SDN Controller Research Articles

LSTM-BASED SERVER AND ROUTE SELECTION IN DISTRIBUTED AND HETEROGENEOUS SDN NETWORK

Today, the Software-defined Network, with its advantages such as greater reliability via automation, more efficient network management, cost-savings, and faster scalability, is increasingly being deployed in many network systems and network operators. The most common deployment architecture is a distributed system with the existence of many independent domains, each controlled by an SDN controller. One of the well-known applications in SDN is server selection and routing. However, deploying server and route selection in distributed and heterogeneous SDN networks faces two issues. First, the lack of global views of the whole system is because the inter-communication between SDN domains has not been standardized for the distributed and heterogeneous SDN network. To solve this issue, we use our previous work, an open East-West interface called SINA, to adaptively guarantee the network state consistency of the distributed SDN network with multiple domains. Secondly, selecting the path for packet transmission based only on the current network states of a local SDN domain is ineffective as it can bring over-utilization to several links and under-utilization to others. Predicting the link cost of the whole path from the source to the destination is necessary. Therefore, this paper proposes an LSTM-based link cost prediction for the server and route selection mechanism in a distributed and heterogeneous SDN network. The experimental results show that our proposal improves up to 15% of link utilization, reduces 10% of packet loss, and obtains the lowest servers’response time compared to benchmarks

Elastic Provisioning of Network and Computing Resources at the Edge for IoT Services

The fast growth of Internet-connected embedded devices demands new system capabilities at the network edge, such as provisioning local data services on both limited network and computational resources. The current contribution addresses the previous problem by enhancing the usage of scarce edge resources. It designs, deploys, and tests a new solution that incorporates the positive functional advantages offered by software-defined networking (SDN), network function virtualization (NFV), and fog computing (FC). Our proposal autonomously activates or deactivates embedded virtualized resources, in response to clients' requests for edge services. Complementing existing literature, the obtained results from extensive tests on our programmable proposal show the superior performance of the proposed elastic edge resource provisioning algorithm, which also assumes an SDN controller with proactive OpenFlow behavior. According to our results, the maximum flow rate for the proactive controller is 15% higher; the maximum delay is 83% smaller; and the loss is 20% smaller compared to when the non-proactive controller is in operation. This improvement in flow quality is complemented by a reduction in control channel workload. The controller also records the time duration of each edge service session, which can enable the accounting of used resources per session.

A Security Enforcement Framework for SDN Controller Using Game Theoretic Approach

Software-defined networking (SDN) has gained significant attention as the future deployment platform for the Internet and enterprise networks. The major advantages of SDN include effective traffic management, dynamic configuration of policy and flow rules, and better scalability with heterogeneous traffic requirements. However, centralized network control and the use of OpenFlow protocols introduce various security challenges for the underlying network. The attacks on the SDN controller is critical as it hosts all network control functions. Motivated by a systematic analysis of different attack scenarios in SDN using the STRIDE attack model, this article presents an effective security enforcement framework for proactive prevention of potential attacks on SDN controllers. First, based on a signaling game approach, we design a trust-based controller attack detection (TCAD) model that calculates the trust value of each incoming packet to take necessary action. Next, we propose a risk-based attack prevention (RAP) model that detects and filters malicious traffic flows in the network. Finally, we evaluate our proposed security enforcement framework on different scenarios with varying traffic requirements and by injecting attacks based on the STRIDE model. Experimental results show 95% accuracy in the potential attack detection and prevention.

