QoS-Aware Machine Learning Task Offloading and Power Control in Internet of Drones

Yao, Jingjing; Ansari, Nirwan

doi:10.1109/jiot.2022.3222968

Cited by 5 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [46], the article explores the joint optimization of machine learning task offloading and wireless power control in fog-aided Internet of Drones (IoD) networks for object recognition services. The authors formulate the problem as a mixed-integer nonlinear programming (MINLP) to minimize average service time under energy constraints.…”

Section: B Related Work On Uav Architecturesmentioning

confidence: 99%

DCM-D2X: An Effective Communication Mobility Model for Decentralized Cooperative Multi-Layer Drone to Everything

Dixit,

Singh

2024

IEEE Access

View full text Add to dashboard Cite

Communication among drones and diverse devices, known as D2X (Drone-to-Everything) communication, faces challenges within traditional drone setups, including routing complexities, interference issues, and susceptibility to single points of failure. These shortcomings hinder network scalability and overall performance. This paper introduces the decentralized cooperative multi-layer drone to everything (DCM-D2X) architecture with integrated hybrid bioinspired grey wolf optimization-waypoint tracking (GWO-WPT) mobility model. DCM-D2X architecture incorporates GWO-WPT mobility patterns that are explicitly integrated for decentralized cooperative multi-layer for effective communication in D2X environments. This model is purposefully integrated and designed to enhance communication efficacy in D2X environments by mitigating single points of failure, optimizing resource allocation, managing interference, and improving cooperative routing. Extensive simulations have been conducted using the optimized link state routing protocol (OLSR) within the network simulator (NS2) to evaluate the proposed architecture and mobility model. Performance metrics, including network diameter, average clustering coefficient, energy consumption, delay, throughput, and packet delivery ratio (PDR), have been assessed. Compared to the latest literature, the proposed model demonstrated an average percentage difference of 19.195% reduction in routing delay, 27.335% reduction in energy consumption, 22.18% increase in packet delivery ratio, 21.25% increase in throughput, and reducing interference up to 23% in high mobility scenarios. The DCM-D2X model demonstrates robustness against node failures in large-scale drone networks, significantly improving interference mitigation, routing efficiency, and network connectivity. These advancements increase D2X communication network performance. INDEX TERMS Drone to Everything (D2X), Flying ad-hoc network (FANET), Grey wolf optimization (GWO), Performance, Single point of failure (SOPF), Unmanned aerial vehicles (UAVs).

show abstract

Section: B Related Work On Uav Architecturesmentioning

confidence: 99%

DCM-D2X: An Effective Communication Mobility Model for Decentralized Cooperative Multi-Layer Drone to Everything

Dixit,

Singh

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…On the other hand, surveillance and secure monitoring are considered as critical tasks in smart buildings; these tasks can be supported by heterogeneous mobile robots, drones, UAVs (Unmanned Aerial Vehicles), IoT devices, and intelligent components [ 16 , 17 , 18 , 19 , 20 , 21 , 22 ]. To provide reinforced surveillance and secure monitoring, the concept of a barrier can be applied to smart buildings because the formation of a barrier and its creation guarantee that any penetrations or mobile objects are detected by system members in the built surveillance barriers within the requested three-dimensional space and plane area [ 23 , 24 , 25 , 26 , 27 , 28 , 29 ].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Smart Building Surveillance Systems in Thin Walls: An Efficient Barrier Design

Lee,

Kim

2024

Sensors

View full text Add to dashboard Cite

This paper introduces an efficient barrier model for enhancing smart building surveillance in harsh environment with thin walls and structures. After the main research problem of minimizing the total number of wall-recognition surveillance barriers, we propose two distinct algorithms, Centralized Node Deployment and Adaptation Node Deployment, which are designed to address the challenge by strategic placement of surveillance nodes within the smart building. The Centralized Node Deployment aligns nodes along the thin walls, ensuring consistent communication coverage and effectively countering potential disruptions. Conversely, the Adaptation Node Deployment begins with random node placement, which adapts over time to ensure efficient communication across the building. The novelty of this work is in designing a novel barrier system to achieve energy efficiency and reinforced surveillance in a thin-wall environment. Instead of a real environment, we use an ad hoc server for simulations with various scenarios and parameters. Then, two different algorithms are executed through those simulation environments and settings. Also, with detailed discussions, we provide the performance analysis, which shows that both algorithms deliver similar performance metrics over extended periods, indicating their suitability for long-term operation in smart infrastructure.

show abstract

Energy-Efficient Federated Knowledge Distillation Learning in Internet of Drones

Cal,

Sun,

Yao

2024

2024 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

QoS-Aware Machine Learning Task Offloading and Power Control in Internet of Drones

Cited by 5 publications

References 41 publications

DCM-D2X: An Effective Communication Mobility Model for Decentralized Cooperative Multi-Layer Drone to Everything

DCM-D2X: An Effective Communication Mobility Model for Decentralized Cooperative Multi-Layer Drone to Everything

Enhancing Smart Building Surveillance Systems in Thin Walls: An Efficient Barrier Design

Energy-Efficient Federated Knowledge Distillation Learning in Internet of Drones

Contact Info

Product

Resources

About