Search

The transition towards full network virtualization will see services for smart ecosystems including smart metering, healthcare and transportation among others, being deployed as Service Function Chains (SFCs) comprised of an ordered set of virtual network functions. However, since such services are usually deployed in remote cloud networks, the SFCs may transcend multiple domains belonging to different Infrastructure Providers (InPs), possibly with differing policies regarding billing and Quality-of-service (QoS) guarantees. Therefore, efficiently allocating the exhaustible network resources to the different SFCs while meeting the stringent requirements of the services such as delay and QoS among others, remains a complex challenge, especially under limited information disclosure by the InPs. In this work, we formulate the SFC deployment problem across multiple domains focusing on delay constraints, and propose a framework for SFC orchestration which adheres to the privacy requirements of the InPs. Then, we propose a reinforcement learning (RL)-based algorithm for partitioning the SFC request across the different InPs while considering service reliability across the participating InPs. Such RL-based algorithms have the intelligence to infer undisclosed InP information from historical data obtained from past experiences. Simulation results, considering both online and offline scenarios, reveal that the proposed algorithm results in up to 10% improvement in terms of acceptance ratio and provisioning cost compared to the benchmark algorithms, with up to more than 90% saving in execution time for large networks. In addition, the paper proposes an enhancement to a state-of-the-art algorithm which results in up to 5% improvement in terms of provisioning cost. [ABSTRACT FROM AUTHOR]

Network function virtualization (NFV) provides dynamic, energy-efficient, and cost-effective network services by segregating network services from expensive and energy-hungry hardware components. Traditional hardware-based network functions are always ON with 100% capacity, resulting in massive energy consumption. In contrast, NFV enables different network services (NS) through virtual network functions (VNFs), which can reduce energy consumption, by automatic ON/OFF (auto-scaling) of the VNFs depending on the traffic load. However, auto-scaling will introduce delays in the network service management process. This delay can be minimized by estimating future resource requirements accurately and taking proactive steps ahead of time. In this research, we propose the use of deep learning based forecasting algorithms to predict the required VNFs and virtual CPU for each VNF to complete a network service, often deployed as service function chain (SFC). We use long short term memory (LSTM), bidirectional-LSTM, and convolutional neural network (CNN) based algorithms to forecast resources from univariate and multivariate network traffic data. Experimental results show that CNN and bidirectional-LSTM-based forecasting models can forecast more accurately than the prior studies. Based on the forecasting models, we propose a resource allocation algorithm (DeepVRM) that can efficiently allocate resources to complete SFC. [ABSTRACT FROM AUTHOR]

Network Function Virtualization (NFV) has been identified to revamp the provisioning of next-generation network services. This new paradigm allows cloud and network/service providers to compose their network services, also known as service function chains (SFCs), in an agile way since the software of the network function is decoupled from the legacy hardware. To reap the benefits of this new technology, there is a need for novel mechanisms that help cloud and network/service providers deploy the increasingly complex virtual network services seamlessly, efficiently, and in a time-efficient way. Existing state-of-the-art techniques often rely on the Integer Linear Programming framework, heuristics/metaheuristics, and greedy methods to deploy the services function chains. However, these techniques although reasonable and acceptable, still suffer from several key limitations: convergence time and scalability. To this end, we propose RAFALE, a suite of solution techniques, to tame this complexity by leveraging the concept of similarity from machine learning and skip-gram modeling framework. To the best of our knowledge, we are the first to tackle these key limitations and propose a suite of solutions to them. RAFALE, a novel approach proposed to find the similarity between the new incoming virtual network service request and all the already-deployed services to learn from the previous experience of deploying techniques and use the same or close similar provisioning techniques. RAFALE is the first and the only method that develops the idea of detecting the similarity between virtual network services. Experimental results show that RAFALE reduces greatly the convergence time needed for provisioning virtual network services and can scale to 100 virtual network functions per virtual network service compared to the state-of-the-art. The Experimental results prove that RAFALE accomplished the NFV promises; decreasing the time and complexity of managing and deploying the virtual services, and providing a solution that is agile, faster, and scalable to deploy the new service requests by skipping one or more service provisioning steps (i.e., detecting and resolving the conflicts among policies, placement, and chaining) while satisfying the validated NFV policies. [ABSTRACT FROM AUTHOR]

