Chain Of Network Functions Research Articles

Reinforcement-Learning-Assisted Service Function Chain Embedding Algorithm in Edge Computing Networks

Edge computing networks are critical infrastructures for processing massive data and providing instantaneous services. However, how to efficiently allocate resources in edge computing networks to meet the embedding requirements of service function chains has become an urgent problem. In this paper, we model the resource allocation problem in edge computing networks as a service function chain embedding problem model, aiming to optimize the resource allocation through reinforcement learning algorithms to achieve the goals of low cost, high revenue, and high embedding rate. In this paper, the basic concepts of edge computing network and service function chain are elaborated, and the resource allocation problem is transformed into a service function chain embedding problem by establishing a mathematical model, which provides a foundation for the subsequent algorithm design. In this paper, a service function chain embedding algorithm based on reinforcement learning is designed to gradually optimize the resource allocation decision by simulating the learning process. In order to verify the effectiveness of the algorithm, a series of simulation experiments are conducted in this paper and compared with other algorithms. The experimental results show that the service function chain embedding algorithm based on reinforcement learning proposed in this paper exhibits superior performance in resource allocation. Compared with traditional resource allocation methods, the algorithm achieves significant improvement in terms of low cost, high revenue, and high embedding rate.

Virtual Network Function Placement for Serving Weighted Services in NFV-Enabled Networks

Network function virtualization (NFV) is a novel network architecture yielding many optimization choices to Internet service providers due to its flexibility. Based on this technique, a network service is constructed from a chain of virtual network functions (VNFs). Although many studies deeply investigate the NFV and propose approaches to address the problem of deploying services in physical networks under different perspectives, they do not consider the importance of services. This issue becomes more critical once the number of network services ever-increasing while the network resources are limited. Here, each service is assigned a weight representing its importance. From this aspect, maximizing the total weight of services accepted to deploy over the physical network is a critical problem and poses many challenges, particularly for networks with limited resources. Therefore, we call this issue the VNF placement for weighted services (VPWS) problem. We then propose three algorithms termed first-fit server algorithm (FSA), best-fit server algorithm (BSA), and service segment-based algorithm (SSBA), respectively, to address the VPWS problem. Eventually, we perform simulations to evaluate the proposed algorithms and factors that affect the VNF placement. The experiment indicates that the total weight yielded by the SSBA outperforms those of the FSA and BSA.

Dynamic Joint VNF Forwarding Graph Composition and Embedding: A Deep Reinforcement Learning Framework

Network Function Virtualization (NFV) is a network service deployment technology that reduces capital and operational costs while yielding flexibility and scalability for service operators. As such, an ordered chain of Virtual Network Functions (VNFs), known as a VNF Forwarding Graph (VNF-FG), should be composed and embedded into the underlying substrate network. In the literature, the composition and embedding stages of VNF-FGs are usually targeted separately, which may result in undesired solutions. In this paper, we propose our joint VNF-FG composition and embedding solution, which considers the variations of service demands while also accounting for dynamic network conditions. Specifically, our proposed solution relies on deep reinforcement learning empowered by two components for estimating dynamic parameters: network resource utilization and service demand analyzers. Moreover, to efficiently explore the problem’s large discrete action space, we utilize a specialized branching Q-network and enhance it with an action filtering mechanism. We evaluated our proposed method against joint and disjoint composition and embedding heuristics as well as versus other deep learning-based methods. Our results show that the proposed method can achieve up to a 95% improvement of embedding cost compared to our benchmarks.

