Dynamic Cost-Aware Routing of Web Requests.

Gandhimathi Velusamy,Ricardo Lent

doi:10.3390/fi10070057

Abstract

Work within next generation networks considers additional network convergence possibilities and the integration of new services to the web. This trend responds to the ongoing growth of end-user demand for services that can be delivered anytime, anywhere, on any web-capable device, and of traffic generated by new applications, e.g., the Internet of Things. To support the massive traffic generated by the enormous user base and number of devices with reliability and high quality, web services run from redundant servers. As new servers need to be regularly deployed at different geographical locations, energy costs have become a source of major concern for operators. We propose a cost aware method for routing web requests across replicated and distributed servers that can exploit the spatial and temporal variations of both electricity prices and the server network. The method relies on a learning automaton that makes per-request decisions, which can be computed much faster than regular global optimization methods. Using simulation and testbed measurements, we show the cost reductions that are achievable with minimal impact on performance compared to standard web routing algorithms.

Highlights

The Internet traffic continues increasing driven by multiple factors, including the proliferation of web of things [1], popularization of wearable computers, business globalization, and new technologies for machine-to-machine communications, high speed network access, and content delivery
We propose a solution based on learning automata—the Cost Aware S-model Reward Penalty Epsilon (CA-S) method seeks to reduce the average cost in serving web requests with replicated web servers deployed on different geographical regions
We have proposed a dynamic method for web request routing among replicated and geographically distributed servers that operate under the authority of different electricity markets

Summary

Introduction

The Internet traffic continues increasing driven by multiple factors, including the proliferation of web of things [1], popularization of wearable computers, business globalization, and new technologies for machine-to-machine communications, high speed network access, and content delivery. It has been estimated that the energy that will be consumed by DCs in the United States by 2020 will be 140 billion kWh (kilowatts-hour), which is equivalent to the power generated by 50 power plants. This amount of energy will cause 150 tones of carbon pollution [3]. DC operators seek to reduce their total cost of ownership to increase the return on investment

Methods

Results

Conclusion