Research On Distributed Collaborative Computing Offloading Strategy Assisted By Terminal Direct Acces

With the integration and rapid development of 5G,Internet of Things,and Artificial Intelligence,as well as the increasing demand of users for computing resources,the use of Mobile Edge Computing(MEC)to unload tasks at the edge of the network has become an important direction for future Internet development.Its advantage is that it can provide short-range communication for users at the edge of the network,and effectively reduce the pressure on user devices.At the same time,it is conducive to the integration of new technologies such as the Internet of Things and cloud computing.In order to solve the problem of limited user resources and computing capabilities,the offloading mode based on Device-to-Device(D2D)technology is proposed as an effective supplement to MEC,aiming at the collaborative control and management of a large number of computing and storage resources to complete the computation-intensive application tasks.Aiming at the problems existing in the existing mobile edge computing,such as limited user resources and computing capabilities,user mobility,and task dependency,this paper carries out the following two aspects of research:(1)In order to solve the problem of offloading decision for user mobility and D2 D collaborative computing in MEC networks.In response to this dilemma,this paper proposes a task offloading framework for D2 D –enabled MEC.By introducing the D2 D cooperative technology,a large amount of computing tasks are offloaded to the MEC server at the network edge through D2 D links for data processing.The goal is to minimize the system energy consumption by optimizing the offloading decisions,namely,whether to perform the task locally,or directly offload to the D2 D device,or offload to the D2 D device with the help of the most suitable D2 D device.Considering the high dynamic characteristics of the edge network,a D2 D collaborative edge network system model is designed and an end-to-end optimization objective function is formulated subject to the delay constraints.Secondly,the task offloading decision-making problem is modeled as a Markov model,and the model is efficiently solved by the Double DQN(DDQN)algorithm.Simulation results show that the proposed D2 D collaborative computing scheme can significantly reduce the energy consumption of mobile users’ task execution compared with other algorithms.(2)In order to solve the problem of offloading decision for computation-intensive tasks in dependency-aware edge networks,a depth-first search scheduling strategy based on task priority is proposed.By taking into account the limited energy and high mobility of users,the network model of joint downlink energy harvesting and uplink computing task offloading is built.Furthermore,the device-to-device optimization objective function is formulated under the constraints of the latency and the task priority and the task offloading problem is modeled as a Markov decision process.By exploiting the advantage of self-learning of deep reinforcement learning,the Dueling Double DQN(D3QN)algorithm based on task dependency is designed to tackle it.Numerical results show that the proposed method can meet the delay requirements of more users and could reduce the completion delay up to 9%-10% against other existing schemes.