DRIVE: Dynamic Resource Introspection and VNF Embedding for 5G Using Machine Learning

Network Slicing (NS) technique is comprehensively reshaping the next-generation communication networks (e.g. 5G, 6G). Software-Defined Networking (SDN) and Network Functions Virtualization (NFV) predominantly control the flow of service functions on NS to incorporate versatile applications as per user demands. In the virtualized-Software Defined Networking vSDN environment, a chain of well-defined virtual network functions (VNFs) are installed on Service Function Chains (SFCs) by multiple Internet Service Providers (ISPs) concurrently. Generation, allocation, re-allocation, release and destroying associative VNFs on SFC is an extremely difficult task while keeping high selection accuracy. Towards solving this fundamental issue, in this work, we have proposed a multi-layered SFC formation for adaptive VNF allocation on dynamic slices. We have formulated an ILP to address the VNF-EAP (VNF-Embedding and Allocation Problem) over real network topology (AT&T Topology). Leveraging machine learning techniques we have shown an intelligent VNF selection mechanism to optimize resource utilization. The performance evaluation shows remarkable efficiency on ML-driven dynamic VNF selections over static allocations on SFCs by halving resource usage. Further, we have also studied a VNF typecasting technique for service backup on outage slices in the field of disaster management activities.

Availability‐aware virtual network function placement based on multidimensional universal generating functions

AbstractNetwork function virtualization (NFV) implements network functions as software, which enables flexible, resource‐efficient, and rapid provision of network services. In NFV, network services are realized by the service function chain (SFC), which is a chain of virtual network functions (VNFs) linked in the proper order. Both availability and deployment cost are key concerns for network operators providing network services as SFC. This paper proposes a flexible VNF placement model on a per‐VNF instance basis that minimizes deployment costs while satisfying availability requirements that may be placed on SFC. This paper uses a multidimensional universal generating function (MUGF) method, which is a multistate system analysis method, to compute the availability of a multistate SFC system with multiple VNFs coexisting on a server. The MUGF method calculates the performance of the entire SFC by combining the performance of servers as determined by applying a continuous‐time Markov chain. To reduce the time to compute the SFC availability, we introduce operators to be applied to MUGF and develop an availability computing method. In addition, a heuristic algorithm for determining VNF placement targeting the lowest deployment cost possible while meeting availability requirements is presented. Numerical results show that the proposed model obtains VNF placement with lower cost than the conventional model in all examined cases. The proposed model achieves VNF placement at 58.5%–75.0% of the deployment cost of the conventional model for the same SFC availability requirements.

Double-Agent Reinforced vNFC Deployment in EONs for Cloud-Edge Computing

With an effective service provisioning strategy that relies on Network Function Virtualization (NFV), cloud-edge computing can enhance the Quality of Service (QoS) in Elastic Optical Networks (EONs). NFV emerges as a promising technology to provide flexible services by orchestrating different virtual Network Function Chains (vNFCs). However, the vNFC deployment process is complex and involves two stages, i.e., allocating diverse Virtual Network Functions (VNFs) onto different physical nodes and routing suitable paths for Virtual Links (VLs). How to coordinate the above two stages to deploy vNFCs efficiently in EONs for cloud-edge computing is extremely important. Previous vNFC deployment algorithms are heuristic policies that disregard heterogeneous characteristics in cloud-edge computing. Recently, single-agent Deep Reinforcement Learning (DRL) can provide adaptive allocation schemes by perceptual learning from the environment. Whereas, its performance is not as good as expected since it makes the process of VFNs deployment and VLs deployment independent. Therefore, we propose a Double-Agent Reinforced vNFC Deployment algorithm (DARD) to integrate the VNFs and VLs deployment stages by two cooperative DRL agents. Additionally, we formulate the vNFC deployment problem as a Mixed Integer Linear Programming (MILP) model to achieve optimal solutions. The performance of DARD is evaluated in both static and dynamic scenarios. Simulation results show that DARD can achieve approaching performance with the MILP model. Moreover, it performs better than the other five state-of-art algorithms.

