Service Placement for Latency Reduction in the Fog Using Application Profiles

Karima Velasquez,Marilia Curado,David Perez Abreu,Edmundo Monteiro

doi:10.1109/access.2021.3085370

Karima Velasquez, Marilia Curado + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3085370

Copy DOI

Abstract

The Cloud-Fog-Internet of Things continuum combines different paradigms to provide connectivity and ubiquity for end-users, while also granting low latency and low jitter to cope with different challenges, including the requirements of latency-sensitive applications, such as virtual/augmented reality and online gaming. This constitutes a complex and dynamic environment with heterogeneous resources that need to be managed or orchestrated, in order to accomplish application requirements for low latency. Common orchestration solutions make placement decisions based only on the resources of the underlying network and the application resource requests; however, using the profiles of applications to make placement decisions has the potential to enhance the final performance perceived by the end-users. This paper proposes the use of application profiles according to their popularity to guide their placement. To corroborate the effectiveness of the use of the profiles, two placement mechanisms are presented, one based on Genetic Algorithm and the other inspired on graph partitions. Simulation results show that it is possible to reduce the latency and jitter of applications via a service placement guided by the profiles. The mechanism based on graph partitions showed better results for all scenarios, followed closely by the Genetic Algorithm in the scenarios with lower load.

Highlights

New applications and services enhance the usability and impact of physical world entities by the use of digital systems and infrastructures, like the Internet of Things (IoT)
For the smallest load, GA showed an exceeding latency of 2 times the values reported by Popularity Ranked Placement (PRP), while First Fit (FF) showed a surmount of around 5 times over PRP
This is because as the load grows, the feasibility condition to validate solutions generated by GA was more difficult to reach via the mutations introduced by the algorithm, generating solutions with elevated fitness values that were discarded for the following generations, evolving slower

Summary

Introduction

New applications and services enhance the usability and impact of physical world entities by the use of digital systems and infrastructures, like the Internet of Things (IoT). The fusion of the physical world with the digital one enables the evolution of applications and services, which encompasses a smart relation and connectivity between people, processes, data, and things [1]. In this context, applications (e.g., eHealth, augmented reality, smart traffic control) usually require real-time analytics, stream mining, and low latency that could not be fulfilled entirely in the IoT devices given their resource constraints. As an extension of the Cloud, the Fog brings computing services closer to the source of data generation (i.e., network edge) providing lower latency levels, mobility support, and location awareness [2], [3]. Since the Fog represents a vast environment filled with heterogeneous devices, it is necessary to design and develop smart placement mechanisms that optimize the resource usage while improving the performance of the applications, for those that are latencysensitive, such as online gaming, videoconferences, and virtual/augmented reality

Methods

Results

Conclusion