Priority/Demand-Based Resource Management with Intelligent O-RAN for Energy-Aware Industrial Internet of Things DOI Open Access
Seyha Ros, Seungwoo Kang, Inseok Song

et al.

Processes, Journal Year: 2024, Volume and Issue: 12(12), P. 2674 - 2674

Published: Nov. 27, 2024

The last decade has witnessed the explosive growth of internet things (IoT), demonstrating utilization ubiquitous sensing and computation services. Hence, industrial IoT (IIoT) is integrated into devices. IIoT concerned with limitation battery life. Therefore, mobile edge computing (MEC) a paradigm that enables proliferation resource reduces network communication latency to realize perspective. Furthermore, an open radio access (O-RAN) new architecture adopts MEC server offer provisioning framework address energy efficiency reduce congestion window IIoT. However, dynamic continuity task generation by lead challenges in management orchestration (MANO) efficiency. In this article, we aim investigate priority on demand. Additionally, minimize long-term average delay resource-intensive tasks, Markov decision problem (MDP) conducted solve problem. deep reinforcement learning (DRL) optimal handling policy for MEC-enabled O-RAN architectures. study, MDP-assisted q-network-based priority/demanding management, namely DQG-PD, been investigated optimizing management. DQG-PD algorithm aims devices, which demonstrates exploiting Q-network (DQN) jointly optimizes each service request. DQN divided online target networks better adapt environment. Finally, our experiment shows work can outperform reference schemes terms resources, cost, energy, reliability, completion ratio.

Language: Английский

Enhancing Network Slicing Security: Machine Learning, Software-Defined Networking, and Network Functions Virtualization-Driven Strategies DOI Creative Commons
José Cunha, Pedro Ferreira, Eva M. Castro Barbero

et al.

Future Internet, Journal Year: 2024, Volume and Issue: 16(7), P. 226 - 226

Published: June 27, 2024

The rapid development of 5G networks and the anticipation 6G technologies have ushered in an era highly customizable network environments facilitated by innovative concept slicing. This technology allows creation multiple virtual on same physical infrastructure, each optimized for specific service requirements. Despite its numerous benefits, slicing introduces significant security vulnerabilities that must be addressed to prevent exploitation increasingly sophisticated cyber threats. review explores application cutting-edge technologies—Artificial Intelligence (AI), specifically Machine Learning (ML), Software-Defined Networking (SDN), Network Functions Virtualization (NFV)—in crafting advanced solutions tailored AI’s predictive threat detection automated response capabilities are analysed, highlighting role maintaining integrity resilience. Meanwhile, SDN NFV scrutinized their ability enforce flexible policies manage functionalities dynamically, thereby enhancing adaptability measures meet evolving demands. Thoroughly examining current literature industry practices, this paper identifies critical research gaps frameworks proposes solutions. We advocate a holistic strategy integrating ML, SDN, enhance data confidentiality, integrity, availability across slices. concludes with future directions develop robust, scalable, efficient capable supporting safe deployment next-generation networks.

Language: Английский

Citations

6
A Novel Framework for Cross-Cluster Scaling in Cloud-Native 5G NextGen Core DOI Creative Commons
Oana-Mihaela Dumitru-Guzu, Călin Vlădeanu, Robert E. Kooij

et al.

Future Internet, Journal Year: 2024, Volume and Issue: 16(9), P. 325 - 325

Published: Sept. 6, 2024

Cloud-native technologies are widely considered the ideal candidates for future of vertical application development due to their boost in flexibility, scalability, and especially cost efficiency. Since multi-site support is paramount 5G, we employ a multi-cluster model that scales on demand, shifting boundaries both horizontal scaling shared resources. Our approach based liquid computing paradigm, which has benefit adapting changing environment. Despite being decentralized deployment across data centers, 5G mobile core can be managed as single cluster entity running public cloud. We achieve this by following cloud-native patterns declarative configuration Kubernetes APIs on-demand resource allocation. Moreover, our setup, analyze offloading Open5GS user control plane functions under two different peering scenarios. A significant improvement terms latency throughput achieved in-band peering, considering traffic between clusters ensured Liqo through VPN tunnel. also validate three end-to-end network slicing use cases, showcasing full automation leveraging capabilities deployments inter-service monitoring applied service mesh solution.

Language: Английский

Citations

0
Priority/Demand-Based Resource Management with Intelligent O-RAN for Energy-Aware Industrial Internet of Things DOI Open Access
Seyha Ros, Seungwoo Kang, Inseok Song

et al.

Processes, Journal Year: 2024, Volume and Issue: 12(12), P. 2674 - 2674

Published: Nov. 27, 2024

The last decade has witnessed the explosive growth of internet things (IoT), demonstrating utilization ubiquitous sensing and computation services. Hence, industrial IoT (IIoT) is integrated into devices. IIoT concerned with limitation battery life. Therefore, mobile edge computing (MEC) a paradigm that enables proliferation resource reduces network communication latency to realize perspective. Furthermore, an open radio access (O-RAN) new architecture adopts MEC server offer provisioning framework address energy efficiency reduce congestion window IIoT. However, dynamic continuity task generation by lead challenges in management orchestration (MANO) efficiency. In this article, we aim investigate priority on demand. Additionally, minimize long-term average delay resource-intensive tasks, Markov decision problem (MDP) conducted solve problem. deep reinforcement learning (DRL) optimal handling policy for MEC-enabled O-RAN architectures. study, MDP-assisted q-network-based priority/demanding management, namely DQG-PD, been investigated optimizing management. DQG-PD algorithm aims devices, which demonstrates exploiting Q-network (DQN) jointly optimizes each service request. DQN divided online target networks better adapt environment. Finally, our experiment shows work can outperform reference schemes terms resources, cost, energy, reliability, completion ratio.

Language: Английский

Citations

0