Smart Edge Computing

5Performance Measures in Edge Computing Using the Queuing Model

Many electronic devices produce large amount of data that should be processed within an efficient time. Nowadays, edge computing is seen as a relevant and appropriate solution to this open challenge to process vast data efficiently. All requests go into the cloud in form of queue. Therefore, all users have to wait until the ongoing request is processed. The edge computing user sends requests to the edge computing service provider to use the resources. If the user finds that the server is busy, the requests need to enter into a queue (waiting line) until the request completes its service. Therefore, this may create obstruction in the network. Hence, to solve this kind of problem, the queuing model is used. It provides services to users with less waiting time. Otherwise, there is a possibility that the user will leave the queue.

This chapter explains how the queuing model is applied on edge computing and also analyzes the performance of edge–cloud computing. “M/M/1”, “M/M/2” and “M/M/4” queuing models are used to improve delay and resource utilization. In this chapter, the aim is to reduce waiting time (delay) and resource utilization to process vast data efficiently. Performance analysis indicates that if the number of edge servers is more, then the waiting time (delay) and resource utilization are reduced.

5.1. Introduction

Computing techniques are increasing rapidly every day with the development of the Internet. ...