Machine intelligence approach: To solve load balancing problem with high quality of service performance for multi-controller based Software Defined Network

2021 ◽  
Vol 30 ◽  
pp. 100511
Author(s):  
Vivek Srivastava ◽  
Ravi Shankar Pandey
Author(s):  
Alabi I Kehinde ◽  
Sagir Lawan ◽  
Fatai O Adunola ◽  
Alabi I Isaac

Author(s):  
Aulia Desy Aulia Nur Utomo

Abstract In the use of internet networks that are general in nature need to implement an appropriate network configuration to maximize the use of internet connections provided by service providers. This is important for the optimal use of internet services and in accordance with utilities that are basically general and shared can be achieved. Per Connection Classifier is a load balancing method for distributing traffic loads to more than one network connection point in a balanced way, so that traffic can run optimally. This research focuses on network configuration methods to maximize internet usage for all users. Quality of Service is used to see the performance of network traffic which is indicated by the value of the parameter delay, throughput, and packet loss. Based on the results of testing and research that have been carried out before and after using load balancing per connection clasifier, the delay value is decreased from 180.26 ms to 148.36 ms and throughput increased from 1.76% to 2.03%, then packet loss decreased from 25.37% to 18.59% according to the TIPHON standard. Keywords: Quality of Service, Per Connection Classification, load balancing, delay, throughput, packet loss


2021 ◽  
Vol 11 (3) ◽  
pp. 34-48
Author(s):  
J. K. Jeevitha ◽  
Athisha G.

To scale back the energy consumption, this paper proposed three algorithms: The first one is identifying the load balancing factors and redistribute the load. The second one is finding out the most suitable server to assigning the task to the server, achieved by most efficient first fit algorithm (MEFFA), and the third algorithm is processing the task in the server in an efficient way by energy efficient virtual round robin (EEVRR) scheduling algorithm with FAT tree topology architecture. This EEVRR algorithm improves the quality of service via sending the task scheduling performance and cutting the delay in cloud data centers. It increases the energy efficiency by achieving the quality of service (QOS).


2011 ◽  
Vol 5 (1) ◽  
pp. 71-78 ◽  
Author(s):  
K. Zheng ◽  
Y. Wang ◽  
L. Lei ◽  
W. Wang ◽  
Y. Lin

Sign in / Sign up

Export Citation Format

Share Document