Research On Resource Allocation Strategy Of Edge Computing Based On Auction Algorithm

In recent years,due to the exponential growth of the number of devices and data traffic,this has brought many challenges to the cloud network to achieve high speed,low delay and other aspects,making the cloud network to carry out a reasonable allocation of resources is particularly important.As one of the core technologies of 5G communication technology,mobile edge computing has attracted more and more attention in the research and application fields.The main idea of mobile edge computing is to sink the cloud computing center to the base station and deploy it as an edge cloud,so that users can get closer to the cloud computing center,so as to quickly solve the problem of computing resource allocation.This paper has conducted research on three aspects:task migration between servers,collaboration between edge servers and resource allocation of a single server.The concrete work is as follows:(1)When resource allocation is performed on the edge server,frequent movement of users will cause frequent interruption of the computing offloading task of the application,resulting in an increase in the time overhead of application computing offloading and device power consumption.To solve this problem,this paper proposes a task pre-migration strategy When the application is computing offloading,the edge server synchronizes the task pre-migration operation.When the user leaves the coverage of the edge server,the neighbor edge server will re-establish a link with the user and continue to perform tasks.Experimental simulation results show that the task pre-migration strategy between the edge servers can reduce the waiting time of the user's computing offload and reduce the power consumption of the device.(2)In general,mobile edge computing is to send data that cannot be processed by the local edge server to the cloud for processing,which brings great pressure to the cloud server and relatively large transmission delay to the remote core network.To solve this problem,this paper proposes an resource allocation strategy based on Reverse Auction.By adopting the idea of Reverse Auction,the overloaded data is allocated to the edge server with small load to reduce transmission delay,user experience,balance server load and relieve network pressure are improved.The simulation results show that the method can balance the load of the server and reduce the transmission delay significantly(3)When the edge server performs resource allocation,the traditional virtual machine allocation method is insufficient to flexibly deal with the problem of computing resource allocation of the edge cloud.To solve this problem,this paper proposes a Dynamic Computing Resource and Frequency Allocation Algorithm(DRFAA)based on the change of users' comprehensive demand.It adopts the 'divide and conquer' strategy and simulate the fine-grained division of resources into 'fluid' resources for allocation,so as to seek for larger throughput and lower transmission delay.Experimental simulation results show that this method can effectively reduce the transmission delay between the user and the edge cloud and improve the throughput of the edge cloud.Based on the above three aspects,the three solutions proposed in this paper can greatly improve the efficiency of resource allocation,balance the network load,reduce the transmission waiting time between users and edge servers,and meet the basic requirements of low latency and high performance of mobile edge computing.