Reliable Dynamic Service Chain Scheduling in 5G Networks

As a key enabler of future 5G network, Service Function Chain (SFC) forwards the traffic flow along a chain of Virtual Network Functions (VNFs) to provide network services flexibility. One of the most important problems in SFC is to deploy the VNFs and schedule arriving requests among computing nodes to achieve low latency and high reliability. Existing works consider a static network and assume that all SFC requests are known in advance, which is impractical. In this paper, we focus on the dynamic 5G network environment where the SFC requests arrive randomly and the computing nodes can redeploy all types of VNF with a time cost. We formulate the problem of SFC scheduling in NFV-enabled 5G network as a mixed integer non-linear programing. The objective is to maximize the number of requests satisfying the latency and reliability constraints. To solve the problem, we propose an efficient algorithm to decide the redundancy of the VNFs while minimizing delay. Then we present a state-of-art Reinforcement Learning (RL) to learn SFC scheduling policy to increase the success rate of SFC requests. The evaluation result shows that our proposed RL solution can increase the success rate by 18.7% over the benchmark algorithms.

A Systematic Literature Review of Reliable Provisioning for Virtual Network Function Chaining

The abstraction of the network node functions using virtualization methods introduced an innovative architecture called Network Function Virtualization (NFV). In NFV, every virtualization software hosts a network service recognized as a Virtual Network Function (VNF). In general, the network provider creates a Service Function Chain (SFC) for every sequence of multiple requested VNFs by the customers. Although NFV allows for a more flexible and economical approach, it is more prone to error and failure. Therefore, providing reliable provisioning for VNF chaining is one of the key issues in NFV. In this paper, we present a systematic literature review to study the pioneer research efforts that provide reliable provisioning for VNF chaining by guaranteeing the availability of the service and resource optimization. Our review is the result of the analysis of 21 screened papers. This paper presents the result of our analysis, including different aspects of a reliable provisioning algorithm, various adopted techniques for reliable provisioning, and the superiority and drawbacks of each algorithm based on the proposed criteria for the evaluation of the provisioning algorithms.

APVNFC: Adaptive Placement of Virtual Network Function Chains

Abstract Designing efficient and flexible approaches for placement of Virtual Network Function (VNF) chains is the main success of Network Function Virtualization (NFV). However, most current work considers the constant bandwidth and flow processing requirements while deploying the VNFs in the network. The constant (immutable) flow processing and bandwidth requirements become critical limitations in an NFV-enabled network with highly dynamic traffic flow. Therefore, bandwidth requirements and available resources of the Point-of-Presence (PoP) in the network change constantly. We present an adaptive model for placing VNF chains to overcome this limitation. At the same time, the proposed model minimizes the number of changes (i.e., re-allocation of VNFs) in the network. The experimental evaluation shows that the adaptive model can deliver stable network services. Moreover, it reduces the significant number of changes in the network and ensures flow performance.

A Resource and Task Scheduling Based Multi-Objective Optimization Model and Algorithms in Elastic Optical Networks.

The elastic optical network (EON) adopting virtual network function (VNF) is a new type of network, in which the routing, spectrum, and data center allocation are key and challenging problems, and solving these three problems simultaneously can not only improve the network efficiency for network providers, but also let users obtain better service. However, few existing works handle these three problems simultaneously. To tackle the three problems simultaneously, given a set of network function chains (i.e., a set of tasks), we set up a new multi-objective optimization model in which the total length of paths for all tasks is minimized, the totally occupied spectrums are minimized, and the loads on all data centers are most balanced, simultaneously. To solve the model, we design two new evolutionary algorithms. The experiments are conducted on 16 cases of 4 widely used types of networks, and the results indicate that the proposed model and algorithms are effective.

