With the advent of 5G, IoT and 4k videos, online gaming, movie streaming and other data intensive applications, the demand for data is sky rocketing. Due to this surge in data, the load on the network increases. This heightened network load causes degradation in network performance. Which can lead to the customer Service Provider (CSP)s loosing revenue if the Service Level Agreement (SLA) are not met.
This report describes how machine learning techniques such as tit for tat can be applied to telecom networks. Machine learning applied to telecom networks help detect congestion and maintain SLAs while increasing yield (revenue).
Several experiments are run with varying conditions on the network, such as low, medium and high loads; different levels of SLA for bandwidth and delay. Once the original conditions are tested without applying any smart blocking techniques, machine learning is applied to detect congestion in the network and block flows to maintain SLA and increase the number of flows that generate revenue.
Library of Congress Subject Headings
Software-defined networking (Computer network technology); Computer networks--Access control; Adaptive routing (Computer network management); Machine learning; Computer networks--Economic aspects
Telecommunications Engineering Technology (MS)
Department, Program, or Center
Electrical, Computer and Telecommunications Engineering Technology (CET)
William P. Johnson
Mark J. Indelicato
Jana, Nabarun, "Increasing Revenue by Applying Machine Learning to Congestion Management in SDN" (2018). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus