Research On Cache Task Offloading Strategy Based On Game Theory In Edge Computing Environment

With the development of science and technology,the demand for computing resources of terminal devices in the field of Internet of Things has increased exponentially.The traditional cloud computing architecture has problems that delay and energy consumption cannot meet the working requirements of local equipment due to the long transmission link.Edge computing can provide computing functions and storage functions near local devices to meet the work requirements of the devices.However,there is a huge gap between the edge computing node and the cloud server in terms of the optimal computing power and the maximum cache space.How to use the computing power and storage capacity of edge servers to meet the task processing needs of local devices effectively is the key problem of edge computing research.The task offloading technology can offload the tasks originally performed by the cloud server to the edge server,taking advantage of the closer distance between the edge server and the local device,and reducing the execution cost of the task.An efficient task offloading strategy can not only considers system delay,but also considers energy consumption and other factors,and allocates the most reasonable processing location for the task,which can reduce the task overhead and improve the running speed.Aiming at this goal,this paper proposes a task offloading strategy that combines edge caching technology in an edge-cloud architecture scenario.The main tasks are as follows:(1)This article improves on the traditional edge-cloud network architecture,the edge server in the architecture is endowed with data caching function,and the network topology model is established for the transmission link between edge servers through undirected graph.(2)The long transmission distance of cloud server will lead to large delay and energy consumption.Aiming at this problem,a task unloading strategy based on edge cache is proposed.By caching various types of data blocks in the edge server,and uploading the tasks generated by the terminal equipment to the edge server which has cached the corresponding types of data blocks for processing,so as to shorten the delay and reduce energy consumption.The simulation results show that the task offloading strategy based on edge cache proposed in this research has more ideal effects in terms of processing delay and system energy consumption than cloud computing-based offloading strategies and traditional edge computing offloading strategies.(3)Aiming at the problem that the cache hit rate of traditional caching strategies is not ideal in some scenarios,a data caching strategy based on multiplayer noncooperative game theory is proposed.The specific method is to treat each edge server as a game object,and select the cache data for each edge server by searching for the Nash equilibrium solution.The simulation results show that the data caching strategy combined with game theory proposed in this research has a better cache hit rate than the data caching strategy based on frequency of use,and the delay in the task offloading strategy is the same as the energy consumption result.Based on the edge cache technology,this paper studies and optimizes the task offloading link under the edge-cloud architecture,comprehensively considering factors such as delay and energy consumption,and effectively solves the problem of task processing location selection.At the same time,combined with the multiplayer noncooperative game algorithm,it answers how to select the cache content in the limited storage space of edge server effectively.