Research On Efficient Dynamic Computation Offloading With Content Caching

With the advent of the 5G,fog computing is booming as an emerging technology.The fog node provides users with powerful computing capabilities and storage resources,and provides services such as low latency,high bandwidth,location awareness,and content caching,so that users cloud get better service experience and lower energy consumption.In order to make full use of the resources of fog nodes,computation offloading has gradually become the main research content of fog computing.The energy consumption of fog nodes often be neglected in energy saving.With the integration of Dynamic Voltage Scaling(DVS)in the CPU,the computation offloading decision can become more flexible and efficient.This dissertation takes the fog node energy consumption and user delay as performance metrics,and aims to find the optimal computation offloading mechanism to improve the performance and user experience better in fog computing.The main contributions of this dissertation can be summarized as the following three apoints:1)Delay guaranteed energy-efficient computation offloading for industrial internet of things(IIo T)in fog computing.In order to improve the computation experience of users in fog computing,an energy efficient computation offloading mechanism with time delay guarantee is proposed.The purpose of this mechanism is to minimize energy consumption when computation tasks are accomplished within a desired energy overhead and delay.It has a comprehensive consideration on the components of energy consumption at fog node,which includes the energy consumption of local computing,transmitting and waiting states.To address this energy minimization problem,an accelerated gradient algorithm is proposed,it can find the optimal offloading ratio with a fast speed that improves the convergence speed of traditional method.Finally,the numerical results reveal that the proposed offloading scheme is superior to the local computing and full offloading schemes in terms of energy consumption and completion time,and further confirm the advantage of convergence rate.2)Energy-optimal dynamic computation offloadingfor industrial internet of things in fog computing.For the purpose of meetting the strict requirements of Industrial Internet of Things applications on energy consumption and delay,a dynamic computation offloading mechanism is proposed for fog nodes with integrated DVS technology.This mechanism aims to optimize the energy consumption of fog nodes and constructs a minimization problem with time delay as the main constraint.It jointly optimizes the variable computing speed,offloading ratio,transmission power,and transmission time to determine the calculation speed of the fog node.Based on above considerations,an alternating minimization algorithm is proposed and finally two single variable convex optimization problems are determined and then solved alternately.The numerical results show that the proposed offloading mechanism is superior to other methods in terms of energy consumption and delay,and further confirms the adaptability and scalability of the mechanism.3)Delay minimization with computation offloading mechanism integrated into content caching.Aiming to reduce the delay caused by repeated computation tasks,a mechanism for minimizing the delay of incorporating content cache is proposed.This mechanism takes the task delay of the end users as an optimization goal,and restricts the content cache limitation as constraints.This mechanism makes use of cloud and fog's cache capabilities,and combines wireless transmission and computing resource allocations to make reasonable offloading decisions.A cloud-fog collaborative caching strategy is proposed first,and turn the optimization problem into general problem based on the task cache status,and then a two-stage heuristic algorithm based on greedy is proposed to solve the optimization problem.Finally,simulation results show that the proposed offloading mechanism improves the cache hit rate and reduces the delay,it also verifies the effectiveness and advantages of this mechanism.