Heuristic for Edge-enabled Network Slicing Optimization using the “Power of Two Choices”

Esteves, Jose Jurandir Alves; Boubendir, Amina; Guillemin, Fabrice; Sens, Pierre

doi:10.23919/cnsm50824.2020.9269099

Cited by 21 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that the 5G Best Effort scenario we chose is characterized by a higher degree of flexibility and fewer constraints compared to other scenarios like ultra-reliable lowlatency communication (URLLC) and enhanced Mobile Broadband (eMBB). Our selection aligns with the criteria outlined by experts such as [77] and [78] and accurately represents a mixture of applications with diverse Quality of Service (QoS) requirements.…”

Section: Evaluating the Ensemblementioning

confidence: 99%

“…Our study assumed a small-scale infrastructure within each domain, typically accommodating up to ten nodes. In terms of network size, we followed the reference in [79], which suggested a network scale akin to that of operators like Orange Labs 5 . The network encompasses various types of data centers, including nodes from the core network, cloud, and edge.…”

Section: Evaluating the Ensemblementioning

confidence: 99%

See 1 more Smart Citation

An Online Ensemble Method for Auto-scaling NFV-based Applications in the Edge

Silva,

Batista,

Delicato

et al. 2023

Preprint

View full text Add to dashboard Cite

The synergy of edge computing and Machine Learning (ML) holds immense potential for revolutionizing Internet of Things (IoT) applications, particularly in scenarios characterized by high-speed, continuous data generation. Offline ML algorithms are unsuitable for data streams, as they require existing datasets to build prediction models. As an embodiment of ML, which embraces the fact that learning environments change over time, in Online Machine Learning (OML) the model is trained with each new observation in production time. Most OML algorithms are developed after the offline version and present different behaviors, considering bias and variance. Finding a suitable estimator to solve a ML problem is still a challenge. In this context, ensemble learning emerges as a promising approach for balancing the bias-variance tradeoff and improving prediction accuracy by aggregating outputs from multiple ML models. This paper introduces a novel ensemble method tailored for edge computing environments, designed to efficiently operate on resource-constrained devices while accommodating various online learning scenarios. The primary objective is to enhance predictive accuracy at the edge. We conducted extensive experimental evaluations to assess our proposed ensemble's predictive performance using synthetic and real datasets. Our ensemble outperformed state-of-the-art data stream algorithms and ensemble regressors across various regression metrics. Furthermore, we evaluated the ensemble's performance in the context of auto-scaling for Virtual Network Function (VNF)-based applications operating at the network's edge.

show abstract

Section: Evaluating the Ensemblementioning

confidence: 99%

Section: Evaluating the Ensemblementioning

confidence: 99%

An Online Ensemble Method for Auto-scaling NFV-based Applications in the Edge

Silva,

Batista,

Delicato

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Similarly, Ref. [32] proposed a novel method of realizing E2E network slicing by jointly addressing the requirements of physical network and locations of users. In particular, their algorithm utilizes Dijkstra's shortest path algorithm to choose the servers with fewer bandwidth usages for the placement of VNFs and to calculate a feasible path with a minimum bandwidth consumption.…”

Section: Edge Enabled Network Slicing Without Slice Isolationmentioning

confidence: 99%

Integration of Network Slicing and Machine Learning into Edge Networks for Low-Latency Services in 5G and beyond Systems

2022

View full text Add to dashboard Cite

Fifth-generation (5G) and beyond networks are envisioned to serve multiple emerging applications having diverse and strict quality of service (QoS) requirements. To meet ultra-reliable and low latency communication, real-time data processing and massive device connectivity demands of the new services, network slicing and edge computing, are envisioned as key enabling technologies. Network slicing will prioritize virtualized and dedicated logical networks over common physical infrastructure and encourage flexible and scalable networks. On the other hand, edge computing offers storage and computational resources at the edge of networks, hence providing real-time, high-bandwidth, low-latency access to radio network resources. As the integration of two technologies delivers network capabilities more efficiently and effectively, this paper provides a comprehensive study on edge-enabled network slicing frameworks and potential solutions with example use cases. In addition, this article further elaborated on the application of machine learning in edge-sliced networks and discussed some recent works as well as example deployment scenarios. Furthermore, to reveal the benefits of these systems further, a novel framework based on reinforcement learning for controller synchronization in distributed edge sliced networks is proposed.

show abstract

“…Leveraging appropriate inter-relations between computational resources and network paths and applying column generation (CG), we are able to find exact solutions for real-sized networks. Thanks to our joint approach, we get rid of restrictive assumptions used in previous work which either consider that all the resources to allocate are known a priori (e.g., by allocating a fixed amount of CPU to match the a-priori known demand) [2]- [6], or formalize the routing problem as a multi-commodity flow problem and assume that the "destination node" is fixed and determined a-priori [7], [8].…”

Section: Introductionmentioning

confidence: 99%

“…Second, we fully leverage the flexibility of virtualized networks and let the PNO decide the placement of software components, as well as which nodes to activate/deactivate to minimize energy consumption. Moreover, while latency constraints are usually expressed in terms of mean delay [2] [9], we model SLAs by considering a maximum latency threshold and the corresponding level of reliability, i.e., the minimum fraction of time where the threshold must be met.…”

Section: Introductionmentioning

confidence: 99%

Joint Placement, Routing and Dimensioning at the Network Edge for Energy Minimization

Elkael,

Araldo,

D'Oro

et al. 2023

GLOBECOM 2023 - 2023 IEEE Global Communications Conference

View full text Add to dashboard Cite

Thanks to resource virtualization, Physical Network Operators (PNOs) can share their 5G network to multiple Mobile Virtual Network Operators (MVNOs) which can leverage the shared physical infrastructure to deploy their services up to the edge. This allows much more flexibility with respect to the previous generation of cellular networks: MVNO software components can be placed at different locations, can be allocated a certain amount of virtual resources (e.g., bandwidth, CPU cycles), and be reachable via different paths. To the best of our knowledge, strategies to minimize energy consumption while satisfying Service Level Agreements (SLAs) between the PNO and the MVNOs are still largely missing, particularly if it is required to take the nonlinearity of delays into account. To fill this gap, we formulate the problem of joint placement of software components, routing of user requests and resource dimensioning. SLAs are represented in terms of latency and reliability constraints. Via Column Generation, we obtain exact solutions in real-sized networks. Our numerical results show that we can save up to 50% energy in networks with up to 30 nodes compared to the state-of-the-art algorithms, which are focused on placement or resource minimization.

show abstract

Heuristic for Edge-enabled Network Slicing Optimization using the “Power of Two Choices”

Cited by 21 publications

References 22 publications

An Online Ensemble Method for Auto-scaling NFV-based Applications in the Edge

An Online Ensemble Method for Auto-scaling NFV-based Applications in the Edge

Integration of Network Slicing and Machine Learning into Edge Networks for Low-Latency Services in 5G and beyond Systems

Joint Placement, Routing and Dimensioning at the Network Edge for Energy Minimization

Contact Info

Product

Resources

About