ARARAT: A Collaborative Edge-Assisted Framework for HTTP Adaptive Video Streaming

With the ever-increasing demands for high-definition and low-latency video streaming applications, network-assisted video streaming schemes have become a promising complementary solution in the HTTP Adaptive Streaming (HAS) context to improve users’ Quality of Experience (QoE) as well as network utilization. Edge computing is considered one of the leading networking paradigms for designing such systems by providing video processing and caching close to the end-users. Despite the wide usage of this technology, designing network-assisted HAS architectures that support low-latency and high-quality video streaming, including edge collaboration is still a challenge. To address these issues, this article leverages the Software-Defined Networking (SDN), Network Function Virtualization (NFV), and edge computing paradigms to propose A collaboRative edge-Assisted framewoRk for HTTP Adaptive video sTreaming (ARARAT). Aiming at minimizing HAS clients’ serving time and network cost, besides considering available resources and all possible serving actions, we design a multi-layer architecture and formulate the problem as a centralized optimization model executed by the SDN controller. However, to cope with the high time complexity of the centralized model, we introduce three heuristic approaches that produce near-optimal solutions through efficient collaboration between the SDN controller and edge servers. Finally, we implement the ARARAT framework, conduct our experiments on a large-scale cloud-based testbed including 250 HAS players, and compare its effectiveness with state-of-the-art systems within comprehensive scenarios. The experimental results illustrate that the proposed ARARAT methods (i) improve users’ QoE by at least 47%, (ii) decrease the streaming cost, including bandwidth and computational costs, by at least 47%, and (iii) enhance network utilization, by at least 48% compared to state-of-the-art approaches.

Reliably Route IoT Packets in Software Defined mmWave Mesh Networks

Although millimeter wave (mmWave) mesh networks provide large bandwidth to deliver IoT packets, link failure caused by non-light-of-sight (NLoS) condition degrades network reliability. With the assistance of software defined networking (SDN), we propose a Fast link failure Recovery Routing (FastReRoute) framework to instantly re-route packets from the failed links to another ones minimizing packet loss. Upon a link fails, FastReRoute first re-routes packets via the pre-configured local backup path. FastReRoute conditionally re-routes packets again according to the management using the SDN controller. We integrate FastReRoute into Mininet for performance evaluation. This demonstrates FastReRoute effectively sustains the network reliability.

Mobility-Aware Proactive Flow Setup in Software-Defined Mobile Edge Networks

The software-defined network (SDN) enabled mobile edge network greatly facilitates network resource management and promotes many emerging applications. However, user mobility may cause the SDN controller to set flow rules frequently, introduce additional flow setup latency, cause delay jitter, and undermine latency-sensitive services. Proactive flow setup is an effective way to eliminate flow setup latency, but existing work fails to maximize the flow setup hit ratio, a metric for evaluating the quality of proactive flow setup decisions, which is critical for latency-sensitive services. In this paper, we study how to proactively set flow rules to maximize the flow setup hit ratio under limited available network resources to eliminate the flow setup latency as much as possible. Then, we formalize the proactive flow setup problem as two integer linear programming problems under two typical routing strategies, default routing and dynamic routing. Both problems are proved to be NP-hard. To tackle these two problems, we propose a linear programming-based polynomial-time approximation algorithm for the default routing case and a greedy-based heuristic algorithm for the dynamic routing case. Extensive trace-driven experimental and simulation results verify that our algorithms can improve the flow setup hit ratio by up to 30.99% compared to existing solutions.

From Control to Chaos: The Dynamic SDN Control Plane

Software-defined networking (SDN) has revolutionized the way networks are designed and managed, with the control plane being a critical component. The SDN control plane is responsible for managing and orchestrating network traffic flows, but its traditional static approach can be limiting in dynamic and complex network environments. This abstract explores the concept of a dynamic SDN control plane, which can adapt and respond to changing network conditions, leading to better network performance and efficiency. The dynamic control plane involves the use of machine learning algorithms, artificial intelligence, and network analytics to constantly monitor and adjust network policies in real-time. The dynamic SDN control plane empowers networks to move from a state of control to chaos, enabling greater flexibility, agility, and resilience in network management. This abstract provides insights into the potential benefits of a dynamic SDN control plane and highlights the challenges and opportunities in implementing this approach.

