Dynamic Service Function Chain Research Articles

Security-Aware Cost Optimized Dynamic Service Function Chain Scheduling

Security-Aware Cost Optimized Dynamic Service Function Chain Scheduling

Enhancing SFC Placement with Parallelized Functions in MEC Using Deep Reinforcement Learning

This study presents an innovative architecture leveraging Deep Reinforcement Learning (DRL) to optimize online service delivery in Mobile Edge Computing (MEC) networks. Our proposed method, the DRL-based dynamic Service Function Chain (SFC) placement with parallelized Virtual Network Functions (VNFs), aims to maximize Long-Term Cumulative Reward (LTCR). By parallelizing VNFs, our approach achieves computational acceleration, enhancing the efficiency of online service provisioning. Furthermore, we enhance future request processing capabilities by extracting the distribution of initialized VNFs. Through comprehensive simulations, our proposed architecture demonstrates a notable improvement, with approximately a 9.5% increase in the average number of accepted requests.

Correction to “Dynamic service function chain placement in mobile computing: An asynchronous advantage actor‐critic based approach”

Correction to “Dynamic service function chain placement in mobile computing: An asynchronous advantage actor‐critic based approach”

Digital twin-assisted service function chaining in multi-domain computing power networks with multi-agent reinforcement learning

The emerging computing power network (CPN) is believed to undergo the paradigm reformation of network function virtualization (NFV) and service function chaining (SFC). It is prerequisite to explore the performance upper bound of NFV-assisted CPN before truly deploying the NFV and SFC technologies onto physical networks. Inspired by the application of digital twin (DT) in the industry and due to its advantage in synchronizing physical objects with their virtual replicas, we propose to use the DT to assist the SFC deployment in the multi-domain CPN, with the aid of multi-agent deep deterministic policy gradient (MADDPG) framework. First, we build a dynamic SFC mapping problem in the virtual twin network layer, by modeling the computing power, link bandwidth, delay performance and the VNF ordering as DT objects and constraints, to jointly optimize the energy consumption, end-to-end delay and the VNF re-deploying cost. Then, the prioritized experience replay and re-parameterization trick-empowered centralized training and decentralized execution MADDPG framework is utilized to learn the SFC deployment, by taking each domain controller as one agent. Finally, numerical experiments are carried out to validate the effectiveness of MADDPG in the cross-domain SFC deployment. For performance verification, the deployment success rate, number of crossed domains, energy consumption, end-to-end latency and load balancing degree are all taken as metrics, to show the performance of MADDPG compared to other learning frameworks.

GCN-Based Multi-Agent Deep Reinforcement Learning for Dynamic Service Function Chain Deployment in IoT

GCN-Based Multi-Agent Deep Reinforcement Learning for Dynamic Service Function Chain Deployment in IoT

Probabilistic Service Function Placement and Dynamic Service Function Chain Formation

Probabilistic Service Function Placement and Dynamic Service Function Chain Formation

A Meta Reinforcement Learning Approach for SFC Placement in Dynamic IoT-MEC Networks

In order to achieve reliability, security, and scalability, the request flow in the Internet of Things (IoT) needs to pass through the service function chain (SFC), which is composed of series-ordered virtual network functions (VNFs), then reach the destination application in multiaccess edge computing (MEC) for processing. Since there are usually multiple identical VNF instances in the network and the network environment of IoT changes dynamically, placing the SFC for the IoT request flow is a significant challenge. This paper decomposes the dynamic SFC placement problem of the IoT-MEC network into two subproblems: VNF placement and path determination of routing. We first formulate these two subproblems as Markov decision processes. We then propose a meta reinforcement learning and fuzzy logic-based dynamic SFC placement approach (MRLF-SFCP). The MRLF-SFCP contains an inner model that focuses on making SFC placement decisions and an outer model that focuses on learning the initial parameters considering the dynamic IoT-MEC environment. Specifically, the approach uses fuzzy logic to pre-evaluate the link status information of the network by jointly considering available bandwidth, delay, and packet loss rate, which is helpful for model training and convergence. In comparison to existing algorithms, simulation results demonstrate that the MRLF-SFCP algorithm exhibits superior performance in terms of traffic acceptance rate, throughput, and the average reward.

