Joint Computation Offloading And Service Caching In Mobile Edge-cloud Computing

For computing intensive and delay sensitive applications scenarios,mobile edge-cloud computing as a new computing paradigm has emerged,which effectively improves the utilization of computing resources.Mobile devices can alleviate their own resource constraints and satisfy different types of service requests by local computation or computation offloading.However,due to the limited resources of mobile edge server,only a few application services can be cached in mobile edge server at the same time.Therefore,we study how to optimize computation offloading decision and service caching decision in mobile-edge cloud computing.The main work of this paper is as follows.In this paper,we research computation offloading in mobile edge-cloud computing.We maximize the satisfaction of users by optimizing computation offloading decision,task scheduling and the clock frequency of mobile devices.Besides we consider the difference of delay sensitivity in different applications and the constraints of dependency relationship between tasks.Firstly,the problem is formalized by network modeling.Moreover,a three-stage distributed algorithm is designed to solve the problem.In this paper,we research service caching in mobile edge-cloud computing.We jointly optimize service caching and computation offloading in mobile edge-cloud computing networks to maximize the profits of network system considering the costs of service replacement and service maintenance.The problem is formalized as a non-convex optimization problem with discrete variables.In order to solve the problem,we propose a dynamic joint computation offloading and service caching algorithm.In this paper,we evaluate the performance of the proposed algorithm through simulation experiments.Firstly,the influence of weight value on energy consumption and delay is analyzed and proved.Finally,the three-stage distributed algorithm is compared with different computation offloading and scheduling algorithms.Besides we verify the feasibility and effectiveness of DJOSC algorithm by comparing with RSC algorithm and NOF algorithm.