Fair Virtual Network Function Mapping and Scheduling Using Proximal Policy Optimization

Network function virtualization redefines a network service as a softwarized chain of virtual network functions (VNFs), which decouples the specific network service from dedicated devices and greatly reduces the hardware cost. The VNFs are generally deployed on common off-the-shelf servers and statistically share computational resources. Due to the inherent integer constraints, the corresponding VNF mapping and scheduling issue is a highly challenging task. In this paper, we consider the mapping and scheduling of VNFs for a given network service, for which a flexible job shop scheduling problem is formulated to optimize the max-min fairness while ensuring the delay requirements of different service chains. Specifically, we propose a deep reinforcement learning method based on offline proximal policy optimization, which dynamically determines the mapping and scheduling decision based on the state of unfinished service chains. The proposed algorithm is scalable to the number of service chains and can be enhanced by Monte Carlo tree search. Numerical results show that the proposed algorithm outperforms the traditional random forest and the greedy algorithms in terms of both service fairness and acceptance ratio.

Truthful auction mechanisms for VNF chain provisioning and allocation across geo-distributed datacenters

With the fast development of network function virtualization (NFV), NFV markets are emerging that allows network service providers (NSPs) to trade different virtual network function (VNF) chains among users. Therefore, efficient mechanisms for VNF chain provisioning and allocation are key to guarantee efficient operations of the NFV markets. One fundamental issue is how to maximize the social welfare of the market such that selfish users have incentives to acquire VNF chains from the markets. To overcome this issue, in this paper, we propose a truthful randomized combinatorial auction mechanism (TRCAM), which integrates the primal–dual approximation algorithm design technique and efficient pricing strategy. This mechanism considers dynamic VNF chain provisioning of the NSP and flexible VNF chain deployment of users. To be specific, we first formulate the social welfare maximization problem as an integer linear program, which is proven to be NP-hard. Then, we propose a primal–dual approximate algorithm which is near-optimal with polynomial-time complexity and employ it as a building block to design the TRCAM. Furthermore, we develop a novel binary-search-based algorithm to boost the average-case performance of the TRCAM. Both strict theoretical analysis and extensive experimental studies demonstrate the effectiveness of our proposed TRCAM, which achieves approximate truthfulness, near-optimal social welfare, individual rationality, and computational efficiency.

A Reinforcement Learning Approach for Virtual Network Function Chaining and Sharing in Softwarized Networks

Cognizant of the ease with which softwarized functions can be dynamically scaled according to real time resource requirements, and the fact that multiple services can have common VNFs in their chaining, this paper tackles the problem of cost effective deployment of online services from the perspective of sharing their VNF instances. First, we formally formulate the deployment problem under VNFs sharing. Secondly, given the NP-hard nature of the above problem, we propose a reinforcement learning (RL) algorithm capable of making intelligent placement decisions while considering multiple conflicting costs. Costs of transmission, VNF instantiation or energy consumption, among others. Thanks to the intelligence of the RL algorithm, simulation results show that the performance of the proposed algorithm is within a 14% margin and similar to an optimal solution in terms of request provisioning cost and acceptance ratio, respectively. Moreover, the algorithm results in more than a 20% and a 70% improvement in terms of request deployment cost and time compared to a state-of-the-art algorithm, and up to more than a 40% improvement in terms of cost compared to an algorithm that greedily minimizes the transmission or VNF activation costs.

Distributed Orchestration of Service Function Chains for Edge Intelligence in the Industrial Internet of Things

Network virtualization techniques are promising to overcome the obstacle of applying and expanding costly traditional networks in the industrial Internet of things (IIoT). Artificial intelligence (AI)-enhanced distributed resource management in edge networks has aroused researchers’ widespread attention. However, dynamically arrived service requests and limited edge resources complicate the service scheduling issue. In this article, we establish a dynamic network virtualization technique enabled service function chain (SFC) orchestration framework in IIoT, formulate the joint optimization problem to maximize total utility and decompose it into two subproblems, i.e., SFC selection and dynamic SFC orchestration. A dynamic orchestration of SFC (DOS) scheme, consisting of resource-aware matching algorithm and averaged multistep double deep q-network algorithm, is designed to embed SFC requests distributedly on the optimal virtualized network function chains. At last, we validate the superiority of our proposed DOS scheme by experimental results.

