Mobile Ad hoc Networks (MANET) are self-organized networks which are characterized by dynamic topologies in time and space. This creates an instable environment, where classical routing approaches cannot achieve high performance. Thus, adaptive routing is necessary to handle the random changing network topology. This research uses Reinforcement Learning approach with Q-Routing to introduce our MANET routing algorithm: Stability-Aware Cognitive Packet Network (CPN). This new algorithm extends the work on CPN to adapt it to the MANET environment with focus on path stability metric. CPN is a distributed adaptive routing protocol that uses three types of packets: Smart Packets for route discovery, Data Packets for carrying data payload, and Acknowledgments to bring back feedback information for the Reinforcement Learning reward function. The research defines a reward function as a combination of high stability and low delay path criteria to discover long-lived routes without disrupting the overall delay. The algorithm uses Acknowledgment-based Q-routing to make routing decisions which adapt on line to network changes allowing nodes to learn efficient routing policies.
This paper proposes a new adaptive Mobile Ad hoc Networks (MANET) routing algorithm to find and maintain paths which provide Qulaity of Service (QoS) for network traffic using a low-complexity bio-inspired learning paradigm. MANETS are highly dynamic, and thus providing QoS routing is considered a challenging, complex domain. Classical routing approaches cannot achieve high performance. Thus, it is necessary for nodes to be self-aware i.e. able to discover neighbours, links, and paths when needed. This proposal combines the selfaware capabilities in CPN with a Q-learning inspired path selection mechanism. The research defines a Q-routing reward function as a combination of high stability and low delay path criteria to discover long-lived routes without disrupting the overall delay.The algorithm uses Acknowledgment-based feedback to update link quality values in order to make routing decisions which adapt on line to network changes allowing nodes to learn efficient routing policies. Simulation Results show how the reward function handles the network changing topology to select paths that improve QoS delivered.
The work presented in this article aims at using an available computer simulation package for the evaluation of the operation of the IBM‐SNA‐VRPC congestion management method on the present state of GULFNET, and a future design of the network that includes more nodes and provides higher reliability.
Mobile Ad hoc Networks (MANET) are self-organized networks that are characterized by dynamic topologies in time and space. This creates an instable environment, where classical routing approaches cannot achieve high performance. Thus, adaptive routing is necessary to handle the challenges in MANETs. Furthermore, it is necessary for nodes to be selfaware i.e., able to discover neighbors, links and paths when needed. This paper proposes a new adaptive Mobile Ad hoc Networks (MANET) routing algorithm to find and maintain paths that provide the needed Quality of Service (QoS) for network traffic using a low-complexity bio-inspired learning paradigm. It combines the self-aware approach in Cognitive Packets Network (CPN) with a Q-routing inspired path selection mechanism. CPN is a distributed adaptive routing protocol that uses three types of packets: Smart Packets for route discovery, Data Packets for carrying data payload and Acknowledgments to bring back feedback information for the Reinforcement Learning reward function. The research defines a Q-routing reward function as a combination of high stability and low delay path criteria to discover long-lived routes without disrupting the overall delay. The algorithm uses Acknowledgment-based feedback for Q-routing to make routing decisions that adapt on line to network changes allowing nodes to learn efficient routing policies. Simulation Results show how the reward function handles the network changing topology to select paths that improve QoS delivered.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.