Topology-Aware Reinforcement Learning Routing Protocol in Underwater Wireless Sensor Networks

Kim, Hee-won; Cho, Junho; Cho, Ho-Shin

doi:10.1109/ictc46691.2019.8939720

Cited by 8 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, KNN-based personalized network resource allocation can only recommend the existing similar configuration, and cannot provide more personalized configuration for the current configuration. In the future, we will consider strengthening learning and deep learning to optimize the allocation of network resources [27,31].…”

Section: Discussionmentioning

confidence: 99%

MMNET: A Multi-Modal Network Architecture for Underwater Networking

Wang

Song

et al. 2020

Electronics

View full text Add to dashboard Cite

At present, the key to underwater sensor network (UWSN) research is to provide personalized network support for many underwater applications. In order to achieve this goal, people need a general UWSN. Most of the current UWSN architecture is based on the traditional network, which are limited to a single hardware platform and software platform. Facing the current numerous underwater applications and heterogeneous networks, the UWSN is unable to provide personalized network services according to different application requirements. In this paper, we propose a heterogeneous network framework called MMNET (multimodal network) based on the idea of multimodality, aiming to achieve the compatibility of heterogeneous networks and the scalability of the new architecture. In addition, in the face of the complexity of heterogeneous networks and the personalized needs of network applications, the resource allocation is expressed as a personalized recommendation problem. The distributed personalized recommendation algorithm is used to configure personalized network resources for applications. Each node only needs to solve its own problems, instead of exchanging channel state information by using a distributed algorithm, so the computational complexity can be greatly reduced and signaling is overhead. Finally, we give a special example to prove that our network framework provides a good application.

show abstract

Section: Discussionmentioning

confidence: 99%

MMNET: A Multi-Modal Network Architecture for Underwater Networking

Wang

Song

et al. 2020

Electronics

View full text Add to dashboard Cite

show abstract

“…While the supervised and unsupervised learning methods were typically combined with heuristics, RL methods consist of either standalone solutions, or solutions augmented by fuzzy systems. The effectiveness of RL to solve routing problems has been demonstrated in a number of studies covering routing in traditional networks, wireless sensor networks, and in software-defined networks [120]- [123]. Hence, RL is regarded as one of the strongest approaches, especially when combined with fuzzy systems.…”

Section: Ai Techniques and Methodsmentioning

confidence: 99%

Systematic Literature Review of AI/ML Techniques Applied to VANET Routing

Teixeira

Ferreira

Macedo

2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Vehicular ad hoc networks (VANETs) have emerged as a powerful network model for providing road safety, as well as infotainment applications, for vehicle passengers and drivers alike. These networks are characterized by high node mobility, which in turn introduces communication intermittency and unreliability, deteriorating the network's performance. To provide solutions to the concerns of performance of such networks, articles have proposed intelligent approaches to deal with such issues by means of artificial intelligence and machine learning techniques. This study aimed to review the literature regarding intelligent routing protocols in VANETs by focusing on the techniques used and on how the solutions were evaluated based on performance. A systematic literature review of studies was conducted by adopting the snowballing procedure to collect studies that propose novel approaches to solving the VANET routing protocol by means of intelligent algorithms. The 86 included studies reported that heuristics, fuzzy logic systems and reinforcement learning approaches are the most popular and effective methods to improve network performance in the dynamic VANET environment. The findings have also shown that the literature has yet to find a consensus as to how to evaluate routing protocol performance. An evaluation and comparison framework is required as to enable transparent routing protocol design and selection in future vehicle applications.

show abstract

QoTa-MPR: QoS-oriented and traffic-aware multi-path routing protocol for internet of remote things

Liu

Guo

et al. 2021

Telecommun Syst

View full text Add to dashboard Cite

Internet of Remote Things (IoRT) is widely used in both military and civilian applications. However, due to the unique characteristics, which is characterized as long-distance and high-latency, the design of the routing protocol is a great challenge of IoRT. In this paper, a QoS-oriented and traffic-aware multi-path routing protocol (QoTa-MRP) is proposed for IoRT. QoTa-MRP is composed of two parts. The first part is the link traffic-aware based muti-paths source route discovery mechanism, which is used to establish multipaths with lower link disjoint degree. The second part is path similarity and traffic priority based multi-path selection mechanism, which is used to determine the transmission mode of the traffic flows to enhance the reliability or effectiveness of the transmission. Simultaneously, the protocol is theoretically analyzed in terms of the successful transmission rate of routing transmission data packet. Finally, the dynamic source routing, which is a very representative protocol and is usually used as the baseline comparison protocol, is revisited for the performance verification of the QoTa-MRP in IoRT. It is shown in the simulation results that there are significant superiorities of QoTa-MRP than that of DSR in terms of network throughput, packet loss rate and routing packet header overhead in IoRT.

show abstract

Topology-Aware Reinforcement Learning Routing Protocol in Underwater Wireless Sensor Networks

Cited by 8 publications

References 4 publications

MMNET: A Multi-Modal Network Architecture for Underwater Networking

MMNET: A Multi-Modal Network Architecture for Underwater Networking

Systematic Literature Review of AI/ML Techniques Applied to VANET Routing

QoTa-MPR: QoS-oriented and traffic-aware multi-path routing protocol for internet of remote things

Contact Info

Product

Resources

About