Multi-path Routing Policy for Distributed Caching System

Abstract

The massive volume of content traffic imposes serious challenges to today’s Internet. Content distribution is widely considered as a useful method of efficiently and successfully processing content traffic. To this effect, effective cache technologies are urgently required for both Internet service providers (ISPs) and Internet users. However, transmission efficiency of major methods for content routing is too low to meet Internet’s needs. This paper proposes an ant multi-path routing algorithm in which network state information is with an excepted heuristic factor function to promote the selected probability of the best possible multiple paths to improve routing efficiency. The state information of links works in the proposed algorithm to update the pheromone, allowing multi-paths to be selected with optimized proportions to distribute content appropriately. Simulation results demonstrate that the proposed method reduces access latency by 10%, thus improving the user’s quality of service (QoS) by a considerable margin. Experimental results further demonstrated the superior network transmission capacity of the proposed optimization framework over other existing systems.