Online and reliable SFC protection scheme of distributed cloud network for future IoT application

The implementation of intelligent device-free sensing (IDFS) necessitates a substantial number of edge IoT devices to extend the service coverage. Prior to deploying these IoT applications on a large scale, a reliable service provision scheme is imperative. In recent years, network function virtualization (NFV) technologies enable fast and convenient service provision by instantiating service function chain (SFC) in the distributed cloud network. However, ensuring resilient service provision is a challenge in NFV environment due to the vulnerability of software-defined network functions. Furthermore, the sequential arrangement of virtual network functions (VNFs) in SFC exacerbates the situation, as the malfunction of any VNFs within the SFC could result in the collapse of the associated service. In this paper, we firstly built a mathematical model for SFC online reliability protection and resource consumption optimization. We then propose a multi-mode VNF backup scheme to guarantee the different reliability requirements for various services. Furthermore, a novel SFC Online Reliability Protection (SORP) scheme is introduced to handle the dynamic SFC requests in distributed cloud network. The simulation results evince the efficacy of the SORP scheme in mitigating service failures and achieving a superior request acceptance ratio, while concurrently reducing average bandwidth consumption, which is particularly noteworthy in high latency scenarios.

Dynamic SFC Embedding Algorithm Assisted by Federated Learning in Space–Air–Ground-Integrated Network Resource Allocation Scenario

Traditional terrestrial wireless communication networks cannot support the requirements for high-quality services for artificial intelligence applications such as smart cities. The space-air-ground integrated network (SAGIN) provides a solution to address this challenge. However, SAGIN is heterogeneous, time-varying, and multi-dimensional information sources, making it difficult for traditional network architectures to support resource allocation in large-scale complex network environments. This paper proposes a service provision method based on Service Function Chaining (SFC) to solve this problem. Network Function Virtualization (NFV) is essential for efficient resource allocation in SAGIN to meet the resource requirements of user service requests. We propose a federation learning (FL) based algorithm to solve the embedding problem of SFCs in SAGIN. The algorithm considers different characteristics of nodes and resource load to balance resource consumption. Then an SFC scheduling mechanism is proposed that allows SFC reconfiguration to reduce the service blocking rate. Simulation results show that our proposed FL-VNFE algorithm is more advantageous compared to other algorithms, with 12.9%, 2.52%, and 10.5% improvement in long-term average revenue, acceptance rate, and long-term average revenue-cost ratio, respectively.

Dynamic SFC placement scheme with parallelized SFCs and reuse of initialized VNFs: An A3C-based DRL approach

Mobile Edge Computing (MEC) is a well-known network architecture that extends cloud computing to the network edge. Compared with cloud computing, Network Function Virtualization (NFV) can provide flexible services in MEC for mobile users. Virtual Network Functions (VNFs) have emerged as software-based hardware middleboxes by NFV technology to host real-time applications. Basically, the combination of multiple VNF instances is defined as a Service Function Chain (SFC), which can provide dynamic service requirements in the MEC. Despite the rapid growth of MEC and the widespread support of service providers for SFC, many issues are still challenging and need to be addressed. In MEC scenarios with limited resources, the effective placement of SFCs with the aim of resource efficiency remains a challenging problem. Motivated by the scalability shortcomings of existing schemes to solve dynamic placement of SFCs, we propose Deep Reinforcement Learning (DRL)-based approaches to solve this problem, i.e., Asynchronous Advantage Actor-Critic (A3C). The proposed scheme is based on the reuse of initialized VNFs to improve the Quality of Service (QoS), which is developed with the aim of maximizing the long-term cumulative reward. In addition, a parallel processing approach of SFCs is included in the proposed scheme, which can split the traffic in each flow into sub-flows. This shares the processing load by instantiating duplicate instances of each VNF type in the SFC. The simulation results guarantee the efficiency of the proposed scheme and improves the average performance between 6% and 24% compared to the state-of-the-art clustering methods.

Dynamic Service Function Chain Deployment and Readjustment Method Based on Deep Reinforcement Learning

With the advent of Software Defined Network (SDN) and Network Functions Virtualization (NFV), network operators can offer Service Function Chain (SFC) flexibly to accommodate the diverse network function (NF) requirements of their users. However, deploying SFCs efficiently on the underlying network in response to dynamic SFC requests poses significant challenges and complexities. This paper proposes a dynamic SFC deployment and readjustment method based on deep Q network (DQN) and M Shortest Path Algorithm (MQDR) to address this problem. We develop a model of the dynamic deployment and readjustment of the SFC problem on the basis of the NFV/SFC network to maximize the request acceptance rate. We transform the problem into a Markov Decision Process (MDP) and further apply Reinforcement Learning (RL) to achieve this goal. In our proposed method (MQDR), we employ two agents that dynamically deploy and readjust SFCs collaboratively to enhance the service request acceptance rate. We reduce the action space for dynamic deployment by applying the M Shortest Path Algorithm (MSPA) and decrease the action space for readjustment from two dimensions to one. By reducing the action space, we decrease the training difficulty and improve the actual training effect of our proposed algorithm. The simulation experiments show that MDQR improves the request acceptance rate by approximately 25% compared with the original DQN algorithm and 9.3% compared with the Load Balancing Shortest Path (LBSP) algorithm.

