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.

The emerging paradigm - Software-Defined Networking (SDN) and Network Function Virtualization (NFV) - makes it feasible and scalable to run Virtual Network Functions (VNFs) in commercial-off-the-shelf devices, which provides a variety of network services with reduced cost. Benefitting from centralized network management, lots of information about network devices, traffic and resources can be collected in SDN/NFV-enabled networks. Using powerful machine learning tools, algorithms can be designed in a customized way according to the collected information to efficiently optimize network performance. In this paper, we study the VNF placement problem in SDN/NFV-enabled networks, which is naturally formulated as a Binary Integer Programming (BIP) problem. Using deep reinforcement learning, we propose a Double Deep Q Network-based VNF Placement Algorithm (DDQN-VNFPA). Specifically, DDQN determines the optimal solution from a prohibitively large solution space and DDQN-VNFPA then places/releases VNF Instances (VNFIs) following a threshold-based policy. We evaluate DDQN-VNFPA with trace-driven simulations on a real-world network topology. Evaluation results show that DDQN-VNFPA can get improved network performance in terms of the reject number and reject ratio of Service Function Chain Requests (SFCRs), throughput, end-to-end delay, VNFI running time and load balancing compared with the algorithms in existing literatures.

With the advances of Software-Defined Networks (SDN) and Network Function Virtualization (NFV), Service Function Chain (SFC) has been becoming a popular paradigm to carry and complete network services. Such new computing and networking paradigm enables Virtual Network Functions (VNFs) to be placed in software entities/virtual machines over a network of physical equipments in elastic and flexible way with low capital and operation expenses. VNFs are chained together to steer traffic as needed. However, most of the existing traffic steering and routing path computation algorithms for SFC are complex, unscalable, and low time-efficiency. In this paper, we study the VNF Selection and Chaining Problem (VNF-SCP) in SDN/NFV-enabled networks. We formulate VNF-SCP as a Binary Integer Programming (BIP) model in order to compute routing path for each SFC Request (SFCR) with the minimum end-to-end delay. Then, a novel Deep Learning-based Two-Phase Algorithm (DL-TPA) is introduced, where VNF selection network and VNF chaining network are designed to achieve intelligent and efficient VNF selection and chaining for SFCRs. Performance evaluation shows that DL-TPA can achieve high prediction accuracy and time efficiency of routing path computation, and the overall network performance can be improved significantly.

Distributed Denial of Service (DDoS) attack is threatening network security with increasing number of DDoS attack events. Software Defined Network (SDN), a popular networking paradigm, brings many opportunities to defend against massive network attacks with its centralized control architecture. In this background, this paper proposes a DDoS attack detection and mitigation system, DETPro, which is an efficient and lightweight framework based on decision tree method. In this system, the POX controller and sFlow agents embedded in OpenvSwitch are responsible for network traffic information collection. The DDoS attack detection module implemented with a modified decision tree algorithm is applied to detect DDoS attacks, utilizing Gini impurity and Pessimistic Error Pruning (PEP) strategy. When attacks appear in the network, the DDoS attack mitigation module keeps the major network functionality working with a dynamic white list mechanism, which can timely block attack traffic and assure benign traffic to be served as usual. Experimental results show that DETPro can detect DDoS attack accurately and protect the network from various DDoS attacks effectively.

Benefiting from Network Function Virtualization (NFV), Service Function Chain (SFC) that is composed of a set of ordered Virtual Network Functions (VNFs) has become a popular network service pattern. One of the most important issues for Internet Service Providers (ISPs) is to determine the optimal placement of VNFs and the traffic steering of SFC to optimize the total network cost while guaranteeing resource constraints. In this paper, we study the cost-efficient VNF Placement and Traffic Steering (VNFP-TS) problem. First, we formulate the problem as a Binary Integer Programming (BIP) model aiming to minimize the node running cost, VNF placement cost and communication cost jointly. Then a heuristic Dynamic Programming based Cost Optimization Algorithm (DP-COA) is proposed to divide and conquer the problem. Finally, we evaluate the proposed algorithm by numerical simulations and confirm that DP-COA can achieve high network performance in terms of acceptance rate of SFC Requests (SFCRs) and throughput, and efficiently reduce the total network cost comparing with algorithms in existing literatures.

Energy Harvesting (EH)-based cellular communication has emerged for the merit of simple deployment and continuous energy supply recently. However, the amounts of harvested energy are not always enough to meet the communication requirements of cellular devices. In this paper, we propose an energy cooperation scheme taking advantage of Device-to-Device (D2D) relaying technology, in which those devices with insufficient energy are aided by others to accomplish data transmission. In this scheme, we study the energy efficiency optimization problem, which involves the D2D relay selection, spectrum reusing and power allocation issues. Mathematically, it is formulated as a Mixed-Integer Nonlinear Programming (MINLP) problem, which turns out to be NP-hard. Thus we make a detailed mathematical analysis to the problem and introduce a two-layer optimization algorithm, and based on which, a suboptimal solution with lower computational complexity is then proposed. The simulation results show that the schemes are valid and can achieve significant improvement in system transmission rate and the satisfaction rate of users' communication requirements.

