A novel unmanned aerial vehicle‐sink enabled mobility model for military operations in sparse flying ad‐hoc network

Agrawal, Juhi; Kapoor, Monit; Tomar, Ravi

doi:10.1002/ett.4466

Cited by 5 publications

(3 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the sake of effective comparison, four algorithms, RWP [ 36 ], PSO, TARFC, and TA&CRFO, are respectively implemented under the condition that the values of all parameters are consistent. The simulation process is executed on MATLAB.…”

Section: Resultsmentioning

confidence: 99%

A Low Complexity Persistent Reconnaissance Algorithm for FANET

Guo

Tang

Qin

2022

Sensors

View full text Add to dashboard Cite

In recent years, with the rapid progress of unmanned aerial vehicle (UAV) technology, UAV-based systems have been widely used in both civilian and military applications. Researchers have proposed various network architectures and routing protocols to address the network connectivity problems associated with the high mobility of UAVs, and have achieved considerable results in a flying ad hoc network (FANET). Although scholars have noted various threats to UAVs in practical applications, such as local magnetic field variation, acoustic interference, and radio signal hijacking, few studies have taken into account the dynamic nature of these threat factors. Moreover, the UAVs’ high mobility combined with dynamic threats makes it more challenging to ensure connectivity while adapting to ever-changing scenarios. In this context, this paper introduces the concept of threat probability density function (threat PDF) and proposes a particle swarm optimization (PSO)-based threat avoidance and reconnaissance FANET construction algorithm (TARFC), which enables UAVs to dynamically adapt to avoid high-risk areas while maintaining FANET connectivity. Inspired by the graph editing distance, the total edit distance (TED) is defined to describe the alterations of the FANET and threat factors over time. Based on TED, a dynamic threat avoidance and continuous reconnaissance FANET operation algorithm (TA&CRFO) is proposed to realize semi-distributed control of the network. Simulation results show that both TARFC and TA&CRFO are effective in maintaining network connectivity and avoiding threats in dynamic scenarios. The average threat value of UAVs using TARFC and TA&CRFO is reduced by 3.99~27.51% and 3.07~26.63%, respectively, compared with the PSO algorithm. In addition, with limited distributed moderation, the complexity of the TA&CRFO algorithm is only 20.08% of that of TARFC.

show abstract

Section: Resultsmentioning

confidence: 99%

A Low Complexity Persistent Reconnaissance Algorithm for FANET

Guo

Tang

Qin

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Беспилотные летательные аппараты (БПЛА) активно используются в различных прикладных областях [Cruz, 2018;Agrawal, Tomar, Kapoor, 2022]. БПЛА могут успешно применяться в поисково-спасательных операциях для решения задач мониторинга территорий, подвергшихся деструктивным воздействиям.…”

Section: Introductionunclassified

Управление Передачей Видеопотоков В Летающей Беспроводной Самоорганизующейся Сети

Лихошерстов,

Польщиков,

Лазарев

2024

ЭИ

View full text Add to dashboard Cite

Статья посвящена совершенствованию видеомониторинга территорий, осуществляемого на основе применения летающей беспроводной самоорганизующейся сети (Flying Ad hoc NETwork, FANET). Видеомониторинг проводится в поисково-спасательных целях. Для обеспечения высокого качества FANET-видеотрансляции предложен алгоритм поддержки принятия решений по управлению передачей видеопотоков. Алгоритм предусматривает оценивание вероятности обеспечения высокого качества видеотрансляции. В зависимости от значений этой вероятности рекомендуется одно из следующих решений: передавать новый видеопоток, сократить среднюю длину беспроводных каналов или отключить передачу малоинформативного видеопотока. В статье предложено считать, что принято правильное решение по управлению характеристиками передачи видеопотоков, если в результате его принятия обеспечено высокое качество видеотрансляции. Результаты вычислительных экспериментов показали, что применение представленного алгоритма позволяет существенно повысить вероятность принятия правильного решения по управлению передачей видеопотоков в FANET.

show abstract

“…The engagement of multiple UAVs enables flexible task assignment, coordinated working methods, and collaborative operation that is fault-tolerant [5]. FANETs are employed in a variety of settings, including civilian [6], military [7], industrial [8], and commercial applications [9]. They are favored because of their robustness [10], adaptability [11], low running costs [12], and ease of construction [13].…”

Section: Introductionmentioning

confidence: 99%

Reinforcement-Based Clustering in Flying Ad-Hoc Networks for Serving Vertical and Horizontal Routing

Abdulhae,

Mandeep,

Islam

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) are receiving increasing attention due to their wide range of applications. Flying ad-hoc networks (FANETs) enable inter-communication between UAVs, but their dynamics and fast changes in mobility and topology make it challenging to achieve stable routing. Clustering based FANETs provide a self-organizing approach for routing, but clustering is a decentralized process based on different utilities that can affect performance. In this work, we propose a centralized agent placed in a remote ground station to adjust the role of each utility in the cluster-head arbitration. Our approach uses six utilities, including node centrality, residual energy, link holding time, velocity similarity, buffer occupancy, and diversity. The developed reinforcement learning (RL)-clustering approach enables routing over multiple planes, with each plane representing a network cell with a different coverage radius of nodes, including Femto, Pico, and Micro planes. We propose a novel reward formulation for effective learning of agents that includes indicators of stability based on role change, energy consumption, and confirmation message through the selected node. For evaluation, the developed RL based agent was evaluated on three types of agents, namely, Q-learning, DQN, and DDPG and it was compared with random agent. Results have shown the superiority of our developed RL based clustering in terms of stability, energy consumption and most network metrics.

show abstract

A novel unmanned aerial vehicle‐sink enabled mobility model for military operations in sparse flying ad‐hoc network

Cited by 5 publications

References 57 publications

A Low Complexity Persistent Reconnaissance Algorithm for FANET

A Low Complexity Persistent Reconnaissance Algorithm for FANET

Управление Передачей Видеопотоков В Летающей Беспроводной Самоорганизующейся Сети

Reinforcement-Based Clustering in Flying Ad-Hoc Networks for Serving Vertical and Horizontal Routing

Contact Info

Product

Resources

About