NFV-based Networks Research Articles

Application of Artificial Intelligence and Machine Learning in Software Defined Networks

Abstract Academics and businesses are very interested in using artificial intelligence (AI) and machine learning (ML) to solve the most challenging problems in a variety of fields. This white paper provides a brief overview of key applications of Artificial Intelligence and Machine Learning in SDN- and NFV-based networks. According to their application history, we categorize the most important developments in this field into different groups and identify the relevant AI methods used. It also covers key challenges and the domain’s future course. We highlight the critical role AI/ML can play in opening the door to self-configuring, self-adapting as well as self-managing networks, but research is inadequate due to the difficulties found in this domain.

CoShare: An Efficient Approach for Redundancy Allocation in NFV

An appealing feature of Network Function Virtualization (NFV) is that in an NFV-based network, a network function (NF) instance may be placed at any node. On the one hand this offers great flexibility in allocation of redundant instances, but on the other hand it makes the allocation a unique and difficult challenge. One particular concern is that there is inherent correlation among nodes due to the structure of the network, thus requiring special care in this allocation. To this aim, our novel approach, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CoShare</i> , is proposed. Firstly, its design takes into consideration the effect of network structural dependency, which might result in the unavailability of nodes of a network after failure of a node. Secondly, to efficiently make use of resources, CoShare proposes the idea of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">shared reservation</i> , where multiple flows may be allowed to share the same reserved backup capacity at an NF instance. Furthermore, CoShare factors in the heterogeneity in nodes, NF instances and availability requirements of flows in the design. The results from a number of experiments conducted using realistic network topologies show that the integration of structural dependency allows meeting availability requirements for more flows compared to a baseline approach. Specifically, CoShare is able to meet diverse availability requirements in a resource-efficient manner, requiring, e.g., up to 85% in some studied cases, less resource overbuild than the baseline approach that uses the idea of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dedicated reservation</i> commonly adopted for redundancy allocation in NFV.

Modelling the Admission Ratio in NFV-Based Converged Optical-Wireless 5G Networks

Network Function Virtualization (NFV)-based 5G networks deliver specific services to a end-users through the creation of Service Function Chains (SFCs), which are composed of a number of Virtualized Network Functions (VNFs) interconnected via a set of virtual links (vLinks). VNFs consume computational resources of the network's servers, while vLinks utilize the communicational resources of the network. The efficient utilization of network resources remains a challenge in NFV-based networks. To this end, in this paper, we propose an analytical framework for the Admission Ratio (AR) calculation in NFV-based converged optical-wireless 5G networks. The proposed methodology employs a network slicing architecture in which different network slices form end-to-end logically isolated networks and each slice delivers a specific service type to the users through its SFC(s). In the proposed analysis, we not only take into account the occupancy distribution in both the network's computational and communicational domains (servers and fiber links), but we also consider the SFC establishment AR by taking into account different sub-service-classes belonging to different slices. The accuracy of the model is evaluated through the comparison of analytical and simulation results and was found satisfactory. Furthermore, the proposed model is employed for the determination of the optimal (minimum) capacity for all SFCs elements (VNFs and vLinks), in a way that users belonging to a specific slice experience a predefined value of AR as minimum. Additionally, our calculations deploy recursive formulas, which have a low computational complexity, as opposed to time-consuming simulations, without requiring the application of complex optimization algorithms.

A Network Measurement System for NFV Networks based on SDN

As a promising innovation to totally change how we design, install and oversee different organizations, Software-based Network Function Virtualization (NFV) empowers hardware-free, adaptable, quickand proficient network service process. With the expanding prevalence of NFV, the Internet has likewise changed to be a hybrid environment where NFV-based network exists together with traditional gadgets. To ease our understanding, plan, assess and handling of such novel organization environment, there is an incredible requirement for new NFV-compatible measurement framework which is still missing till now. To overcome this issue, a framework, named Software Defined Network Measurement System (SDNMS) is introduced. First the architecture of SDNMS is proposed. In this design, a conventional strategy to portray the working method of the network measurement is defined. This technique can likewise be used to produce network measurement middle box (NMMB) in a particular location of the NFV network as per the customized description file, and to flexibly install the network measurement function. Besides, the innovation of virtual network measurement function (VNMF) joined with LXC is said to be shape NMMB function.Thirdly, a control strategy is introduced to control the beginning, stop, and update NMMB to produce a particular network measurement system. At last, a model of SDNMS with network observing function to screen network performance anomalies and locate fault is presented. Test results have shown that SDNMS design and related advancements are practical and successful to launch and control network measurement functions in NFV network. We trust SDNMS could give another strategy to experts to do network management and examine at the age of NFV