A joint orchestration of security and functionality services at network edge

Edge computing emerges as a new paradigm to provide low-latency network services in close proximity to end users. Based on the network function virtualization (NFV) technology, network services can be flexibly and scalably provisioned as virtual network function (VNF) chains deployed at edge servers. With such advantages, both the industry and research communities have done extensive studies on deploying VNF chains at network edge. The existing works mainly take an ideal assumption that the network is totally safe and there are no malicious users. Therefore, they leverage all available resources to serve their users. However, such an assumption is impractical in real networks. Security services, such as firewall, deep packet detection, intrusion detection, are always required for production networks. The existing service deployment methods fail to consider the co-existence of security services and functionality services. In this paper, we present the topic of joint deployment of both security and functionality services, wherein the security services are responsible to check the data flows before being processed by the functionality services. To solve this problem, we propose the Secure Deployment Pattern, which aims to simultaneously satisfy the security protection and QoS requirements at network edge. It divides the services into two kinds, i.e., the user-oriented functionality services, and the service provider-oriented security services. In this case, it is very challenging to jointly deploy the security services and functional services with respect to the resource and latency constraints. We formulate this problem as an integer programming model, and propose the heuristic algorithms to solve it. As far as we know, this paper is the first step, which targets at a proper orchestration of security and functionality services in edge computing. Extensive evaluations show that the proposed algorithms are effective and efficient, in terms of the execution time and the average number of served requests.

Run-Time Adaptive In-Kernel BPF/XDP Solution for 5G UPF

Flexibility is considered a key feature of 5G softwarization to deliver a timely response to changes in network requirements that may be caused by traffic variation, user mobility, dynamic network function chains, slice lifecycle management operations, among others. In this article, we evolve the upf-bpf1 open-source project by proposing a new design to improve its flexibility by reducing the run-time adaptation time. The project proposes an in-kernel solution based on BPF and eXpress Data Path (XDP) for 5G User Plane Function (UPF) implementations. The Just-In-Time (JIT) compilation may have a huge impact on the adaptation time due to the in-kernel verification of the BPF programs at run-time. Our results show latency improvements of around 95% to inject the BPF program into the Linux kernel. Furthermore, the solution keeps the same functionalities and delivers a packet processing performance of around 10–11 Mpps using 6 cores with almost 70% of the CPU utilization in downlink/uplink directions.

Next-Generation Edge Computing Assisted Autonomous Driving Based Artificial Intelligence Algorithms

Edge Computing and Network Function Virtualization (NFV) concepts can improve network processing and multi-resources allocation when intelligent optimization algorithms are deployed. Multiservice offloading and allocation approaches pose interesting challenges in the current and next-generation vehicle networks. The state-of-the-art optimization approaches still formulate exact algorithms, and tune approximation methods to get sufficient solutions. These approaches are data-centric that aim to use heterogeneous data inputs to find the near optimal solutions. In the context of connected and autonomous vehicles (CAVs), these techniques show an exponential computational time and deal only with small and medium scale networks. Therefore, we are motivated by using recent Deep Reinforcement Learning (DRL) techniques to learn the behavior of exact optimization algorithms while enhancing the Quality of Service (QoS) of network operators and satisfying the requirements of the next-generation Autonomous Vehicles (AVs). DRL algorithms can improve AVs service offloading and optimize edge resources. An Optimal Virtual Edge Autopilot Placement (OVEAP) algorithm is proposed using Integer Linear Programming (ILP). Moreover, an autopilot placement protocol is presented to support the algorithm. Optimal allocation and Virtual Network Function (VNF) placement and chaining of the autopilot, based on several new constraints such as computing and networking loads, network edge infrastructure, and placement cost, are designed. Further, a DRL approach is formulated to deal with dense Internet of Autonomous Vehicle (IoAV) networks. Extensive simulations and evaluations are carried out. Results show that the proposed allocation strategies outperform the state-of-the-art solutions and give better performance in terms of Total Edge Servers Utilization, Total Edge Servers Allocation Time, and Successfully Allocated autopilots.