Go-to-Controller is Better: Efficient and Optimal LPM Caching with Splicing

Modern data center networks are required to support huge and complex forwarding policies as they handle the traffic of the various tenants. However, these policies cannot be stored in their entirety within the limited memory available at commodity switches. The common approach in such scenarios is to have SDN controllers manage the memory available at the switch as a fast cache, updating and changing the forwarding rules in the cache according to the workloads dynamics and the global policy at hand. Many such policies, such as Longest-prefix-match (LPM) policies, introduce dependencies between the forwarding rules. Ensuring that the cache content is always consistent with the global policy often requires the switch to store (potentially many) superfluous rules, which may lead to suboptimal performance in terms of delay and throughput. To overcome these deficiencies, previous work suggested the concept of splicing, where modified Go-to-Controller rules can be inserted into the cache to improve performance while maintaining consistency. These works focused mostly on heuristics, and it was conjectured that the problem is computationally intractable. As our main result, we show that the problem of determining the optimal set of rules, with splicing, can actually be solved efficiently by presenting a polynomial-time algorithm that produces an optimal solution, i.e., for a given cache size we find an optimal set of rules, some of which are go-to-controller, which maximize the total weight of the cache while maintaining consistency. However, such optimality comes at a cost, encompassed by the fact that our algorithm has a significantly larger running time than SoTA solutions which do not employ splicing. Therefore, we further present a heuristic exhibiting close-to-optimal performance, with significantly improved running time, matching that of the best algorithm, which does not employ splicing. In addition, we present the results of an evaluation study that compares the performance of our solutions with that of SoTA approaches, showing that splicing can reduce the cache miss ratio by as much as 30%, without increasing the cache size. Lastly, we propose a simple and fast-to-compute metric (that is consistency-oblivious) in order to evaluate the potential benefits of splicing compared to classical LPM-caching, for a given policy and traffic distribution. We show that our metric is highly correlated with such benefits, thus serving as an indication of whether splicing should be incorporated within the system architecture.

SDN-enabled Resource Provisioning Framework for Geo-Distributed Streaming Analytics

Geographically distributed (geo-distributed) datacenters for stream data processing typically comprise multiple edges and core datacenters connected through Wide-Area Network (WAN) with a master node responsible for allocating tasks to worker nodes. Since WAN links significantly impact the performance of distributed task execution, the existing task assignment approach is unsuitable for distributed stream data processing with low latency and high throughput demand. In this paper, we propose SAFA, a resource provisioning framework using the Software-Defined Networking (SDN) concept with an SDN controller responsible for monitoring the WAN, selecting an appropriate subset of worker nodes, and assigning tasks to the designated worker nodes. We implemented the data plane of the framework in P4 and the control plane components in Python. We tested the performance of the proposed system on Apache Spark, Apache Storm, and Apache Flink using the Yahoo! streaming benchmark on a set of custom topologies. The results of the experiments validate that the proposed approach is viable for distributed stream processing and confirm that it can improve at least 1.64× the processing time of incoming events of the current stream processing systems.

An Intelligence-Defined Networking Architecture With Importance-Based Network Resource Control

As network complexity increases because of the diversification of applications and services based on Internet of Autonomous Things (IoAT), it is difficult for humans to design the optimal control rule for software-defined networking (SDN) controllers. Intelligence-defined networking, called IDN, is proposed to overcome this limitation through machine learning (ML) algorithms. Since the existing IDN approaches are mostly designed to optimize only the network Quality of Services (QoS), including throughput, jitter, and latency, the controllers do not consider the importance of data in the applications and the services. This causes the controller to allocate insufficient resources to the crucial data flow, which leads critical problems, such as self-driving car accidents. To prevent this problem, we propose an importance-based IDN architecture that enables network controllers to manage network traffic with an importance levels (ILs) of data flows. First, we devise an importance estimation scheme to set the IL for the flows. Second, a dynamic resource allocation model of the controllers is developed by means of deep learning algorithms in order to make the optimal network resource. Additionally, an online learning mechanism based on weighted auto-labeling is adopted to continue enhancing the adaptability of the resource allocation model on runtime as the network conditions change. The evaluation results of the proposed architecture under various autonomous things scenarios show that the loss rate for data flows of higher importance is reduced by one-quarter compared to the case of a network controller without IL and that the bandwidth waste ratio is reduced by 10% compared to the rule-based model.

