Bandwidth-aware allocation of resilient Virtual Software Defined Networks

This paper presents the contributions of the phd thesis “Mechanisms for management of SLA for Virtual Software Defined Networks based on QoS Classes”. Over the years the Internet has become the primary means of communication, where the users expect to access the Internet anytime, anywhere, and with a certain quality level. As a consequence, in the past few years the traffic demand to Internet access has increased. However, since the current Internet does not guarantee Quality of Service (QoS) and Quality of Experience (QoE), the companies apply a Service Level Agreements (SLA) with Internet Service Providers (ISPs). In this way, the Internet service providers aim to improve utilization of network resources and service delivery to the users through the deployment of Virtual Networks (VNs) over Software Defined Networks (SDNs), called virtual software defined networks (VSDNs). However, the management of this type of environment still presents open issues. In this context, a set of mechanisms to manage VSDN was developed. The objectives of the developed mechanisms are to negotiate, to deploy and to adapt the VSDNs according to the current state of the network infrastructure and the SLA definition.

Data center operators are accepting software defined networking (SDN) to manage their networks, but it remains challenging how to provide desirable virtual SDN services to tenants in a public cloud. We design SVirt, which enables highly flexible virtual SDN in a multi-tenant cloud by a substrate-agnostic SDN virtualization architecture. By redesigning the physical switch's processing pipeline with a late-binding key extractor, SVirt supports virtual SDN switches with different processing pipelines simultaneously on a physical switch. In the control plane, SVirt enables many-to-one and one-to-many mapping when allocating the physical resource for a virtual network, which embraces arbitrary topology and TCAM resource demanded by a virtual network. In the data plane, SVirt explicitly carries the forwarding context information in the packets, overcoming the context-loss problem in a virtual SDN network. We develop a NetFPGA prototype of SVirt switch. Evaluations based on event-driven simulations and prototype-based experiments demonstrate that, compared with traditional approaches, SVirt significantly enhances the cloud's capability to accept various virtual SDN requests and improves the network's throughput.

This article presents a description of the method of increasing the stability of data transmission in a software-defined network (SDN) by means of its dynamic reconfiguration, considering the parameters of the quality of service (QoS) of communication channels and the reliability of nodes. The existing algorithms do not provide a comprehensive solution to the problem of determining the most optimal path that would provide a connection from the source point to the destination. They consider only certain parameters of the network, depending on which the time spent on communication between nodes is less than in the case of other routes. In conditions of growth in the number of users of computer networks and the number of node switches, there is an urgent problem of increasing the stability of data transmission in branched computer networks. It is proposed to solve this by considering the quality of service parameters of communication channels when constructing routes. The aim of the research is to increase data transmission stability in a virtual software-defined network in conditions of failures of nodes and increasing loads on communication channels. The first objective of the research is to create a method for finding a set of non-intersecting optimal paths that would consider various metrics of the quality of service of communication channels. The second research objective is to develop a dynamic reconfiguration mechanism for SDN switch flow tables to be able to reroute traffic in the event of individual node failure. In the course of the research, the first objective was performed by mathematically substantiating the construction of the generalized weight matrix of transitions between the nodes of the network graph. When creating a request to determine a route for traffic in the network, its status and indicators are updated in order to increase the accuracy of data on available resources and establish the optimal path that meets the quality of service criteria. It is proposed to consider four quality of service metrics for path construction: the number of hops between vertices, the available bandwidth, the time delay, and the percentage of lost packets. Using the generalized transition weight matrix, the SDN controller selects the most optimal path among a set of alternative non-intersecting paths. Then, using the reliability coefficients of the nodes as a constraint to choose the optimal path between the vertices, the controller chooses the main route from the set of alternatives according to the requirement for the reliability of the nodes set by the administrator, and considers the other routes as backup. The second task was solved by proposing a method of dynamic network reconfiguration using known paths. If in the process of traffic transmission there is a failure in the intermediate links of the network or the communication channels between them, then monitoring data of the SDN controller are used for reconfiguration and bypassing the problem area, which allows the controller to quickly choose an alternative path for sending traffic and build a new path based on already known data about communication channels in the network. The obtained results of theoretical studies testify to the correctness of the chosen solutions and proposals for the objectives set in the article.

