Research On CDN Load Balancing Algorithm In Fog Computing

Content Distribution Network(CDN)enables users to access the data needed to distribute to the edge of the network nearby,so as to achieve the goal of accelerating and improving the quality of service,and content distribution network is widely applied to various large enterprises and e-commerce websites.Cloud content distribution network combined with content distribution network and cloud computing technology can effectively solve the real-time problem of traditional content distribution network,but with the development of Internet of Things and the increasing of the intelligent terminal equipment,the core of calculation slowly moves from the network center to the network edge.The recent fog computing mode can adapt to the change of cloud computing mode.As an extension of cloud computing,fog computing has the characteristics of low latency and wide geographical distribution,which makes fog content distribution network more widely applied to various services.The massive computing resources provided by fog nodes can effectively reduce the computation cost.Load balancing plays an important role in the fog computing system,the performance of load balancing algorithm will directly affect the performance of the whole system.Therefore,this paper selects the content distribution network load balancing algorithm in fog computing as a research topic.The specific content is as follows.(1)In fog computing environment,an improved weighted minimum connection number load balancing algorithm is proposed.The weight of the server is represented by the ratio of the idle load of the server to the total load,it can better reflect the load capacity of the node to some extent.Based on the ratio of the original connection number to the weight value,the ratio of load to weight is selected as an important criterion,which can better solve the problem of the number of server connections and load mismatches.A delay optimization strategy is proposed to reduce cloud access and user waiting delay through fog computing layer information interaction.The improved algorithm is compared with the traditional minimum connection number and the weighted minimum connection number load balancing algorithm.Experimental results show that the improved weighted minimum connection number load balancing algorithm is more balanced in the case of the same number of connections.(2)In fog content distribution network environment,a fog content distribution network multiplex transmission load balancing algorithm is proposed.A fog computing layer is added between the edge server and the client,and the user requests data transmission through a large number of fog nodes concurrently.The data requested by the user is divided,and each fog node receives the divided data according to the ratio of the current residual load to the total residual load of the fog computing layer.The feature code of the identification information is introduced,the missing data is resend to increase the stability of the fog node data transmission in the process of data transmission.The proposed algorithm is compared with the data direct transmission method.The experimental results show that the fog content distribution network multiplex transmission load balancing algorithm has a faster transmission speed,and the load occupancy rate of each fog node is a certain proportion.At the end of this paper,the above research content is summarized,and the next step of the work is prospected.