Flow Scheduling of Service Chain Processing in a NFV-Based Network

Network Function Virtualization (NFV) is changing the way we implement the network functions from expensive hardware to software middleboxes, called Virtual Network Functions (VNFs). Flows always request to be processed by several middleboxes in a specific order, which is known as a service chain. Most researches study the middlebox placement problemand few of them pay attention to the flow scheduling of a deployed service chain, resulting in poor control of flow completion times. However, the flow completion time is an extreme metric to evaluate the performance of a network. Therefore, we focus on the service chain scheduling problem. We aim to minimize the flow completion time in two aspects:the longest completion time (makespan) and the average completion time. First, a transmission and processing delay model is proposed to formulate the communication latency behaviour of flows being processed by middleboxes. When there are only two middleboxes in theservice chain, we propose one optimal solution for each aspect, respectively. For a service chain with an arbitrary length, we prove the NP-hardness of our problem in both aspects and two corresponding heuristic algorithms are designed, which are extended from ourproposed optimal solutions for a service chain with a length of two. Real testbed experiments and extensive simulations are conducted to evaluate the performance of our proposed algorithms in various scenarios.

Grouping Service Chains of Multiple Flows in NFV-Based Networks

In Software Defined Networks (SDNs), flows usually request to be processed by a service chain (an ordered set of virtualized network services). SDN-enabled networks manage the routing and processing of flows by a large number of associated finer-granularity rules. These rules are maintained by switches in their local hardware such as Ternary Content Addressable Memories (TCAMs), which support high-speed parallel lookup on wildcard patterns. However, the capacity of hardware switches is limited to thousands because of their high requirements for cost and power. In order to avoid much slower matching by using software switches or even packet loss, we can group flows so that all matching rules can be placed in hardware switches. In such a grouping, all flows in each group match only one rule and will be forwarded to the same routing path, instead of each flow matching one rule. This will result in a longer delay because of processing by the longer newly-grouped service chain. In this paper, we efficiently group flows to minimize the total cost while satisfying the capacity constraint of the forwarding tables in hardware switches. We first prove the submodularity of our objective function and propose a corresponding performance-guaranteed solution. Additionally, we design an efficient heuristic solution based on the classic k-means algorithm. Furthermore, we include discussions on dynamic network situations (insertion, deletion, and update of flows) and an alternative objective. We also conduct real experiments on our testbed to indicate the practicality of our motivation. Extensive simulations are conducted to evaluate the performance of our proposed algorithms.

Virtual Cache &amp; Virtual Wan Accelerator Function Placement for Cost-effective Content Delivery Services

The algorithm to determine the place where network functions are located and how much capacities of network function flexibly are required is essential for economical NFV (Network Functions Virtualization)-based network design. The authors proposed a placement algorithm of virtual routing function and virtual firewall function in the NFV-based network for minimizing the total network cost and developed the effective allocation guidelines for these virtual functions. This paper proposes an NFV-based virtual cache placement algorithm for cost-effective content delivery service such as video streaming, which judges the optimal placement of the cache per content, not on a virtual machine (VM) like the conventional CDN (virtual CDN). Moreover, the content is dynamically cached at the time of first content delivery like ICN (Information-Centric Networking) without placing the cache in advance like CDN .Our evaluation results revealed that the proposed algorithm could reduce total network costs by about 15% compared with CDN .Even if the content cache is deployed economically, performance will degrade if the latency between the content cache and user terminals is long. In order to prevent such a case, this paper also propose a cost-effective placement method of NFV-based WAN accelerator function.

Modeling and analysis of robust service composition for network functions virtualization

Fault tolerance is critical for constructing a reliable service in Network Functions Virtualization (NFV). In this paper, we propose novel models and algorithms that provide the resilience of NFV services from multiple node and link failures. We first design an optimization model and the PAR protection algorithm that can efficiently protect an NFV service demand from network failures without any action from a controller due to the diversity of flow assignment. We then develop an optimization model for total demand protection with a guarantee of recovering the whole demand volume. Further, a new restoration algorithm, namely UNIT, is proposed for the design of large survivable NFV-based networks with the recovery of the affected bandwidth under the uncertainty of multiple network failures. We analytically prove the performance guarantee of UNIT in comparison with the optimal static solution. The results of our experimental study in a Mininet-based environment with the Ryu controller show that a combination of PAR and UNIT efficiently protects NFV-based networks from failures in terms of both resource restoration and recovery time.

