Scalable CDN service PoC over distributed cloud management platform

Author(s):  
TaeYeon Kim ◽  
BhumCheol Lee
Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1553
Author(s):  
Marian Rusek ◽  
Grzegorz Dwornicki

Introduction of virtualization containers and container orchestrators fundamentally changed the landscape of cloud application development. Containers provide an ideal way for practical implementation of microservice-based architecture, which allows for repeatable, generic patterns that make the development of reliable, distributed applications more approachable and efficient. Orchestrators allow for shifting the accidental complexity from inside of an application into the automated cloud infrastructure. Existing container orchestrators are centralized systems that schedule containers to the cloud servers only at their startup. In this paper, we propose a swarm-like distributed cloud management system that uses live migration of containers to dynamically reassign application components to the different servers. It is based on the idea of “pheromone” robots. An additional mobile agent process is placed inside each application container to control the migration process. The number of parallel container migrations needed to reach an optimal state of the cloud is obtained using models, experiments, and simulations. We show that in the most common scenarios the proposed swarm-like algorithm performs better than existing systems, and due to its architecture it is also more scalable and resilient to container death. It also adapts to the influx of containers and addition of new servers to the cloud automatically.


Author(s):  
Kugathasan Janarthanan ◽  
P.R.L.C Peramune ◽  
A.T Ranaweera ◽  
Theviyanthan Krishnamohan ◽  
Lakmal Rupasinghe ◽  
...  

2013 ◽  
Vol 756-759 ◽  
pp. 3904-3908
Author(s):  
Shu Hu ◽  
Jing Li ◽  
Hu Song

In recent years, cloud computing technology has become the most popular field in IT industry, and it has changed the traditional IT technical architecture, development and deployment model in enterprise. Existing cloud management platforms tend to focus only on a single-level resources management, lack of a management platform that combines infrastructure resources, application platform deployment and monitoring services. This paper has designed a deployment-architecture that supports application platform in multi-cloud environment. It helps users deploy the required platform dynamically via self-help tool, frees users from infrastructure management, and provides common and inheritable deployment architecture for infrastructure environment.


2018 ◽  
Vol 53 ◽  
pp. 03026
Author(s):  
Jianbo Wu ◽  
Song Chai

In current China, especially in western provinces, pasture management is largely backward and has low level of automation, and intelligent pasture systems are urgently needed to improve efficiency of management process and reduce operating cost. An intelligent pasture cloud management system based on fuzzy PID control algorithm is proposed in this paper, which consists of management platform software, transmission equipment, intelligent control module and information acquisition module. The sensors acquisition environment parameters are uploaded to the cloud server, fuzzy PID control is performed on the cloud server, and the control parameters are delivered to the intelligent control module for reasonable and effective environmental regulation, such as the temperature and humidity of the pasture. Pasture administrators can check pasture status at any time for remote pasture management, and the pasture environment can be automatically and intelligently regulated. After simulation experiments, we prove that our system is effective.


Sign in / Sign up

Export Citation Format

Share Document