Re-architecting mobile network functions and central office is one of the hottest topics of software defined networking (SDN) and network function virtualization (NFV). It is known as Next generation mobile network (NGMN). The main benefit of re-architecting is to bring cloud advantages to mobile operator networks. On the other hand, while the openness is one of the most wanted characteristics of NGMN, many open source implementations have been introduced to accelerate realizing the NGMN such as resource allocation management and orchestration which is considered as one of the hardest problems in SDN, NFV, and network virtualization. To that end, this article has comprehensively reviewed the mobile core architecture, resource management and orchestration evolutions in order to investigate the relay of the mobile operators on open source components, especially in developing countries, in order to build their future NGMN infrastructure for 4G/5G (fourth/fifth generations) access networks. Furthermore, the article shows a large number of open source infrastructure' components that the operator needs to integrate them together, which is a challenging task. Moreover, the article addresses the integration framework challenges for resource management and orchestration based on continuous integration continuous development (DevOps) model. The outcomes of this work encourage mobile operators to involve and contribute to open source integration efforts as well as build and test their NGMN integration scenarios. [ABSTRACT FROM AUTHOR]

With the penetration of Network Function Virtualization (NFV), network functions, traditionally deployed as proprietary physical equipment like firewalls, Network Address Translations (NATs), are gradually being implemented as software and deployed on standardized hardware. One of the crucial challenges in this paradigm is how to place the software implemented network functions to minimize the number of used physical servers. In this paper, we study the problem of how to optimally place Virtual Network Functions (VNFs) in networks where it is allowed to migrate already placed VNFs to decrease used servers. We first formulate the offline problem as an Integer Linear Programming (ILP) problem, and then propose a semi-online algorithm to solve the online variant of the problem. We name the proposed algorithm Semi-onlIne Vnf plAcement (SIVA). In particular, SIVA is based on a bin packing algorithm that solves online bin packing problem while taking care of migrations. According to our theoretical analysis, SIVA migrates at most λ VNFs each step, and it has Asymptotic Competitive Ratio (ACR) of 3/2 if k → ∞ , where λ = k · | N | , k is a tunable parameter, and | N | is the the number of supported VNF types. We conduct extensive numerical simulations to evaluate the performances of SIVA. The experiment results validate the theoretical analysis and show that SIVA outperforms the state-of-the-art algorithms by achieving near-optimal performance with minor VNF migrations. [ABSTRACT FROM AUTHOR]

The Service Function Chaining (SFC) is an architecture to orchestrate network services by creating and deploying the rule-based service function chains and steering network traffic through them. One of the main tasks in SFC is the optimal composition of the service functions and checking the validation of the composed service chain based on the predefined rules. As the problem of optimal chain composition is NP hard, in this paper a Finite Automaton (FA) model is proposed to limit the solution space by considering the practical scenarios. Since the chaining rules depend on the substrate physical platform, the proposed FA is based on the data centre, mobile, and security scenarios introduced by Internet Engineering Task Force (IETF). Subsequently, Finite Automaton Matcher (FAM) shows that the proposed FA is an acceptable tool for validating the correctness of the composed service chain. Experimental results and complexity analysis show that this method reduces the number of service chain compositions and therefore the time complexity significantly. [ABSTRACT FROM AUTHOR]

With the advances of network function virtualization and cloud computing technologies, a number of network services are implemented across data centers by creating a service chain using different virtual network functions (VNFs) running on virtual machines. Due to the complexity of network infrastructure, creating a service chain requires high operational cost especially in carrier-grade network service providers and supporting stringent QoS requirements from users is also a complicated task. There have been various research efforts to address these problems that only focus on one aspect of optimization goal either from users such as latency minimization and QoS based optimization, or from service providers such as resource optimization and cost minimization. However, meeting the requirements both from users and service providers efficiently is still a challenging issue. This paper proposes a VNF placement algorithm called VNF-EQ that allows users to meet their service latency requirements, while minimizing the energy consumption at the same time. The proposed algorithm is dynamic in a sense that the locations or the service chains of VNFs are reconfigured to minimize the energy consumption when the traffic passing through the chain falls below a pre-defined threshold. We use genetic algorithm to formulate this problem because it is a variation of the multi-constrained path selection problem known as NP-complete. The benchmarking results show that the proposed approach outperforms other heuristic algorithms by as much as 49% and reduces the energy consumptions by rearranging VNFs. [ABSTRACT FROM AUTHOR]