Distributed Cross-Domain Optimization for Software Defined Industrial Internet of Things

As a promising paradigm, the Industrial Internet of Things (IIoT) provides a wide range of intelligent services through the interconnection and interaction of heterogeneous networks. The quality of these services depends on how the bandwidth is shared among different flows. Hence, it is critical to design a flexible flow control strategy in multi-region management scenarios. In this paper, we establish a flow optimization model based on the IIoT networks managed by multiple Software-Defined Networking (SDN) controllers. Specifically, it jointly optimizes the real-time delivery, route selection, and constrained resource allocation to maximize the total utilities of domains. Since the topology and resources within each domain are kept secret, the problem model belongs to a multi-block problem with coupling constraints, which is difficult to be solved directly. To this end, we first decompose the problem into several intra-domain subproblems, which can be solved in parallel. By considering the inter-domain communication problem, we then introduce the slack variables to implement the interaction among domains. Finally, we design a distributed Proximal Symmetric Alternating Direction Method of Multipliers (Prox-SADMM) algorithm to solve the above joint optimization problem. Through numerical simulations, we investigate the impact of data timeliness, multi-path routing, and resource constraints on the rate utility. The performance analysis confirms that the Prox-SADMM algorithm can be well applied to large-scale networks and provides guidance to set appropriate parameter values according to the realistic requirements of IIoT networks.

Defense Against Software-Defined Network Topology Poisoning Attacks

Software-Defined Network (SDN) represents a new network paradigm. Unlike conventional networks, SDNs separate control planes and data planes. The function of a data plane is enabled using switches, whereas that of a control plane is facilitated by a controller. The controller learns network topologies and makes traffic forwarding decisions. However, some serious vulnerabilities are gradually exposed in the topology management services of current SDN controller designs. These vulnerabilities mainly exist in host tracking and link discovery services. Attackers can exploit these weak points to poison the network topology information in SDN controllers. In this study, a novel solution is proposed to defend against topology poisoning attacks. By analyzing the existing topology attack principles and threat models, this work constructs legal conditions for host migration to detect host hijacking attacks. The checking of the Link Layer Discovery Protocol (LLDP) source and integrity is designed to defend against link fabrication attacks. A relay-type link fabrication attack detection method based on entropy is also designed. Results show that the proposed solution can effectively detect existing topological attacks and provide complete and comprehensive topological security protection.

Performance evaluation of software-defined networking controllers in wired and wireless networks

Traditional networking solutions are unable to meet modern computing needs due to the expanding popularity of the internet, which requires increased agility and flexibility. To meet these objectives, software-defined networking (SDN) arises. A controller is a major element that will determine if SDN succeeds or fails. Various current SDN controllers in many sectors must be evaluated and compared. The performance of two well-known SDN controllers, POX and Ryu, is evaluated in this research. We used the Mininet-WiFi emulator to implement our work and the distributed internet traffic generator (D-ITG) to assess the aforementioned controllers using delay, jitter, packet loss, and throughput metrics. What is new in our research is the study of network performance in two different types of transmission media: wired and wireless. The speed of the wired medium was chosen to be fast ethernet, which was not previously studied. In addition, the size of the packet was varied among 128, 256, 512, and 1,024 bytes. The comparison was performed on three topologies (single, linear, and tree). The experimental results showed that Ryu offers significantly lower latency, jitter, and packet loss than POX in most scenarios. Also, the Ryu controller has higher throughput than POX, especially on wireless networks.