Joint Dynamical VNF Placement and SFC Routing in NFV-Enabled SDNs

Due to that Service Function Chain (SFC) permits the forwarding of flows along a predetermined sequence chain of Virtual Network Functions (VNFs), it has become a common service in Network Function Virtualization (NFV)-enabled Software Defined Networks (SDNs). Generally, since there are multiple same VNF-instances in NFV-Enabled SDNs, this brings a great challenge for selecting or placing the required VNF-instances to satisfy the routing of SFC Request flows (SRs). In this paper, we study the routing problem for SRs by jointly considering dynamical VNF placement and multiple Resources and Quality of Service (QoS) constraints in NFV-Enabled SDNs. Specifically, we first define two optimization problems: one is the Dynamical VNF Placement and Routing Problem for SRs (DVPRP) and the other is the Delay, packet Loss and Jitter Aware Dynamical VNF Placement and Routing Problem for SRs (DLJA-DVPRP). We then formulate the two problems as Integer Linear Programming (ILP) problems. Next, we creatively devise an auxiliary edge-weight graph and propose two efficient algorithms to solve the problems with the aim of minimizing the resource consumption costs as well as ensuring multiple QoS constraints. Especially, we utilize the shortest path algorithm based on Lagrange relaxation method to solve the DLJA-DVPRP with multiple QoS constraints. Compared with existing algorithms, simulation results demonstrate our proposed algorithms have better performance in terms of throughput, traffic acceptance rate and load balance.

Q-SR: An extensible optimization framework for segment routing

Segment routing (SR) combines the advantages of source routing powered by software-defined networking (SDN) paradigm and hop-by-hop routing in legacy network infrastructure. The recent applications of SR in multi-domain network and service function chaining (SFC) entail the efficient use of multiple segments. However, because of the computation inefficiency, it is nearly impossible to accurately evaluate whether and to what extent various types of networks will benefit from SR with multiple segments using conventional approaches. In this paper, we propose a flexible Q-SR framework as well as its formulation in order to fully explore the potential of SR from an algorithmic perspective. The framework is highly extensible to design and evaluate algorithms that can be adapted to various network topologies and traffic matrices. For the offline setting, we develop a fully polynomial time approximation scheme (FPTAS) which can find a (1+ω)-approximation solution for any specified ω>0 in time that is a polynomial function of the network size. To the best of our knowledge, the proposed FPTAS is the first algorithm that can compute arbitrarily accurate solution. For the online setting, we develop an online primal–dual algorithm that is proven to be O(1)-competitive and violates link capacities by a factor of O(logn), where n is the node number of the network. For the proposed approximation algorithms, we prove theoretical performance bounds and conduct extensive simulations on synthetic and realistic networks to analyze SR related and algorithmic parameters and validate the computation efficiency in both offline and online scenarios.

A Combinatorial Reliability Analysis of Generic Service Function Chains in Data Center Networks

In data center networks, the reliability of Service Function Chain (SFC)—an end-to-end service presented by a chain of virtual network functions (VNFs)—is a complex and specific function of placement, configuration, and application requirements, both in hardware and software. Existing approaches to reliability analysis do not jointly consider multiple features of system components, including, (i) heterogeneity, (ii) disjointness, (iii) sharing, (iv) redundancy, and (v) failure interdependency. To this end, we develop a novel analysis of service reliability of the so-called generic SFC, consisting of n = k + r sub-SFCs, whereby k ≥ 1 and r ≥ 0 are the numbers of arbitrary placed primary and backup (redundant) sub-SFCs, respectively. Our analysis is based on combinatorics and a reduced binomial theorem—resulting in a simple approach, which, however, can be utilized to analyze rather complex SFC configurations. The analysis is practically applicable to various VNF placement strategies in arbitrary data center configurations, and topologies and can be effectively used for evaluation and optimization of reliable SFC placements.