A reinforcement learning approach based on convolutional network for dynamic service function chain embedding in IoT

SummaryNetwork communication technologies are developing rapidly in various scenarios, such as 6G, SDN/NFV, and IoT. And the demand for dynamic service function chain orchestration is increasing day by day. Due to the dynamic complexity of IoT networks, the service function chain (SFC) embedding problem in IoT scenarios is more difficult. In this paper, a reinforcement learning algorithm based on convolutional neural network is first applied to SFC embedding, combined with DQN's experience pool reply and target network mechanism. The proposed scheme is verified in three typical complex networks: Random network, BA scale‐free network, and small‐world network. The experimental data suggest that the applicability of the approach proposed in IoT scenarios and, on the whole, the proposed algorithm can achieve lower latency and faster convergence performance than the mainstream algorithms with the increase of SFC number and node number.

Securing Dynamic Service Function Chain Orchestration in EC-IoT Using Federated Learning

Dynamic service orchestration is becoming more and more necessary as IoT and edge computing technologies continue to advance due to the flexibility and diversity of services. With the surge in the number of edge devices and the increase in data volume of IoT scenarios, there are higher requirements for the transmission security of privacy information from each edge device and the processing efficiency of SFC orchestration. This paper proposes a kind of dynamic SFC orchestration security algorithm applicable to EC-IoT scenarios based on the federated learning framework, combined with a block coordinated descent approach and the quadratic penalty algorithm to achieve communication efficiency and data privacy protection. A deep reinforcement learning algorithm is used to simultaneously adapt the SFC orchestration method in order to dynamically observe environmental changes and decrease end-to-end delay. The experimental results show that compared with the existing dynamic SFC orchestration algorithms, the proposed algorithm can achieve better convergence and latency performance under the condition of privacy protection; the overall latency is reduced by about 33%, and the overall convergence speed is improved by about 9%, which not only achieves the security of data privacy protection of edge computing nodes, but also meets the requirements of dynamic SFC orchestration.

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.

Resource Aware Routing for Service Function Chains in SDN and NFV-Enabled Network

Owing to the Network Function Virtualization (NFV) and Software-Defined Networks (SDN), Service Function Chain (SFC) has become a popular service in SDN and NFV-enabled network. However, as the Virtual Network Function (VNF) of each type is generally multi-instance and flows with SFC requests must traverse a series of specified VNFs in predefined orders, it is a challenge for dynamic SFC formation to optimally select VNF instances and construct paths. Moreover, the load balancing and end-to-end delay need to be paid attention to, when routing flows with SFC requests. Additionally, fine-grained scheduling for traffic at flow level needs differentiated routing which should take flow features into consideration. Unfortunately, traditional algorithms cannot fulfill all these requirements. In this paper, we study the Differentiated Routing Problem considering SFC (DRP-SFC) in SDN and NFV-enabled network. We formulate the DRP-SFC as a Binary Integer Programming (BIP) model aiming to minimize the resource consumption costs of flows with SFC requests. Then a novel routing algorithm, Resource Aware Routing Algorithm (RA-RA), is proposed to solve the DRP-SFC. Performance evaluation shows that RA-RA can efficiently solve the DRP-SFC and surpass the performance of other existing algorithms in acceptance rate, throughput, hop count and load balancing.

Subscriber aware dynamic service function chaining

In this study, a novel subscriber aware dynamic service function chaining (SFC) framework is developed by using open source software-defined networking (SDN) and network function virtualization (NFV) solutions, where the aim is to provide service chaining per user traffic and to transform SGi-LAN services into virtual network functions. With this SFC framework, customer based dynamically applicable value added services can be provided without the need for manual operation that would require vast effort. In order to show the performance and scalability of the proposed framework, the solution is tested in a live telecom lab with varying number of subscribers and thread counts. The test results show that the proposed solution can successfully manage subscribers dynamically without packet loss for 2 million simultaneous subscribers’ traffic flows when the system is overloaded, regardless of hardware or vendor. In addition, it has been observed that the service chain rules can be applied in a very short period such as 2.9 s for 10,000 simultaneous subscriber SFC requests even in the loaded traffic flows, while the CPU consumption of virtual machines remained between 23.5% and 28.5%. These results have proved that the proposed solution can be used in large-scale telecom networks.