Allocation of Virtual Firewall Functions in NFV-Based Networks with Minimum Network Cost

Allocation of Virtual Firewall Functions in NFV-Based Networks with Minimum Network Cost

SDNMS: A software defined network measurement system for NFV networks

As a promising technology to completely transform how we architect, deploy, operate and manage various networks, software-based Network Function Virtualization (NFV) enables hardware-independent, flexible, fast and efficient network service provision. With the increasing popularity of NFV paradigm, the Internet has also transformed to be a hybrid environment where NFV-based network entities coexist with traditional network devices. To facilitate our understanding, design, evaluate and manage of such novel network environment, there is a great need for a new NFV-compatible network measurement system which is still in absent so far. To bridge this gap, a system, named Software Defined Network Measurement System (SDNMS), is presented in this paper. Firstly, the architecture of SDNMS is proposed. In this architecture, a formal method to describe the working mode of the network measurement is defined. This method can also be utilized to generate a network measurement middle box (NMMB) in a specific location of the NFV network according to the customized description file, and to flexibly deploy the network measurement function. Secondly, the technology of virtual network measurement function (VNMF) combined with LXC is studied to form NMMB function. Thirdly, a control method is presented to control the start, stop, and update NMMB to form a specific network measurement system function. Finally, a prototype of SDNMS with network monitoring function to monitor network performance anomalies and locate faults is introduced. Experimental results have shown that SDNMS architecture and related technologies are feasible and effective to deploy and control network measurement functions in NFV networks. We hope SDNMS could provide a new method for practitioners to conduct network management and research at the age of NFV.

Allocation of Virtual Firewall Functions in NFV-Based Networks with Minimum Network Cost

NFV-based network implements a variety of network functions with software on general-purpose servers and this allows the network operator to select any capacity and location of network functions without any physical constraints. It is essential for economical NFV-based network design to determine the place where each network function should be located in the network and what its capacity should be. The authors proposed an algorithm of virtual routing function allocation in the NFV-based network for minimizing the network cost and provided effective allocation guidelines for virtual routing functions. This paper proposes the deployment algorithm of virtual firewall function in addition to virtual routing function for minimizing the network cost. Our evaluation results have revealed the following: (1) Installing a packet filtering function, which is a part of the firewall function, in the sending-side area additionally can reduce wasteful transit bandwidth and routing processing and thereby reduce the network cost. (2) The greater the number of packets filtered by packet filtering function in the sending-side area, the more the reduction of network cost is increased. (3) The greater the bandwidth cost relative to the routing function cost, the greater the effect of statistical multiplexing on reducing the network cost. (4) The proposed algorithm would be approaching about 95% of the deployment with the optimal solution.

FENDE: Marketplace-Based Distribution, Execution, and Life Cycle Management of VNFs

The emergence of NFV has drawn the attention of academia, standardization bodies, and industry, because of the possibility of reducing capital and operational costs while introducing innovation in computer networks. To enable developers to independently publish and distribute VNFs, marketplaces akin to online application stores are essential. Research efforts in several aspects are necessary to enable wider adoption of such online application stores in emerging NFVbased computer networks. This article reviews the historical perspective of networking paradigms and technologies to propose FENDE, a marketplace and ecosystem for the distribution and execution of VNFs and composition of service function chains. Major challenges that must be overcome to promote the adoption of marketplaces in emerging NFV-based networks are investigated and discussed.

On efficient virtual network function chaining in NFV-based telecommunications networks

Network function virtualization enables the softwarization of network functions on standardized commodity hardware, which is promising to help the network carriers to achieve a lower investment cost, a shorter time to deployment, as well as a more flexible and dynamic way of network configuration and management. One of the key challenges is how to efficiently place and chain the software-based virtual network functions in the physical substrate to provision the requested network service while minimizing the physical network cost. In this paper, we mathematically formulate the virtual network function chaining problem using Integer Linear Programming (ILP), in order to facilitate an optimal solution. We propose a set of centralized algorithms to efficiently minimize the physical network cost. The proposed Close To Destination (CTD) algorithm can achieve a near-optimal physical network cost that is close to the optimal result obtained from the ILP solution, but with a very low computational complexity. In addition, we propose a distributed algorithm, called Look Ahead (LA), which plans ahead and jointly considers multiple next-hops VNF requirements to facilitate an efficient VNF chain forwarding decision. Comprehensive simulations are conducted to evaluate the proposed approaches, and the results demonstrate the effectiveness of the proposed CTD algorithm and the distributed LA algorithm.