Software Defined Networking (SDN) is believed to be a promising networking practice in facing the challenges of ever-increasing traffic demand and network growth. With wider deployment of SDN enabled network infrastructures, the conventional network virtualization problem will gradually evolve into an SDN virtualization problem, in which both virtual data plane and control plane entities are instantiated from their physical network counterparts. In this paper, we first argue that the delay constrained virtual SDN embedding problem is in general different from the conventional virtual network (VN) embedding problem. This paper tries to define the delay constrained vSDN embedding problem space, followed by a potential network architecture that supports SDN virtualization. This study then formulates the delay constrained vSDN embedding problem with the objective of maximizing request acceptance ratio and proposes a set of heuristics to tackle the embedding problem. Our results show that both the control plane placement and data plane mapping are restricted by a strict controller-to-switch (C2S) delay constraint. When the delay constraint is relaxed over a certain value, the acceptance ratio is dominated by control plane resources or data plane resources. Certainly, with different resource configurations and substrate network diameters, the tolerances of C2S delay constraint are distinct.

With the advent of 5G technology, we are witnessing the development of increasingly bandwidth-hungry network applications, such as enhanced mobile broadband, massive machine-type communications and ultra-reliable low-latency communications. Software Defined Networking (SDN), Network Function Virtualization (NFV) and Network Slicing (NS) are gaining momentum not only in research but also in IT industry representing the drivers of 5G. NS is an approach to network operations allowing the partition of a physical topology into multiple independent virtual networks, called network slices (or slices). Within a single slice, a set of Service Function Chains (SFCs) is defined and the network resources, e.g. bandwidth, can be provisioned dynamically on demand according to specific Quality of Service (QoS) and Service Level Agreement (SLA) requirements. Traditional schemes for network resources provisioning based on static policies may lead to poor resource utilization and suffer from scalability issues. In this article, we investigate the application of Reinforcement Learning (RL) for performing dynamic SFC resources allocation in NFV-SDN enabled metro-core optical networks. RL allows to build a self-learning system able to solve highly complex problems by employing RL agents to learn policies from an evolving network environment. In particular, we build an RL system able to optimize the resources allocation of SFCs in a multi-layer network (packet over flexi-grid optical layer). The RL agent decides if and when to reconfigure the SFCs, given state of the network and historical traffic traces. Numerical simulations show significant advantages of our RL-based optimization over rule-based optimization design.

Software-Defined Networking (SDN) is a new efficiently idea of programmable networks that separates the control plane from data plane of all network devices. Internet service provider is responsible for all the control decisions and communication among the forwarding elements from centralized controller. SDN provides the various optimized services. Quality of service (QoS) routing is a path computation method that is suitable for the different traffics generated by several applications, while utilization of network resources has increased. This agreement of service is defined by QoS requirements such as throughput, delay, jitter and packet loss etc. Multimedia applications often require assured from multi QoS constrained, causing the NP-complete problem which cannot be simply solved in polynomial time and high management complexity in the transition network. SDN is able to reduce complexity and it is used to efficiently implement traffic, hence SDN significantly values to development QoS routing. In this paper, we propose QoS routing algorithm called Quantized Level Balance (QLB) for SDN that considers one or many QoS parameters relating to the network application. To satisfy the requirements, QLB selects QoS parameters depending to the level of appropriate application service quality. We have replicated our algorithm on simulate topology with Scalable Video-streaming Evaluation Framework (SVEF). We measure the Peak Signal-to-Noise Ratio (PSNR) and Mean Opinion Score (MOS) of Scalable Video Coding (SVC) at the receiver. Our propose algorithm is improved than single-metric approach that may choose poor QoS parameter paths.

In a distributed computing environment, guaranteeing the hard deadline for real-time messages is essential to ensure schedulability of real-time tasks. Since capabilities of the shared resources for transmission are limited, e.g., the buffer size is limited on network devices, it becomes a challenge to design an effective and feasible resource sharing policy based on both the demand of real-time packet transmissions and the limitation of resource capabilities. We address this challenge in two cooperative mechanisms. First, we design a static routing algorithm to find forwarding paths for packets to guarantee their hard deadlines. The routing algorithm employs a validation-based backtracking procedure capable of deriving the demand of a set of real-time packets on each shared network device, and it checks whether this demand can be met on the device. Second, we design a packet scheduler that runs on network devices to transmit messages according to our routing requirements. We implement these mechanisms on virtual software-defined network (SDN) switches and evaluate them on real hardware in a local cluster to demonstrate the feasibility and effectiveness of our routing algorithm and packet scheduler.

In the differentiated services (DS) enabled networks, Internet service providers (ISPs) establish service level agreements (SLAs) with their customers. Prices of the SLAs and quality of data transmission services should correspond to the requirements of the customers and operations aims of the ISPs. For this reason, IP domains of the ISPs should contain a control system for setting the selling prices of the SLAs and DS services used for data flows of the SLAs. The control system should consider dynamically both requirements of the customers and quality of end-to-end data transmission services. This task is complex because the customers and operators of other networks may not give useful information to the ISPs for the control task. For this reason, a new fuzzy controller based control system is developed. The system operates using local measurements of ingress routers of IP domains about the behaviour of the customers. It does not inquire the level of satisfaction of the customers about offered data transmission services, or capacities of networks of other operators. The operations of the control system are tested using the Network Simulator 2.Key wordsMulti-service InternetDifferentiated ServicesService Level AgreementsFuzzy controllers

This chapter introduces a greedy approach for delay monitoring of IP networks. It proposed two-phased monitoring scheme that ensures complete coverage of the network from both links and paths point of views, and it minimizes the monitoring overhead on the underlying production network. In the first phase it computes the locations of monitoring stations such that all network links or paths are covered by the minimal number of stations. Subsequently, in the second phase, it computes the minimal set of probe messages to be sent by each station such that the latency of every routing path can be measured. Unfortunately, both the station selection and the probe assignment problems are NP-hard. However, by using greedy approximation algorithms the scheme finds solutions close to the best possible approximations to both the station selection and the probe assignment problems. Further, the experimental results demonstrate the effectiveness of the presented algorithms for accurately monitoring large networks with very few monitoring stations and probe messages close to the number of network links.

This chapter describes cloud, virtualization, software-defined networking (SDN), and self-managed concepts, architectures, and their building blocks, as possible future directions for multiple-system operator (MSO) networks and services. Cloud computing technologies are emerging as infrastructure services for provisioning computing and storage resources on demand in a simple and uniform way. Cloud-based virtualization allows for easy upgrade and migration of enterprise application, including also the whole IT infrastructure segments, which brings significant cost saving compared to traditional infrastructure development and management requiring good amount of manual work. SDN is defined by open networking foundation (ONF) as an emerging architecture that is dynamic, manageable, cost-effective, and adaptable. The chapter explains self-managed network concept, network element (NE) and network management system (NMS) architectures, and fault management communication mechanisms for centrally and distributedly self-managed networks. The concept is applied to virtual networks (VNs) and SDN.

Multi-tenant software-defined networks have emerged as a promising service platform to manage and share virtual network services between tenants and end-users. However, when using a service level agreement (SLA) in a multi-tenant circumstance, the resource competition among tenants incurred in many challenges on the quality of services (QoS) provisioning. First, as the existing QoS provisioning was to translate the high-level SLA contact into a group of corresponding low-level QoS rules, this traditional top-down translation mechanism was too ossified to support the dynamic SLA negotiation. Second, since an end-user usually requested multiple services and different services had different QoS requirements, the QoS provisioning required tenants to monitor and control the network status though OpenFlow protocol in a fine-grained way. To address these issues, we propose an SLA-aware fine-grained QoS provisioning (SFQP) scheme for MTSDN. The SFQP scheme extracts the eigen characteristics of each packet by application-aware technology automatically. Considering tenants are more willing to serve for users which have popular SLA contact to earn more revenues, we predict the SLA popularity by K-nearest neighbor. Moreover, we present an SLA-aware dynamic bandwidth allocation algorithm to implement the proposed SFQP scheme. The feasibility of the proposed scheme is verified by simulations of the SLA taxonomy, bandwidth utilization, and bandwidth fluctuation.

A service level agreement (SLA) is part of a contract between a cloud service provider (CSP) and a cloud service user (CSU) which defines and describes different agreed properties of the service. The negotiation of the SLA between a CSU and a CSP is a pivotal process in the SLA life cycle. An SLA may include many negotiable quality of service (QoS) parameters with each QoS parameter having multiple acceptable values. Different combinations of acceptable values for all QoS parameters grow exponentially as number of QoS parameters and their selectable values increase. Manually negotiating for all of the QoS parameters considering their various options can be an erroneous and diligent task with lower utility. In this paper, a time efficient flip-flop negotiation strategy for the SLAs in cloud services is presented. The flip-flop negotiation strategy is based on a time dependent 3D utility function and on a dynamic concession strategy using the polynomial extrapolation of opponent's concession. This negotiation strategy is useful for time-critical cloud services as it operates with a motive of reaching an agreement at earlier time without compromising over the utility level of the agreement. Moreover, a multi-provider concurrent negotiation method is presented in this work using the flip-flop negotiation strategy. Multiple experiments are performed (using the implementation of flip-flop negotiation strategy) to test the presented work. The results of the experiments enforce the validity of the flip-flop negotiation strategy for such cloud services where time is an important factor during the SLA negotiation process.

A Service Level Agreement (SLA) is a legal contract between parties to ensure the Quality of Service (QoS). It specifies one or more service level objectives (SLO), to ensure that the QoS delivered has met customer expectations. However, It becomes hard to guarantee QoS levels and detect SLA violations. Therefore, we propose to use MDE (Model Driven Engineering) to express the SLA contract requirements. This latter, created with a specific modeling language (DSML), will be used harmonically with a Multi-agent systems (MASs) in order to monitor SLA violations in real-time. Indeed, MASs are suitable tools for self-detection of failures and self-monitoring of cloud operations and services, QoS negotiation and SLA management. They are designed to operate in a dynamically changing environment. Our main motivation is firstly to use MDE technology for the creation of the SLA contract and then to integrate MASs in order to control the quality of service contract and guarantee transparency and symmetry with respect to the SLA contract between prospective signatories.

Service level agreement (SLA) in cloud computing can be defined as a contractual agreement signed between cloud user and cloud provider in order to manage the quality of service (QoS) parameters which are the fundamental part of SLAs. The current dynamic SLA monitoring approaches have considered the cloud provider's perspective only. To take into consideration the user's perspective; this research proposes a dynamic SLA monitoring approach by generating new SLA terms based on analysing the SLA penalties. A new proposed trade-off mechanism is applied between monthly cost and QoS guarantee values. Thus; we propose a dynamic model for updating QoS parameters of SLA in cloud environment. Java language is used with a QoS measurement dataset to experiment the proposed approach. The current Static SLA (SSLA) approaches are compared with the proposed Dynamic SLA (DSLA) approach. The results of this experimental study show that the number of SLA violations in DSLA are less than the number of SLA violations in SSLA.

Service level agreement (SLA) in cloud computing can be defined as a contractual agreement signed between cloud user and cloud provider in order to manage the quality of service (QoS) parameters which are the fundamental part of SLAs. The current dynamic SLA monitoring approaches have considered the cloud provider's perspective only. To take into consideration the user's perspective; this research proposes a dynamic SLA monitoring approach by generating new SLA terms based on analysing the SLA penalties. A new proposed trade-off mechanism is applied between monthly cost and QoS guarantee values. Thus; we propose a dynamic model for updating QoS parameters of SLA in cloud environment. Java language is used with a QoS measurement dataset to experiment the proposed approach. The current Static SLA (SSLA) approaches are compared with the proposed Dynamic SLA (DSLA) approach. The results of this experimental study show that the number of SLA violations in DSLA are less than the number of SLA violations in SSLA.