Using IGMP Protocol to Improve the Latency of Cloud Computing

Abstract

To solve the problem of network latency of cloud computing, organizations usually use the edge computing, which means shorter physical distance from the client, or the parallel computing method, which means separate the task to multi cloud servers. However, these two major solutions do not effectively solve the problem of network latency caused by multiple clients accessing the same resources. In this paper, a new strategy is proposed based on the operation mode of Internet Group Management Protocol (IGMP) to solve the networks latency and waste of network resources caused by multiple clients’ access. This paper would perform the comparison tasks by using Amazon Web Services (AWS). To show the differences, there would be a simulated test of 1000 clients who are trying to access cloud resources from one cloud server. By comparing the total time of 1000 clients receiving their resources, the original group takes 5309 seconds for the cloud server to process the tasks. The test group takes 5034 seconds for the cloud server to process the tasks, which is about 5.68% improvement. Through the research, the conclusion is that if cloud resources are partition properly, the grouping strategy could effectively alleviate the networks latency problem of multiple clients.