Estimating VNF Resource Requirements Using Machine Learning Techniques

Jmila, Houda; Khedher, Mohamed Ibn; Yacoubi, Mounîm El

doi:10.1007/978-3-319-70087-8_90

Cited by 27 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The work of [36] by Jmila et al adapts SVR to estimate VNF resource requirements by predicting the CPU demand of incoming traffic. The authors compare their results against those of an Artificial Neural Network (ANN) and shown that SVR outperformes ANN in terms of both accuracy and stability.…”

Section: B Ml-based Approachesmentioning

confidence: 99%

End-to-End Performance-Based Autonomous VNF Placement With Adopted Reinforcement Learning

Bunyakitanon

Vasilakos

Nejabati

et al. 2020

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

The autonomous placement of Virtual Network Functions (VNFs) is a key aspect of Zero-touch network and Service Management (ZSM) in Fifth Generation (5G) networking. Therefore, current orchestration frameworks need to be enhanced, accordingly. To address this need, this work presents an Adapted REinforcement Learning VNF Performance Prediction module for Autonomous VNF Placement, namely AREL3P. Our solution design bears a dual novelty. First, it leverages end-to-end service-level performance predictions for placing VNFs. Second, whereas the majority of other Machine Learning efforts in the literature use Supervised Learning (SL) techniques, AREL3P is based on a particular form of Reinforcement Learning adapted to predictions. This makes placement decisions more resilient to dynamic conditions, as well as portable to other network nodes, and able to generalize in heterogeneous network environments. Backed by a meticulous performance evaluation over a real 5G end-to-end testbed, we verify the above properties after integrating AREL3P to Open Source Management and Orchestration (OSM MANO) decisions. Among other highlights, we show increased VNF performance predictions accuracy by 40-45%, and an overall improved VNF placement efficiency against other SL benchmarks reflected by near-optimal decision scores in 23 out of a total of 27 investigated scenarios. Index Terms-Machine learning, network function virtualization, end-to-end communication, zero-touch management, cloud and edge computing.

show abstract

Section: B Ml-based Approachesmentioning

confidence: 99%

End-to-End Performance-Based Autonomous VNF Placement With Adopted Reinforcement Learning

Bunyakitanon

Vasilakos

Nejabati

et al. 2020

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…An Artificial Neural Network (ANN) has been applied to learn and build models for the virtual network (VN) based on collected network data. H. Jmila et al [12] have proposed a solution that leverages Support Vector Regression (SVR) to predict the amount of CPU needed to handle the incoming traffic flows.…”

Section: Related Workmentioning

confidence: 99%

Latency-aware Service Placement and Live Migrations in 5G and Beyond Mobile Systems

Mada

Bagaa

Tale

et al. 2020

ICC 2020 - 2020 IEEE International Conference on Communications (ICC)

View full text Add to dashboard Cite

5G system and beyond will build on the network slicing for offering high customizable services with different requirements that run on top of the same shared infrastructure. Each network slice, such as Ultra-Reliable Low latency Communications (URLLC) and Enhanced Mobile Broadband (eMBB), has different requirements that can be even contradicting from a slice to another. A network slice consists of a set of physical or virtual network functions (VNF/PNF) that have various capabilities and run across multiple administrative and cloud domains of different technology. A user can simultaneously request multiple services from different network slices. In this paper, we address the problem of initial placement and live migration of multiple mobile services across centralized and edge cloud by taking into account service types, network conditions and users' mobility features. As a solution to this problem, in this paper, we suggest and evaluate a solution that orchestrates the network services in a cost-efficient way, ensuring that each user could be simultaneously served by multiple slices while perceiving a high QoS and ensuring that the service level agreements (SLAs) of the consumed services are not violated.

show abstract

“…As for another important VNF scenarios, its most challenging task is to meet the continuously varying demands of dynamic algorithm calls, in order to efficiently scale the allocated resources and meet fluctuating needs. After studying the behavior of a VNF as a function of its environment, an SVR (Support Vector Regression) approach was proposed [60] that helped model its resource requirements in order to allocate them dynamically, with greater efficiency and superiority than the state-of-the-art methods.…”

Section: A Resource Management and Allocationmentioning

confidence: 99%

“…Currently, more and more new tools such as ML and MEC are being used to make decisions adaptively and intelligently based on information from a global perspective. Although there are many problems that have not yet been solved, some exploratory, theoretical work has been discussed, such as the modeling of the optimal placement of the intelligent entity in [59], and estimating the CPU needs of VNFs as a function in [60].…”

Section: A Resource Management and Allocationmentioning

confidence: 99%

A Survey of Networking Applications Applying the Software Defined Networking Concept Based on Machine Learning

et al. 2019

View full text Add to dashboard Cite

The main task of future networks is to build, as much as possible, intelligent networking architectures for intellectualization, activation, and customization. Software-defined networking (SDN) technology breaks the tight coupling between the control plane and the data plane in the traditional network architecture, making the controllability, security, and economy of network resources into a reality. As one of the important actualization methods of artificial intelligence (AI), machine learning (ML), combined with SDN architecture will have great potential in areas, such as network resource management, route planning, traffic scheduling, fault diagnosis, and network security. This paper presents the network applications combined with SDN concepts based on ML from two perspectives, namely the perspective of ML algorithms and SDN network applications. From the perspective of ML algorithms, this paper focuses on the applications of classical ML algorithms in SDN-based networks, after a characteristic analysis of algorithms. From the other perspective, after classifying the existing network applications based on the SDN architecture, the related ML solutions are introduced. Finally, the future development of the ML algorithms and SDN concepts is discussed and analyzed. This paper occupies the intersection of the AI, big data, computer networking, and other disciplines; the AI itself is a new and complex interdisciplinary field, which causes the researchers in this field to often have different professional backgrounds and, sometimes, divergent research purposes. This paper is necessary and helpful for researchers from different fields to accurately master the key issues.INDEX TERMS Artificial intelligence, machine learning, network management, software-defined networking.

show abstract

Estimating VNF Resource Requirements Using Machine Learning Techniques

Cited by 27 publications

References 16 publications

End-to-End Performance-Based Autonomous VNF Placement With Adopted Reinforcement Learning

End-to-End Performance-Based Autonomous VNF Placement With Adopted Reinforcement Learning

Latency-aware Service Placement and Live Migrations in 5G and Beyond Mobile Systems

A Survey of Networking Applications Applying the Software Defined Networking Concept Based on Machine Learning

Contact Info

Product

Resources

About