Nx-IoT: Improvement of Conventional IoT Framework by Incorporating SDN Infrastructure

The rapid advancement of the Internet of Things (IoT) in real-world applications has attracted immense research endeavors in the last few years. It has got tremendous potential in industrial automation and various other fields. The use of IoT has changed the perspective of general applications in today’s world. In this article, a next-generation architecture, Nx-IoT, is proposed for conventional 6LoWPAN-based IoT. The proposed Nx-IoT architecture works in two modes: 1) single controller-based (6SSDx) and 2) multicontroller-based (6MSDx). The Nx-IoT architecture uses new algorithms for routing management and load distribution among the SDN controllers. The experimentation is carried out in a prototype testbed environment. The result shows improved performances in terms of round trip and packet drop, compared to the conventional 6LoWPAN and cloud system. The proposed Nx-IoT architecture reduces the latency and shows better throughput performances as compared to the existing state of the art.

Enhancing Software-Defined Networks with Intelligent Controllers to Improve First Packet Processing Period

Software-Defined Networking (SDN) has a detailed central model that separates the data plane from the control plane. The SDN controller is in charge of monitoring network security and controlling data flow. OpenFlow-enabled routers and switches work as packet-forwarding devices in the network system. At first, OpenFlow forwarding devices like routers and switches do not know how to handle the data packets transmitted by the host. This is because they do not have any security controls, policies, or information. These packets are sent to their destination. In this situation, the OpenFlow forwarding device sends the first data packet of a host to the SDN controller, which checks the control packets for the data packet and creates flow entries in the switch flow table to act on the following categories of data packets coming from the host. These activities at the SDN controller and switch levels are time-intensive, and the first data packet from the host always takes a longer time to reach its destination. In this article, we suggest an SDN controller with instant flow entries (SDN-CIFE) to reduce the amount of time it takes for the host to transmit its first data packet. Before traffic comes from the host, our method adds the necessary flow entries to the flow table of the OpenFlow switch. The technique was made in Python and tested on a Mininet network emulator using the RYU controller. The results of the experiment show that the time it takes to process the first data packet is reduced by more than 83%.

Adaptive population-based multi-objective optimization in SDN controllers for cost optimization

In Wireless Sensor Networks, Software Defined Networks (SDN) provide a logically centralized control plane as a potential means of streamlining network management (WSNs). The employment of several SDN controllers to build a physically distributed SDN is a common tactic to boost speed, expand scalability, and offer fault tolerance. However, the deployment of many controllers results in increased synchronization and deployment expenses. Therefore, selecting the optimal location for SDN controllers to improve WSN performance is a research issue. In this paper, the multi-objective optimization problem known as the controller placement problem (CPP) is initially formulated. Cost, time, and reliability are just a few of the restraints that are taken into consideration in this regard. In addition, a new Adaptive Population-Based Cuckoo Optimization (APB-CO) for optimal controller placement is implemented. In the end, APB-CO performs experiments to validate the efficacy by analyzing Sync (7.5), Coverage (47), Controller Cost (4.8), and Fitness (0.6983) for the 100th node variation at network 1. The proposed model obtained the controller cost as 34.4, compared to the existing method such as Simulated Annealing (44.3) and Greedy Approach (42.6).

A multi-aerial base station assisted joint computation offloading algorithm based on D3QN in edge VANETs

With the rapid development of Internet of Vehicle technology, vehicular edge computing is gradually becoming a key technology for task offloading and resource scheduling. However, the application of traditional base station and vehicle edge network processing introduces large latency, energy consumption and QoS degradation issues for sensitive intensive tasks. To address these issues, we propose a Multi-Aerial Base Station Assisted Joint Computation Offload algorithm based on D3QN in Edge VANETs (MAJVD3). The use of SDN Controllers senses global information and enables efficient resource scheduling. Firstly, a non-convex optimization problem is formulated and proved as an NP-hard problem by combining optimization variables, metrics and environmental constraints. Secondly, we propose to use ϵ-greedy MAJVD3 algorithm for interactive exploration with a dynamic environment to find the optimal solution to non-convex optimization problem. Finally, the network performance, applicability and neural network learning are evaluated separately, and the simulation results shows the effectiveness and convergence of the proposed algorithm. Compared with the existing baseline algorithms, the proposed MAJVD3 algorithm improves the network utility by 4.8%, 100% and 149.6%, respectively. The task latency is reduced by 3%, 30.4% and 30.7%, respectively, and the energy consumption is reduced by 4.8%, 42.3% and 45.7%, respectively.

