Research On Task Offloading Algorithm Based On Integrated Trust Mechanism In Mobile Edge Computing

With the advent of the internet of everything and the era of smart,such as artificial intelligence,big data,the internet of things,and the internet of vehicles have developed rapidly,and various types of service requests such as computing-intensive and delay-sensitive are constantly emerging.The traditional cloud computing-based data processing model has been difficult to meet various service requests,and guarantee the user's service experience.Mobile Edge Computing(MEC)emerged as a new computing model.It essentially sinks some of the services and functions of cloud computing to the edge of the network to alleviate problems such as excessive network transmission burden,limited terminal equipment resources,and task response delays.However,the development of MEC is currently in its infancy,many technologies are not mature,and many issues need to be further studied.Reasonable task offloading is one of the crucial issues to be solved urgently in MEC.Moreover,due to the dynamic,real-time and complexity of the MEC environment,the security and reliability issues of edge data have become increasingly prominent.Therefore,based on the above problems,this thesis takes the security and reliability of edge data as a research innovation point,and combined with deep reinforcement learning algorithms,to study the problem of task offloading in the MEC environment.The specific research contents are as follows:(1)In order to ensure the security and reliability of edge data during offloading,a set of task offloading integrated trust evaluation mechanism is constructed based on the comprehensive consideration of the identity credibility,behavior credibility and capability credibility of users and computing nodes.(2)Based on the proposed integrated trust evaluation mechanism and deep reinforcement learning algorithm,a novel task offloading algorithm is proposed to solve the task offloading problem in two-tier MEC environment.The experimental results show the effectiveness of the algorithm,which can ensure the performance of task offloading,and effectively reduce the average response time of tasks and the total energy consumption of the system.(3)Aiming at the limitation of edge server resources in the two-tier MEC model,a task offloading algorithm based on the three-tier MEC model is proposed.The algorithm can make reasonable decisions to determine whether the task needs to be offloaded,and which computing unit to offload for processing.Experimental results show that the algorithm has better performance than other algorithms,and has good scalability,robustness and stability.