formulated,and the resource allocation and unloading strategies are jointly optimized,and the optimal solution is obtained by using the convex optimization technique.The simulation results show that the IDCOO algorithm can effectively reduce the weighted sum of delay and energy consumption.