Optimum Transmission Delay for Function Computation in NFV-Based Networks: The Role of Network Coding and Redundant Computing

In this paper, we study the problem of delay minimization in network function virtualization-based networks. In such systems, the ultimate goal of any request is to compute a sequence of functions in the network, where each function can be computed at only a specific subset of network nodes. In conventional approaches, for each function, we choose one node from the corresponding subset of the nodes to compute that function. In contrast, in this paper, we allow each function to be computed in more than one node, redundantly in parallel, to respond to a given request. We argue that such redundancy in computation not only improves the reliability of the network but also, perhaps surprisingly, reduces the overall transmission delay. In particular, we establish that by judiciously choosing the subset of nodes which compute each function, in conjunction with a linear network coding scheme to deliver the result of each computation, we can characterize and achieve the optimal end-to-end transmission delay. In addition, we show that using such technique, it is possible to significantly reduce the transmission delay as compared to the conventional approaches. In fact, in some scenarios, such reduction can even scale with the size of the network, where by increasing the number of nodes that can compute the given function in parallel by a multiplicative factor, the end-to-end delay will also decrease by the same factor. Moreover, we show that while finding the subset of nodes for each computation, in general, is a complex integer program, approximation algorithms can be proposed to reduce the computational complexity. In fact, for the case where the number of computing nodes for a given function is upper bounded by a constant, a dynamic programming scheme can be proposed to find the optimum subsets in polynomial times. Our numerical simulations confirm the achieved gain in performance in comparison with conventional approaches.

Reliable Broadcasting in 5G NFV-Based Networks

The emerging 5G technology will support high data rates with low latency and high levels of reliability. To satisfy these requirements, mobile operators have deployed enhancements to LTE networks in a move toward the development of future 5G networks. One of these enhancements is the LTE-broadcasting service. Another enhancement is the employment of network functions virtualization, which will provide elasticity of resources, scalability, and flexibility. In a virtualized LTE-broadcasting network, the main components of the LTE-broadcasting service will be implemented as VNFs. This article introduces a scheme to determine the number of redundant VNF components necessary to satisfy the reliability requirements of broadcasting services in 5G networks. A series-parallel redundant model determines the optimum number of virtual components instantiated to achieve a required service reliability level. The model is compared to a parallel-series one and shown to achieve greater effectiveness, achieving five nines reliability and promoting low end-to-end delay.

Performance evaluation of revised virtual resources allocation scheme in network function virtualization (NFV) networks

The design, management, and operation of network infrastructure have evolved during the last few years, leveraging on innovative technologies and architectures. With such a huge trend, due to the flexibility and significant economic potential of these technologies, software-defined networking (SDN) and network functions virtualization (NFV) are emerging as the most indispensable key catalysers. SDN/NFV enhancing the infrastructure agility, thus network operators and service providers are able to program their own network functions (e.g., gateways, routers, load balancers) on vendor-independent hardware substrate. One of the most important considerations in NFV deployment is how to allocate the virtual resources that are needed to provide flexible virtual network services in an NFV-based network infrastructure. Thus, the most important prerequisite for NFV deployment is achieved fast, scalable and dynamic composition and allocation of networks functions (NFs) to implement network services (NSs). We have proposed a revised RA algorithm that integrates embedding and scheduling of virtual network functions (VNFs) simultaneously. In this paper, performance evaluation of the revised RA algorithm is performed and the proposed algorithm is applied more effectively in NFV environment where the demand for resources is flexible and concentrated.

A benchmarking of the efficiency of supervised ML algorithms in the NFV traffic classification

The implementation of NFV allows improving the flexibility, efficiency, and manageability of networks by leveraging virtualization and cloud computing technologies to deploy computer networks. The implementation of autonomic management and supervised algorithms from Machine Learning [ML] become a key strategy to manage this hidden traffic. In this work, we focus on analyzing the traffic features of NFV-based networks while performing a benchmarking of the behavior of supervised ML algorithms, namely J48, Naïve Bayes, and Bayes Net, in the IP traffic classification regarding their efficiency; considering that such an efficiency is related to the trade-off between time-response and precision. We used two test scenarios (an NFV-based SDN and an NFV-based LTE EPC). The benchmarking results reveal that the Naïve Bayes and Bayes Net algorithms achieve the best performance in traffic classification. In particular, their performance corroborates a good trade-off between precision and time-response, with precision values higher than 80 % and 96 %, respectively, in times less than 1,5 sec.

Resource Allocation in NFV: A Comprehensive Survey

Network functions virtualization (NFV) is a new network architecture framework where network function that traditionally used dedicated hardware (middleboxes or network appliances) are now implemented in software that runs on top of general purpose hardware such as high volume server. NFV emerges as an initiative from the industry (network operators, carriers, and manufacturers) in order to increase the deployment flexibility and integration of new network services with increased agility within operator’s networks and to obtain significant reductions in operating expenditures and capital expenditures. NFV promotes virtualizing network functions such as transcoders, firewalls, and load balancers, among others, which were carried out by specialized hardware devices and migrating them to software-based appliances. One of the main challenges for the deployment of NFV is the resource allocation of demanded network services in NFV-based network infrastructures. This challenge has been called the NFV resource allocation (NFV-RA) problem. This paper presents a comprehensive state of the art of NFV-RA by introducing a novel classification of the main approaches that pose solutions to solve it. This paper also presents the research challenges that are still subject of future investigation in the NFV-RA realm.