Enhancing the Performance of Adhoc On demand distance vector(Aodv) Routing Protocol using AI

Is this project an undergraduate, graduate, or faculty project?

Graduate

group

What campus are you from?

Daytona Beach

Authors' Class Standing

Prachi Choudhary, Graduate Raju Dhakal, Graduate

Lead Presenter's Name

Prachi Choudhary

Faculty Mentor Name

Laxima Niure Kandel

Abstract

Uncrewed Aerial Vehicles (UAVs) and ground nodes provide effective solution for establishing emergency communication networks in disaster situations where conventional communication systems are damaged and unavailable. These hybrid UAV-assisted adhoc networks can be rapidly deployed, offering flexibility and mobility needed to support critical Search and Rescue (SAR) operations. The unique capabilities of both UAVs and fixed nodes in UAV-assisted networks ensures reliable communication for first responders (FRs) and disaster survivors. This research aims to design an enhanced version of the Ad Hoc On-Demand Distance Vector (AODV) routing protocol utilizing Q-learning techniques. We evaluate the performance of proposed Q-learning-enhanced AODV protocol against to the original AODV protocol within a network that includes both UAVs and ground nodes, simulated using the NS-3 network simulator.

Did this research project receive funding support from the Office of Undergraduate Research.

No

Share

COinS
 

Enhancing the Performance of Adhoc On demand distance vector(Aodv) Routing Protocol using AI

Uncrewed Aerial Vehicles (UAVs) and ground nodes provide effective solution for establishing emergency communication networks in disaster situations where conventional communication systems are damaged and unavailable. These hybrid UAV-assisted adhoc networks can be rapidly deployed, offering flexibility and mobility needed to support critical Search and Rescue (SAR) operations. The unique capabilities of both UAVs and fixed nodes in UAV-assisted networks ensures reliable communication for first responders (FRs) and disaster survivors. This research aims to design an enhanced version of the Ad Hoc On-Demand Distance Vector (AODV) routing protocol utilizing Q-learning techniques. We evaluate the performance of proposed Q-learning-enhanced AODV protocol against to the original AODV protocol within a network that includes both UAVs and ground nodes, simulated using the NS-3 network simulator.