Mobility, Residual Energy, and Link Quality Aware Multipath Routing in MANETs with Q-learning Algorithm

Tilwari, Valmik; Dimyati, Kaharudin; Hindia, Mohammad Nour; Fattouh, Anas; Amiri, Iraj Sadegh

doi:10.3390/app9081582

Cited by 44 publications

(21 citation statements)

References 57 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The emergence of tabular reinforcement learning [7], [39], also referred to as tabular Q-Learning, in the early 1990s spurred several studies that attempted to exploit Q-Learning for distributed routing in classical Internet Protocol (IP) networks, see e.g., [40]- [44], as well as for optical burst routing [45]. Tabular Q-Learning has recently also been employed for optimizing the video quality in multimedia networking [46], mobile ad hoc network routing [47], and for load scheduling in the energy Internet [48]. While Q-Learning was generally found to achieve good routing performance, the distributed nature of classical IP network operation makes implementation challenging.…”

Section: Review Of Related Workmentioning

confidence: 99%

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

et al. 2020

View full text Add to dashboard Cite

Flow routing can achieve fine-grained network performance optimizations by routing distinct packet traffic flows over different network paths. While the centralized control of Software-Defined Networking (SDN) provides a control framework for implementing centralized network optimizations, e.g., optimized flow routing, the implementation of flow routing that is adaptive to varying traffic loads requires complex models. The goal of this study is to pursue a model-free approach that is based on reinforcement learning. We design and evaluate QR-SDN, a classical tabular reinforcement learning approach that directly represents the routing paths of individual flows in its state-action space. Due to the direct representation of flow routes in the QR-SDN state-action space, QR-SDN is the first reinforcement learning SDN routing approach to enable multiple routing paths between a given source (ingress) switch-destination (egress) switch pair while preserving the flow integrity. That is, in QR-SDN, packets of a given flow take the same routing path, while different flows with the same source-destination switch pair may take different routes (in contrast, the recent DRL-TE approach splits a given flow on a per-packet basis incurring high complexity and out-of-order packets). We implemented QR-SDN in a Software-Defined Network (SDN) emulation testbed. Our evaluations demonstrate that the flow-preserving multi-path routing of QR-SDN achieves substantially lower flow latencies than prior routing approaches that determine only a single source-destination route. A limitation of QR-SDN is that the state-action space grows exponentially with the number of network nodes. Addressing the scalability of direct flow routing, e.g., through routing only high-rate flows, is an important direction for future research. The QR-SDN code is made publicly available to support this future research.

show abstract

Section: Review Of Related Workmentioning

confidence: 99%

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Other weakness of these techniques, they have been compared only with protocols which do not consider the link stability and the multipath principle; therefore these routing protocols performance evaluations are not fair. A few multipath protocols using the link stability and the energy consumption as criteria to select the best paths, for routing data packets have been proposed; we cite [17][18]. The majority of these protocols were simulated in unrealistic environments with not practical nodes behavior, such as sudden stop and change of direction under high speed.…”

Section: Multipath Energy-aware Andmentioning

confidence: 99%

An efficient energy aware link stable multipath routing protocol for mobile ad hoc networks in urban areas

Benatia¹,

Smail²,

Meftah³

et al. 2020

Telfor J

View full text Add to dashboard Cite

Ad Hoc wireless mobile networks are characterized by a lack of central administration and the fact that any element of the network, being very mobile, is susceptible to disappear. In an Ad Hoc network, all the elements must cooperate in order to establish a temporary network to communicate. This communication is affected by the links stability mainly in a restricted environment such as a city and the depletion of the batteries energy of the nodes. These factors degrade the ad hoc networks performance. We propose in this paper a stable routing protocol with weak energy consumption for urban areas in order to improve these performances. The proposed solution is a multipath protocol named ESMRua (Efficient energy aware and Link Stable Multipath Routing Protocol in urban areas). ESMRua uses a path selection scheme based on energy constraint, signal quality and link stability. For the link stability, three calculation variants are used. ESMRua will be designed for realistic mobility, contrary to the main existing protocols which are designed to the random mobility models; these models have unrealistic behaviors such as a brusque acceleration and a sudden stop. Simulation results show that our multipath protocol enhances the performance of the ad hoc networks, mainly in terms of routing overhead, energy consumption and network reliability.

show abstract

“…In Ref. [10], the authors propose multiple parameters such as residual energy, mobility, and link quality for multipath optimal routing in MANETs. It enhances the lifetime of the network over a sustained period of time.…”

Section: Attempts On Multipath Routingmentioning

confidence: 99%

Adaptive Group-based QoS Aware Link State Proactive Multipath Routing for Large-Scale MANETs (GMP-OLSR)

Yitayih¹

2020

IJST

View full text Add to dashboard Cite

Objectives: To propose a group-based QoS aware proactive multipath routing based on OLSR protocol. Methodology: This work proposes a group-based proactive multipath routing based on the OLSR protocol, which is designed to be adaptive for a big crowded Mobile Ad-hoc Network to satisfy the desire for real-time multimedia applications. This approach will restrict mobile nodes to be participated in the cluster head selection process based on the mobility and energy of a node. It uses a grouping strategy to manage the network topology and performing route maintenance, and preserve multiple prioritized routes with the support of Quality of Service (QoS) aware computation. Findings: The study evaluated the performance of the proposed group-based QoS aware multipath Optimal Link State Routing (GMP-OLSR) routing through the OMNET++ network simulation environment. Within different network density, the proposed approach offered a significant reduction in end to end delay, overhead and an increment in data packet delivery ratio. Applications: Using an appropriate groupbased QoS aware multipath routing strategy for mobile ad hoc networks provides better performance and improves the services of mobile applications.

show abstract

Mobility, Residual Energy, and Link Quality Aware Multipath Routing in MANETs with Q-learning Algorithm

Cited by 44 publications

References 57 publications

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

An efficient energy aware link stable multipath routing protocol for mobile ad hoc networks in urban areas

Adaptive Group-based QoS Aware Link State Proactive Multipath Routing for Large-Scale MANETs (GMP-OLSR)

Contact Info

Product

Resources

About