Smart Packet Transmission Scheduling in Cognitive IoT Systems: DDQN Based Approach

Salh, Adeeb; Audah, Lukman; Kim, Kwang Soon; Alsamhi, Saeed Hamood; Alhartomi, Mohammed A.; Almalki, Faris A.; Abdullah, Qazwan; Saif, Abdu; Algethami, Haneen

doi:10.1109/access.2022.3168549

Cited by 29 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Industry 5.0 Industry 5.0 is a manufacturing paradigm change that prioritizes human-machine interaction. It has emerged due to advances in AI, distributed computing, and B5G connectivity [189,190], and it is likely to accelerate even further with the inclusion of supporting technologies such as FL and industrial edge computing [191]. In addition, industry 5.0 will minimize latency, boost overall data security and privacy, increase efficiency, and support transactions hindered by limited connection thanks to the development of UAV computing [192].…”

Section: B5g Networkmentioning

confidence: 99%

Computing in the Sky: A Survey on Intelligent Ubiquitous Computing for UAV-Assisted 6G Networks and Industry 4.0/5.0

Alsamhi

Shvetsov

Kumar

et al. 2022

Drones

Self Cite

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs) are increasingly being used in a high-computation paradigm enabled with smart applications in the Beyond Fifth Generation (B5G) wireless communication networks. These networks have an avenue for generating a considerable amount of heterogeneous data by the expanding number of Internet of Things (IoT) devices in smart environments. However, storing and processing massive data with limited computational capability and energy availability at local nodes in the IoT network has been a significant difficulty, mainly when deploying Artificial Intelligence (AI) techniques to extract discriminatory information from the massive amount of data for different tasks.Therefore, Mobile Edge Computing (MEC) has evolved as a promising computing paradigm leveraged with efficient technology to improve the quality of services of edge devices and network performance better than cloud computing networks, addressing challenging problems of latency and computation-intensive offloading in a UAV-assisted framework. This paper provides a comprehensive review of intelligent UAV computing technology to enable 6G networks over smart environments. We highlight the utility of UAV computing and the critical role of Federated Learning (FL) in meeting the challenges related to energy, security, task offloading, and latency of IoT data in smart environments. We present the reader with an insight into UAV computing, advantages, applications, and challenges that can provide helpful guidance for future research.

show abstract

Section: B5g Networkmentioning

confidence: 99%

Computing in the Sky: A Survey on Intelligent Ubiquitous Computing for UAV-Assisted 6G Networks and Industry 4.0/5.0

Alsamhi

Shvetsov

Kumar

et al. 2022

Drones

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, in the ultra-reliable and lowlatency communications (URLLC) scenario, the round trip delay between a sender and a receiver can reach 1 ms [19], [36]. However, random traffic loads from a large number of devices may cause serious network congestion and severe packet loss, and the stringent QoS requirements of delay and reliability will not be satisfied [19], [20], [36]. In this regard, we elaborate on network uncertainty, followed by effective RL-based strategies.…”

Section: A System Descriptionmentioning

confidence: 99%

“…To abstract, allocate, and optimize resources, the joint resource orchestration strategy is learned by the double dueling DQN algorithm with the aid of the SDN controller and NFV. Similar to the multihidden-layer neural network design in [20], [174] for URLLC-enabled IoT applications, an advanced multilayer convolutional neural network is proposed to improve the learning efficiency. Owing to the dynamic crowd in various sectors of smart cities, the double DQN-based smart routing algorithm was devised to reduce network congestion and balance the network workload in [169].…”

Section: General Iot Applicationsmentioning

confidence: 99%

“…As the number of smart devices is dramatically increasing in diverse 5G and beyond network scenarios (e.g., smart factory, smart home, and smart city) shown in Fig. 1, with various applications such as VR/AR/XR, digital twin, and autonomous driving [9], [11], [15], [16], MEC is envisioned to play an important role in satisfying the high-quality requirements of computation-intensive businesses [9], [11] and low-latency applications [17]- [20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence

Wei

Guo

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Mobile edge computing (MEC) is considered a novel paradigm for computation-intensive and delay-sensitive tasks in fifth generation (5G) networks and beyond. However, its uncertainty, referred to as dynamic and randomness, from the mobile device, wireless channel, and edge network sides, results in high-dimensional, nonconvex, nonlinear, and NP-hard optimization problems. Thanks to the evolved reinforcement learning (RL), upon iteratively interacting with the dynamic and random environment, its trained agent can intelligently obtain the optimal policy in MEC. Furthermore, its evolved versions, such as deep reinforcement learning (DRL), can achieve higher convergence speed efficiency and learning accuracy based on the parametric approximation for the large-scale state-action space. This paper provides a comprehensive research review on RL-enabled MEC and offers insight for development in this area. More importantly, associated with free mobility, dynamic channels, and distributed services, the MEC challenges that can be solved by different kinds of RL algorithms are identified, followed by how they can be solved by RL solutions in diverse mobile applications. Finally, the open challenges are discussed to provide helpful guidance for future research in RL training and learning MEC. INDEX TERMS Mobile edge computing (MEC), network uncertainty, reinforcement learning (RL).

show abstract

“…They employed UAVs as aerial base stations for the edge network. Reference [47] presented a smart packet transmission strategy for reward clipping that assures high reliability and excellent packet delivery. To handle intelligent transmission scheduling in cognitive IoT systems, they employed a combined approach of generative adversarial network and deep distribution Q network.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Latency- and Power-Aware Approach for Beyond Fifth-Generation Internet-of-Things Edge Systems

Kaushik

Al-Raweshidy

2022

IEEE Access

View full text Add to dashboard Cite

Fifth-generation (5G) empowered internet of things (IoT) edge networks suffer from latency in delay-sensitive applications. To fulfil the low latency requirements of beyond fifth-generation (B5G)-IoT applications and provide quality of service (QoS) to IoT-edge communication, it is important to minimize server delay. Furthermore, 5G-IoT systems consume more power than their predecessors, which is a concern given the growing size of future IoT networks. This research presents a hybrid latency and power-aware approach for B5G-IoT networks (HLPA B5G-IoT) that minimizes latency with minimum overhead on battery-constrained IoT nodes while simultaneously providing a power-efficient solution for B5G-IoT-edge networks. HLPA B5G-IoT has a novel algorithm classifier tool (ACT) for selecting appropriate optimization algorithms based on the characteristics and requirements of B5G-IoT systems. The ACT matrix not only parametrically compares HLPA B5G-IoT with existing approaches but also identifies crucial parameters that enable algorithm selection for load balancing and energy efficiency. In this paper, metaheuristic algorithms, i.e., biogeography-based optimization (BBO) and grey wolf optimization (GWO), are tailored to meet the requirements of load balancing and power efficiency in IoT-edge systems. The proposed load-balancing algorithm reduces latency and improves overall network performance by 33.33%, 27.45%, 23.52%, 21.56%, 13.72%, 11.76%, and 7.84% compared with simulated annealing (SA), genetic algorithm (GA), particle swarm optimization (PSO), bacteria foraging algorithm (BFA), ant colony optimization (ACO), bat algorithm (BA), and genetic SA PSO (GSP), respectively. The power-efficiency algorithm consumes 46.6%,

show abstract

Smart Packet Transmission Scheduling in Cognitive IoT Systems: DDQN Based Approach

Cited by 29 publications

References 37 publications

Computing in the Sky: A Survey on Intelligent Ubiquitous Computing for UAV-Assisted 6G Networks and Industry 4.0/5.0

Computing in the Sky: A Survey on Intelligent Ubiquitous Computing for UAV-Assisted 6G Networks and Industry 4.0/5.0

Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence

A Hybrid Latency- and Power-Aware Approach for Beyond Fifth-Generation Internet-of-Things Edge Systems

Contact Info

Product

Resources

About