Research On Task Offloading And Resource Allocation Strategy Based On User Cooperation In Edge Computing Network

With the swift evolution of communication technology,a plethora of computation-intensive and delay-sensitive applications have surfaced.The escalating business demands have resulted in a colossal challenge for user devices with their limited computing resources.Consequently,the service experience of users has been considerably affected.To address this issue,Mobile Edge Computing technology has garnered extensive attention.By placing computing resources in proximity to users and utilizing task offloading,MEC can provide computing power support for users.Additionally,cooperative computing among users has become a crucial approach to enhancing the computing power of edge computing networks.To overcome the contradiction between the limited network resources and diverse user requirements,a deep analysis of the task offloading and resource allocation strategies in the network is necessary.Cooperative computing among users entails leveraging idle resources of terminal devices to collaboratively complete computing tasks.However,users’ resources are limited and primarily focused on their individual task requirements.Therefore,designing a viable cooperative computing mechanism and allocating network resources reasonably based on users’needs is crucial in ensuring a seamless cooperative computing experience.Additionally,users are more inclined to offload tasks to trusted devices to ensure the security and privacy of offloading data.Hence,designing a cooperative computation offloading strategy that considers the trust relationship between users is a significant challenge.This thesis aims to establish a feasible mechanism for cooperative computing and trust relationship between users,as well as to enhance the quality of service for users through reasonable task offloading and resource allocation strategies.The primary work involved in this research is outlined as follows.This thesis proposes a cooperative computing-based user pairing and resource allocation algorithm for the multi-user offloading scenario in edge computing networks.Firstly,each user device is paired with a cooperative device based on their task requirements.Secondly,the user satisfaction is defined based on historical cooperation relationship between nodes.With the energy consumption,computing resource cost and satisfaction of users,a user utility function is designed to represent the benefit value of user cooperative computing。Then,a joint optimization problem is constructed based on user cooperative pairing,communication power allocation,task offloading time,and offloading ratio.The optimization objective is to maximize the total utility value of all users.To facilitate the solution,the problem is transformed and decomposed into two sub-problems.For the user cooperative pairing sub-problem,an optimal cooperative pairing algorithm based on cross-entropy is proposed.For the offloading power allocation,task offloading time,and offloading ratio sub-problems,a joint optimization algorithm based on Lagrangian dual method is proposed.The simulation results demonstrate that the proposed mechanism effectively reduces user task computing cost and improves the total utility value of the system.This thesis proposes a task offloading and resource allocation algorithm based on the social relationship between users to enhance the privacy and security of user cooperative computing in edge computing networks.Firstly,this thesis considers the trust relationship between user devices and designs two indicators,namely social strength and social threshold,to capture the strength of trust between users and their privacy and security requirements.Social strength is constructed based on community relationship,contact frequency,and friend relationship.Then,based on the social strength and threshold,computing resources,and delay tolerance constraints,a joint optimization problem about task offloading and resource allocation is constructed.Since the problem is non-convex and the variables are coupled with each other,it is challenging to solve directly.Therefore,this thesis transforms and splits it into two subproblems.For the task offloading sub-problem,an offloading strategy based on the improved genetic algorithm is proposed.For the resource allocation sub-problem,a resource allocation algorithm based on maximizing the task completion ratio is proposed.The simulation results demonstrate that the proposed algorithm effectively improves the user computing task completion rate and reduces the total energy consumption of users.