Abstract:
Nanonetworks consist of interacting nano-nodes from several hundred cubic nanometers to several cubic micrometers. Nano-nodes’ limited computational resources, energy fluctuations caused by energy harvesting processes, and transmission range at Terahertz (THz)-band frequencies (0.1-10 THz) make nanonetwork routing protocol design difficult.
This paper proposes a reinforcement learning-based multi-hop deflection routing algorithm (MDR-RL) to dynamically and efficiently explore packet transmission routing paths. First, nano-nodes implement new routing and deflection tables to deflect packets to neighbors when route entries are invalid.
Second, on-policy and off-policy reinforcement learning-based forward and feedback updating schemes update the tables. Finally, extensive simulations in networks simulator-3 analyze MDR-RL’s performance using different updating policies and compare it to other machine learning routing algorithms based on Neural Networks and Decision Trees. The MDR-RL improves packet delivery ratio, number of delivered packets, and packet average hop count.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