A P4-assisted task offloading scheme for Fog networks: An intelligent transportation system scenario

In Fog-based Internet of Things (IoT) networks, Fog computing offers great promises to achieve efficient task processing among IoT devices and the Cloud with lower processing delay and a lighter bandwidth burden. However, the sustainability of these networks is critical so that Fog servers efficiently allocate/offload increasing task types to appropriate resources. In this paper, a novel task offloading scheme called Task Offloading Scheme with P4 (TOS-P4) is proposed for Fog-based IoT networks using Programming Protocol-independent Packet Processors (P4) technology. The proposed scheme is evaluated through an Intelligent Transportation System (ITS) application scenario and compared to a conventional model called Task Offloading Scheme with Software-Defined Networking controller (TOS-SDN). In this scenario, the network traffic is regulated by P4, allowing task offload decisions to be more flexible and programmable according to server loads and predetermined forwarding rules. We present the applicability of the proposed task offloading scheme in the Fog-based IoT network and its benefits to network performance in terms of latency and computation overhead. According to the experimental results, when the servers’ load status is measured at 5 s intervals, TOS-P4 is 6.54 times more efficient than TOS-SDN in waiting times of tasks received at Resource Poor (RP) Fog servers. Also, in TOS-SDN case, the average waiting time of a task on RP Fog servers is 30 times more compared to Resource Rich (RR) Fog servers.

(INVITED)Reconfigurable topology testbeds: A new approach to optical system experiments

Optical transmission systems provide high capacity, low latency and jitter, and high reliability for city-scale networks. Recirculating loop experiments have facilitated the study of signal propagation in long-haul optical transmission systems. However, they are unsuited for developing control and management software for city-scale optical networks with dozens or hundreds of reconfigurable optical add drop multiplexer (ROADM) units, diverse interconnection topologies, and dynamic traffic patterns. Large-scale testbeds can help, but may be inflexible and time- or cost-prohibitive. Reconfigurable testbeds such as COSMOS enable piece-wise emulation of a city-scale network by applying space and wavelength switching, dual-use software-defined networking (SDN) controllers, and comb sources, while digital twin models enable software emulation. Results from the development of a digital twin for COSMOS are presented for optical amplifiers and stimulated Raman scattering (SRS) including both analytical and machine learning (ML) models.

SDN-Based Security for Smart Devices Against Denial of Service Attacks

Objectives: To achieve a reliable IoT environment by mitigating the DoS attack. Methods: The study focuses on building a firewall on an Open Flow-based Software Defined Networking (SDN) controller to secure a network. We chose the POX controller, which is based on the Python programming language, from among various controllers. Furthermore, a detailed analysis of denial of service attacks against IoT devices has been carried out using Wireshark. Findings: SDN design allows networks to actively monitor traffic and diagnose threats, making network management easier. DoS & DDoS attack is simulated for IoT application which resulted in the loss of packets. Novelty: When compared to the traditional firewall where the internal traffic cannot be seen and filtered, SDN based firewall can filter the packet based on the policy defined. Here the experiment is carried out using open-source software.SDN security was built into the architecture to ensure the availability, integrity, and privacy of all connected resources and information. SDN-based Firewall is used as a solution against the denial of service attack. Through simulation, we have found and analyzed an efficient unsupervised method for detecting DDoS. Keywords: Network Attack; Smart Devices; Security; Firewall; Software Defined Network