Cooperative reinforcement learning approach for routing in ad hoc networks

Desai, Rahul; Patil, B. P.

doi:10.1109/pervasive.2015.7086962

Cited by 13 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where α is the step size. To accelerate the algorithm, Q-learning only performs (17) once before the policy improvement in each round of the policy iteration. (One step of the policy evaluation in a policy iteration process is also known as the value iteration process.)…”

Section: Conventional Q-learningmentioning

confidence: 99%

“…Thus, routing can be modeled as a Markov decision process [7] and naturally fits into the realm of reinforcement learning; see [8] for a comprehensive survey of the applications of reinforcement learning to communications and networking. In this direction, many previous works [9]- [17] have employed the classical Q-learning [18] algorithm to train agents to find the optimal route. In most of these works, a distinct agent is associated with each transmission node.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer

Cui

2021

IEEE Trans. Commun.

View full text Add to dashboard Cite

Section: Conventional Q-learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer

Cui

2021

IEEE Trans. Commun.

View full text Add to dashboard Cite

“…In the work of [30], the authors proposed a new machine learning approach to choose the optimal route in ad hoc networks, which is based on the cooperative RL in modeling the swarm intelligence from the models of social insect behavior. To prove the effectiveness of their proposed approach, the authors presented the analysis and performance evaluation by comparing with the existing routing protocols, and the results indicate that the packet delivery ratio is significantly improved when RL is utilized.…”

Section: Applications Of Rl In Networkingmentioning

confidence: 99%

SDN Flow Entry Management Using Reinforcement Learning

Al-Fuqaha

Shuaib

et al. 2018

ACM Trans. Auton. Adapt. Syst.

View full text Add to dashboard Cite

Modern information technology services largely depend on cloud infrastructures to provide their services. These cloud infrastructures are built on top of Datacenter Networks (DCNs) constructed with high-speed links, fast switching gear, and redundancy to offer better flexibility and resiliency. In this environment, network traffic includes long-lived (elephant) and short-lived (mice) flows with partitioned/aggregated traffic patterns. Although SDN-based approaches can efficiently allocate networking resources for such flows, the overhead due to network reconfiguration can be significant. With limited capacity of Ternary Content-Addressable Memory (TCAM) deployed in an OpenFlow enabled switch, it is crucial to determine which forwarding rules should remain in the flow table and which rules should be processed by the SDN controller in case of a table-miss on the SDN switch. This is needed in order to obtain the flow entries that satisfy the goal of reducing the long-term control plane overhead introduced between the controller and the switches. To achieve this goal, we propose a machine learning technique that utilizes two variations of Reinforcement Learning (RL) algorithms—the first of which is a traditional RL-based algorithm, while the other is deep reinforcement learning-based. Emulation results using the RL algorithm show around 60% improvement in reducing the long-term control plane overhead and around 14% improvement in the table-hit ratio compared to the Multiple Bloom Filters (MBF) method, given a fixed size flow table of 4KB.

show abstract

“…Thus, routing can be readily modeled as a Markov decision process [7] and naturally fits into the realm of reinforcement learning. In this direction, many previous works [8,9,10,11,12,13,14,15,16] have employed the classical Q-learning [17] algorithm to train agents to find the optimal route. In these works, a distinct agent is associated with each transmission node.…”

Section: Introductionmentioning

confidence: 99%

Scalable Reinforcement Learning For Routing In Ad-Hoc Networks Based On Physical-Layer Attributes

Cui

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This work proposes a novel and scalable reinforcement learning approach for routing in ad-hoc wireless networks. In most previous reinforcement learning based routing methods, the links in the network are assumed to be fixed, and a different agent is trained for each transmission node -this limits scalability and generalizability. In this paper, we account for the inherent signal-to-interferenceplus-noise ratio (SINR) in the physical layer and propose a more scalable approach in which a single agent is associated with each flow and is trained using a novel reward definition and according to the physical-layer characteristics of the environment. This allows a highly effective routing strategy based on the geographic locations of the nodes in the ad-hoc network. The proposed deep reinforcement learning strategy is capable of accounting for the mutual interference between the links and is capable of producing highly effective routing solutions over the entire network in a scalable manner.

show abstract

Cooperative reinforcement learning approach for routing in ad hoc networks

Cited by 13 publications

References 12 publications

Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer

Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer

SDN Flow Entry Management Using Reinforcement Learning

Scalable Reinforcement Learning For Routing In Ad-Hoc Networks Based On Physical-Layer Attributes

Contact Info

Product

Resources

About