Towards A Machine Learning-Based Framework For Automated Design of Networking Protocols

Pasandi, Hannaneh Barahouei

doi:10.1109/percomw.2019.8730720

Cited by 5 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we discovered that the RL-based approach may face instability since the agent has to find a balance between exploration and exploitation. In [2], [13] we give a complete overview of the whole protocol design framework using machine learning techniques. In these works, we describe the key design considerations for the learning agent (e.g., centralized, distributed or hybrid agents) and describe how these agents should communicate with one another.…”

Section: Related Workmentioning

confidence: 99%

MAC Protocol Design Optimization Using Deep Learning

Pasandi

Nadeem

2020

2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

Self Cite

View full text Add to dashboard Cite

Evolving amendments of 802.11 standards feature a large set of physical and MAC layer control parameters to support the increasing communication objectives spanning application requirements and network dynamics. The significant growth and penetration of various devices come along with a tremendous increase in the number of applications supporting various domains and services which will impose a never-before-seen burden on wireless networks. The challenge however, is that each scenario requires a different wireless protocol functionality and parameter setting to optimally determine how to tune these functionalities and parameters to adapt to varying network scenarios. The traditional trialerror approach of manual tuning of parameters is not just becoming difficult to repeat but also sub-optimal for different networking scenarios. In this paper, we describe how we can leverage a deep reinforcement learning framework to be trained to learn the relation between different parameters in the physical and MAC layer and show that how our learning-based approach could help us in getting insights about protocol design optimization task.

show abstract

Section: Related Workmentioning

confidence: 99%

MAC Protocol Design Optimization Using Deep Learning

Pasandi

Nadeem

2020

2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…They show that their approach can learn how to cope with other nodes without any prior information about them. Authors in [15] describe a broader overview of a framework that shows how ML techniques are leveraged for centralized and distributed ML agents to design MAC protocols.…”

Section: Related Workmentioning

confidence: 99%

Quality of Service in IEEE 802.11 WLANs: An Experimental Study

Wang¹

2019

Preprint

View full text Add to dashboard Cite

While the IEEE 802.11 protocol is being widely used, it is not specifically designed to handle multimedia traffic, which covers an important portion of the Internet traffic today. Voice and video multicast streaming is inefficient, as there is lack of transmission reliability in such approaches where delay is not guaranteed. In this work, we focus on the performance of Enhanced Distributed Channel Access (EDCA) mechanism proposed by IEEE 802.11e which provides traffic prioritization and since most of the previous works are done based on simulation results, we test the performance of this protocol in a real platform using sofware Defined Networks. We then validate the impact of different EDCA parameters ( e.g., AIFS and TXOP) by tuning them to see their impact on the delay of the network and eventually on network traffic.

show abstract