BCOOL: A Novel Blockchain Congestion Control Architecture Using Dynamic Service Function Chaining and Machine Learning for Next Generation Vehicular Networks

This paper presents the first, novel, dynamic, resilient, and consistent Blockchain COngestion ContrOL (BCOOL) system for vehicular networks that fills the gap of trustworthy Blockchain congestion prediction systems. BCOOL relies on the heterogeneity of Machine Learning, Software-Defined Networks and Network Function Virtualization that is customized in three hybrid cloud/edge-based On/Offchain smart contract modules and ruled by an efficient and reliable communication protocol. BCOOL’s first novel module aims at managing message and vehicle trustworthiness using a novel, dynamic and hybrid Blockchain Fog-based Distributed Trust Contract Strategy (FDTCS). The second novel module accurately and proactively predicts the occurrence of congestion, ahead of time, using a novel Hybrid On/Off-Chain Multiple Linear Regression Software-defined Contract Strategy (HOMLRCS). This module presents a virtualization facility layer to the third novel K-means/Random Forest-based On/Off-Chain Dynamic Service Function Chaining Contract Strategy (KRF-ODSFCS) that dynamically, securely and proactively predicts VNF placements and their chaining order in the context of SFCs w.r.t users’ dynamic QoS priority demands. BCOOL exhibits a linear complexity and a strong resilience to failures. Simulation results show that BCOOL outperforms the next best comparable strategies by 80% and 100% reliability and efficiency gains in challenging data congestion environments. This yields to fast, reliable and accurate congestion prediction decisions, ahead of time, and optimizes transaction validation processing time. Globally, the Byzantine resilience, complexity and attack mitigation strategies along with simulation results prove that BCOOL securely predicts the congestion and provides real-time monitoring, fast and accurate SFC deployment decisions while lowering both capital and operational expenditures (CAPEX/OPEX) costs.

Dynamic Service Function Chain Orchestration for NFV/MEC-Enabled IoT Networks: A Deep Reinforcement Learning Approach

Network function virtualization (NFV) and mobile-edge computing (MEC) have been introduced by Internet service providers (ISPs) to deal with various challenges, which hinder them from satisfying ambitious quality of experience demands of the Internet-of-Things (IoT) applications. In NFV/MEC-enabled IoT networks, any IoT service can be expressed as a service function chain (SFC) consisting of several strictly ordered virtual network functions (VNFs), which can be geographically placed onto edge clouds close to IoT terminals. However, regarding the large number of IoT terminals and constant dynamics of IoT networks, determining the placement of VNFs and routing service paths that optimize the end-to-end delays in the hybrid edge clouds is a challenging problem. This problem is also called SFC dynamic orchestration problem (SFC-DOP). To address the SFC-DOP, we are motivated to creatively present an SFC dynamic orchestration framework for IoT deep reinforcement learning (DRL). Also, a DRL-based algorithm for SFC-DOP with the actor–critic and the deterministic policy gradient scheme is provided, which can efficiently deal with the SFC-DOP in IoT networks. The obtained experimental results show the outstanding performance of our proposal compared with the current benchmarks.

A Novel Approach for Service Function Chain Dynamic Orchestration in Edge Clouds

Network function virtualization (NFV) and mobile edge computing (MEC) are two of the promising technologies that are expected to play a critical role in mobile edge cloud networks, thus satisfying ambitious quality of experience (QoE) requirements of the Internet of things (IoT) applications. In MEC-NFV system, a service function chain (SFC) consists of an ordered set of virtual network functions (VNFs) that are connected based on the business logic of service providers. However, the inefficiency of the SFC orchestration process is one major problem due to the dynamic nature of mobile edge cloud networks and abundance of IoT terminals. In this letter, a quantum machine learning (QML)-based scheme is proposed as solution that can handle complex and dynamic SFC orchestration in mobile edge cloud networks. Simulation results show that our proposal significantly provides more than 8-fold reduction of run time compared to the Viterbi algorithm, and the end-to-end delay is only about 1.1 times of the exact solution.

Dynamic Service Function Chain Embedding for NFV-Enabled IoT: A Deep Reinforcement Learning Approach

The Internet of things (IoT) is becoming more and more flexible and economical with the advancement in information and communication technologies. However, IoT networks will be ultra-dense with the explosive growth of IoT devices. Network function virtualization (NFV) emerges to provide flexible network frameworks and efficient resource management for the performance of IoT networks. In NFV-enabled IoT infrastructure, service function chain (SFC) is an ordered combination of virtual network functions (VNFs) that are related to each other based on the logic of IoT applications. However, the embedding process of SFC to IoT networks is becoming a big challenge due to the dynamic nature of IoT networks and the abundance of IoT terminals. In this paper, we decompose the complex VNFs into smaller virtual network function components (VNFCs) to make more effective decisions since VNF nodes and IoT network devices are usually heterogeneous. In addition, a deep reinforcement learning (DRL) based scheme with experience replay and target network is proposed as a solution that can efficiently handle complex and dynamic SFC embedding scenarios in IoT. Our simulations consider different types of IoT network topologies. The simulation results present the efficiency of the proposed dynamic SFC embedding scheme.