Slice-Based Service Function Chain Embedding for End-to-End Network Slice Deployment

Li, Hang; Kong, Zixuan; Chen, Yawen; Wang, Luhan; Lu, Zhaoming; Wen, Xiangming; Jing, Wenpeng; Xiang, Wan

doi:10.1109/tnsm.2023.3250719

Cited by 14 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under the mobility of mobile robots and unreliable environments of the STIN, Wei et al [31] employ a Lyapunov optimization-based decomposition and a dual-agent Q-Learning algorithm to solve a joint problem of task offloading, velocity control, and service migration. Considering the mobility of satellites and limited on-board resources, a DRL-based approach is proposed in [32] to solve the service deployment problem. However, these studies lack exploration of the inter-satellite cooperation to fully utilize the available on-board resources in case of load imbalance on satellite networks.…”

Section: B Task Offloading With Service Migration For Secmentioning

confidence: 99%

See 1 more Smart Citation

Task Offloading With Service Migration for Satellite Edge Computing: A Deep Reinforcement Learning Approach

Wu,

Yang,

2024

IEEE Access

View full text Add to dashboard Cite

Satellite networks with edge computing servers promise to provide ubiquitous and low-latency computing services for the Internet of Things (IoT) applications in the future satellite-terrestrial integrated network (STIN). For some emerging IoT applications, the services require real-time user-dependent state information, such as time-varying task states and user-specific configurations, to maintain service continuity. Service migration is crucial for dynamic task offloading to synchronize the user-dependent state information between computing servers. However, how to offload computing tasks at low latency with the impact of service migration remains challenging due to the high-speed movement and load imbalance of low Earth orbit (LEO) satellite networks. In this work, we investigate the task offloading problem with service migration for satellite edge computing (SEC) using inter-satellite cooperation. Facing dynamic service requirements with limited on-board bandwidth, energy, and storage resources of satellite networks, we formulate the problem with the aim of minimizing the service delay to optimize the offloading path selection. By leveraging a deep reinforcement learning (DRL) approach, we propose a distributed scheme based on the Dueling-Double-Deep-Q-Learning (D3QN) algorithm. Simulation results show that the proposed scheme can effectively reduce the service delay, and outperform the benchmark algorithms.INDEX TERMS Satellite edge computing (SEC), task offloading, service migration, deep reinforcement learning (DRL).

show abstract

Section: B Task Offloading With Service Migration For Secmentioning

confidence: 99%

“…These studies assume that the services are already on the offloading nodes, without service migration. Some researchers consider service migration since it significantly affects the system performance [29]- [32]. However, using inter-satellite cooperation for service migration still needs further research.…”

mentioning

confidence: 99%

Task Offloading With Service Migration for Satellite Edge Computing: A Deep Reinforcement Learning Approach

Wu,

Yang,

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A Network Slice is a logical network on a shared infrastructure that provides specific network capabilities and characteristics, supporting various service properties for the customers of the network slicing. Network slices are generally made up of sets of network slice subnets, the network slice subnets are then made up of Virtualized Network Functions (Li et al, 2023).…”

Section: Network Slicing and Network Function Virtualisationmentioning

confidence: 99%

Blockchain-Based Security Framework for VNF Package Protection in 5G Network Slicing Services

Boukessessa,

Ghazli,

Ali-Pacha

2024

Transport and Telecommunication Journal

View full text Add to dashboard Cite

The demand for scalable, open and granular networks has enabled mobile networks such as 5G to adopt new concepts including NFV (Network Function Virtualization). NFV separates the dependency of network functions from the hardware component, allowing them to be deployed flexibly and dynamically across network slices. In this way, operators can deliver personalized services and optimize the use of network resources, contributing to greater operational efficiency and an enhanced end-user experience. However, there are several issues to be addressed, such as the security of VNFs and the way in which service provider customers instantiate NSSIs (Network Slice Subnet Instance). In this article, we present a new approach based on blockchain 2.0, which guarantees the immutability of VNFs and templates, as well as highly secure instantiation with access management and support for replay attacks.

show abstract

“…• NSDP: using the original model from [4] (equations (2) to (11) in addition to connectivity-related constraints Fig. 6: Mandala topology [4].…”

Section: Numerical Evaluationmentioning

confidence: 99%

“…A NFS can be a function from the radio-access network, the core network or any NF (e.g., proxy, firewall, etc.). Network slicing has attracted a lot of interest from both academia and industry where several challenges are addressed considering the management architecture [9], network design [4], [10], [11] and resource management [12], [13], [14], among others. In [9] the authors propose 6GLEGO which is an end-to-end orchestration framework for beyond-5G and 6G networks to overcome the limitations of the ETSI-NFV MANO orchestrator [15].…”

Section: Introductionmentioning

confidence: 99%

Network Slice Robustness with Function Sets

Yellas,

Choi,

Chemouil

et al. 2024

NOMS 2024-2024 IEEE Network Operations and Management Symposium

View full text Add to dashboard Cite

Slice-Based Service Function Chain Embedding for End-to-End Network Slice Deployment

Cited by 14 publications

References 45 publications

Task Offloading With Service Migration for Satellite Edge Computing: A Deep Reinforcement Learning Approach

Task Offloading With Service Migration for Satellite Edge Computing: A Deep Reinforcement Learning Approach

Blockchain-Based Security Framework for VNF Package Protection in 5G Network Slicing Services

Network Slice Robustness with Function Sets

Contact Info

Product

Resources

About