A Utility-Driven Multi-Queue Admission Control Solution for Network Slicing

Han, Bin; Sciancalepore, Vincenzo; Feng, Di; Costa‐Pérez, Xavier; Schotten, Hans D.

doi:10.1109/infocom.2019.8737517

Cited by 57 publications

(31 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In SJAP, we consider a scenario where the request time R t for a job Q i measured on the basis of the waiting processes Q inprocess . Therefore, in order to get selected for admission in SJAP queue, a request must satisfy the condition of R t > Q inprocess and is similar to [45] except that it does not perform the slicing for function isolation.…”

Section: • Smart Job Admission Policy (Sjap)mentioning

confidence: 99%

Bouncer: A Resource-Aware Admission Control Scheme for Cloud Services

et al. 2019

View full text Add to dashboard Cite

Cloud computing is a paradigm that ensures the flexible, convenient and on-demand provisioning of a shared pool of configurable network and computing resources. Its services can be offered by either private or public infrastructures, depending on who owns the operational infrastructure. Much research has been conducted to improve a cloud’s resource provisioning techniques. Unfortunately, sometimes an abrupt increase in the demand for cloud services results in resource shortages affecting both providers and consumers. This uncertainty of resource demands by users can lead to catastrophic failures of cloud systems, thus reducing the number of accepted service requests. In this paper, we present Bouncer—a workload admission control scheme for cloud services. Bouncer works by ensuring that cloud services do not exceed the cloud infrastructure’s threshold capacity. By adopting an application-aware approach, we implemented Bouncer on software-defined network (SDN) infrastructure. Furthermore, we conduct an extensive study to evaluate our framework’s performance. Our evaluation shows that Bouncer significantly outperforms the conventional service admission control schemes, which are still state of the art.

show abstract

Section: • Smart Job Admission Policy (Sjap)mentioning

confidence: 99%

Bouncer: A Resource-Aware Admission Control Scheme for Cloud Services

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Lately, we have seen a deluge of algorithms to efficiently slice portions of the network and instantiate service-specific slices. These solutions leverage optimization [2,7,27,28,48], game-theory [10,14,33] and machine learning [52] tools.…”

Section: Related Workmentioning

confidence: 99%

Sl-edge

D’Oro

Bonati

Restuccia

et al. 2020

Proceedings of the Twenty-First International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Netw

View full text Add to dashboard Cite

Network slicing of multi-access edge computing (MEC) resources is expected to be a pivotal technology to the success of 5G networks and beyond. The key challenge that sets MEC slicing apart from traditional resource allocation problems is that edge nodes depend on tightly-intertwined and strictly-constrained networking, computation and storage resources. Therefore, instantiating MEC slices without incurring in resource over-provisioning is hardly addressable with existing slicing algorithms. The main innovation of this paper is SlEDGE , a unified MEC slicing framework that allows network operators to instantiate heterogeneous slice services (e.g., video streaming, caching, 5G network access) on edge devices. We first describe the architecture and operations of SlEDGE , and then show that the problem of optimally instantiating joint network-MEC slices is NP-hard. Thus, we propose near-optimal algorithms that leverage key similarities among edge nodes and resource virtualization to instantiate heterogeneous slices 7.5x faster and within 25% of the optimum. We first assess the performance of our algorithms through extensive numerical analysis, and show that SlEDGE instantiates slices 6x more efficiently then state-ofthe-art MEC slicing algorithms. Furthermore, experimental results on a 24-radio testbed with 9 smartphones demonstrate that SlEDGE provides simultaneously highly-efficient slicing of joint LTE connectivity, video streaming over WiFi, and ffmpeg video transcoding.

show abstract

“…Some of the literature refers to approaches where incoming network slice requests are put into one or multiple queues when not enough resources are available in the network. For example, the authors in [7] consider a number of heterogeneous queues (i.e., different queues for different request priorities) and devise a multiqueuing controller for slice admission that maximizes the overall network utilization. The performance of the proposed controller is benchmarked against two simple strategies, i.e., first-come-first-served and slice-type-based approaches.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The application of RL-based algorithms for improving the performance of communication networks has recently gained interest from both academia and industry. Most of these works focus on resource scheduling [5,6,7] and/or assignment optimization problems [8,2]. On the other hand, to the best of our knowledge, there are no works that apply RL to solve the slice admission problem.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning for Slicing in a 5G Flexible RAN

Raza

Natalino

Öhlen

et al. 2019

J. Lightwave Technol.

View full text Add to dashboard Cite

Network slicing enables an infrastructure provider (InP) to support heterogeneous 5G services over a common platform (i.e., by creating a customized slice for each service). Once in operation, slices can be dynamically scaled up/down to match the variation of their service requirements. An InP generates revenue by accepting a slice request. If a slice cannot be scaled up when required, an InP has to also pay a penalty (proportional to the level of service degradation). It becomes then crucial for an InP to decide which slice requests should be accepted/rejected in order to increase its net profit. This paper presents a slice admission strategy based on reinforcement learning (RL) in the presence of services with different priorities. The use case considered is a 5G flexible radio access network (RAN), where slices of different mobile service providers are virtualized over the same RAN infrastructure. The proposed policy learns which are the services with the potential to bring high profit (i.e., high revenue with low degradation penalty), and hence should be accepted. The performance of the RL-based admission policy is compared against two deterministic heuristics. Results show that in the considered scenario, the proposed strategy outperforms the benchmark heuristics by at least 55%. Moreover, this paper shows how the policy is able to adapt to different conditions in terms of: (i) slice degradation penalty vs. slice revenue factors, and (ii) proportion of high vs. low priority services.

show abstract

A Utility-Driven Multi-Queue Admission Control Solution for Network Slicing

Cited by 57 publications

References 24 publications

Bouncer: A Resource-Aware Admission Control Scheme for Cloud Services

Bouncer: A Resource-Aware Admission Control Scheme for Cloud Services

Sl-edge

Reinforcement Learning for Slicing in a 5G Flexible RAN

Contact Info

Product

Resources

About