With the development of Software-Defined Networks (SDNs) and Network Function Virtualization (NFV), Service Function Chains (SFCs), that steer the traffic through a series of specified Virtual Network Functions (VNFs) with predefined orders, has become a popular network service paradigm. Compared with the rule-based routing algorithms, deep-learning technology has great potential to achieve efficient path computation for SFC Requests (SFCRs) in an intelligent way. However, traditional intelligent models have trouble in the speed of convergence, which incurs long training time and high computation consumptions. In this paper, we propose a novel Multi-Task Deep Learning (MTDL) based architecture, which improve generalization by sharing related information of tasks, to assure fast convergence in training process, and an MTDL-based Routing Algorithm (MTDL-RA) to efficiently compute routing paths with the minimum end-to-end delay for SFCRs. Performance evaluation results demonstrate that our proposed MTDL-based architechture and routing algorithm can achieve significantly reduction in the training time and obtain high performance in terms of SFCR acceptance rate and the delay of paths, respectively.

By means of network function virtualization (NFV), dedicated proprietary network devices can be implemented as software and instantiated flexibly on common-off-the-shelf servers, in the form of virtual network functions (VNF). NFV can bring great cost reduction as well as operation flexibility. However, it also brings new problems, one of which is how to meet the availability of network services in the VNF deployment process, because of the error prone nature of software. The availability aware VNF deployment problem has attracted attention by academics, and reserving redundancy has been treated as the de facto technology. Compared with traditional backup schemes for physical machines, resource orchestration in NFV is more flexible and the characteristics of software should be considered to improve resource utilization efficiency. Based on the above considerations, in this paper we further study the availability aware VNF deployment problem in datacenter networks. To improve the resource utilization efficiency, the sharing mechanism of redundancy and multi-tenancy technology are taken into account. Then we formulate the problem mathematically and propose a joint deployment and backup scheme (JDBS). Finally, we conduct a numerical simulation in detail and compare it with four contrasting schemes in the existing literature. The simulation results show that JDBS is obviously superior to the contrasting schemes and can save about 40% resources at most.

Network Function Virtualization (NFV) and Software-Defined Networks (SDN) enable Internet Service Providers (ISPs) to place Virtual Network Functions (VNFs) to achieve the performance and security benefit without incurring high Operating Expenses (OPEX) and Capital Expenses (CAPEX). In NFV environment, Service Function Chains (SFCs) always need to steer the traffic through a series of VNF instances in predefined orders. Moreover, the required number and placement of VNF instances should be optimized to adapt to dynamic network load. Therefore, it is considerable for ISPs to conduct an optimal SFC embedding strategy to improve the network performance and revenue. In the paper, we study the SFC Embedding Problem (SFC-EP) with dynamic VNF placement in geo-distributed cloud system. We formulate this problem as a Binary Integer Programming (BIP) model aiming to embed SFC requests with the minimum embedding cost. Furthermore, the novel SFC eMbedding APproach (SFC-MAP) and VNF Dynamic Release Algorithm (VNF-DRA) have been proposed to efficiently embed SFC requests and optimize the number of placed VNF instances. Performance evaluation results show that the proposed algorithms can provide higher performance in terms of SFC request acceptance rate, network throughput, and mean VNF utilization rate and efficiently reduce the total VNF running time compared with the algorithms in existing literatures.

Network function virtualization (NFV) brings great conveniences and benefits for the enterprises to outsource their network functions to the cloud datacenter. In this paper, we address the virtual network function (VNF) placement problem in cloud datacenter considering users' service function chain requests (SFCRs). To optimize the resource utilization, we take two less-considered factors into consideration, which are the time-varying workloads, and the basic resource consumptions (BRCs) when instantiating VNFs in physical machines (PMs). Then the VNF placement problem is formulated as an integer linear programming (ILP) model with the aim of minimizing the number of used PMs. Afterwards, a Two-StAge heurisTic solution (T-SAT) is designed to solve the ILP. T-SAT consists of a correlation-based greedy algorithm for SFCR mapping (first stage) and a further adjustment algorithm for virtual network function requests (VNFRs) in each SFCR (second stage). Finally, we evaluate T-SAT with the artificial data we compose with Gaussian function and trace data derived from Google's datacenters. The simulation results demonstrate that the number of used PMs derived by T-SAT is near to the optimal results and much smaller than the benchmarks. Besides, it improves the network resource utilization significantly.