Adaptive flow routing model in SDN

Beshley, Mykola; Seliuchenko, Marian; Panchenko, Oleksiy; Polishuk, Artur

doi:10.1109/cadsm.2017.7916140

Cited by 40 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clearly, as Eqs. (2) and (3) indicate, the design of action A t has an impact on the size of the action space |A|. A disadvantage of the Direct Change approach is that the action space scales with the product of the numbers of possible paths for the flows; in contrast, the action space of OneFlow Change scales with the sum of the numbers of possible paths for the flows, as analyzed in more detail in Section IV-C4.…”

Section: B Action-space Designmentioning

confidence: 99%

“…The values, in turn, are dictionaries with an action, see Eqs. (2) and 3, as key and the actual Q-value as value, i.e.,…”

Section: Reinforcement Learning Agent 1) Q-learningmentioning

confidence: 99%

“…The centralized controller has global knowledge of the network status, i.e., all the switching nodes and their interconnecting links, as well as network monitoring metrics. SDN appears therefore very well suited to enable the optimization of flow routing [2]- [4].…”

mentioning

confidence: 99%

See 2 more Smart Citations

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

et al. 2020

View full text Add to dashboard Cite

Flow routing can achieve fine-grained network performance optimizations by routing distinct packet traffic flows over different network paths. While the centralized control of Software-Defined Networking (SDN) provides a control framework for implementing centralized network optimizations, e.g., optimized flow routing, the implementation of flow routing that is adaptive to varying traffic loads requires complex models. The goal of this study is to pursue a model-free approach that is based on reinforcement learning. We design and evaluate QR-SDN, a classical tabular reinforcement learning approach that directly represents the routing paths of individual flows in its state-action space. Due to the direct representation of flow routes in the QR-SDN state-action space, QR-SDN is the first reinforcement learning SDN routing approach to enable multiple routing paths between a given source (ingress) switch-destination (egress) switch pair while preserving the flow integrity. That is, in QR-SDN, packets of a given flow take the same routing path, while different flows with the same source-destination switch pair may take different routes (in contrast, the recent DRL-TE approach splits a given flow on a per-packet basis incurring high complexity and out-of-order packets). We implemented QR-SDN in a Software-Defined Network (SDN) emulation testbed. Our evaluations demonstrate that the flow-preserving multi-path routing of QR-SDN achieves substantially lower flow latencies than prior routing approaches that determine only a single source-destination route. A limitation of QR-SDN is that the state-action space grows exponentially with the number of network nodes. Addressing the scalability of direct flow routing, e.g., through routing only high-rate flows, is an important direction for future research. The QR-SDN code is made publicly available to support this future research.

show abstract

Section: B Action-space Designmentioning

confidence: 99%

“…The values, in turn, are dictionaries with an action, see Eqs. (2) and 3, as key and the actual Q-value as value, i.e.,…”

Section: Reinforcement Learning Agent 1) Q-learningmentioning

confidence: 99%

See 1 more Smart Citation

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…As a result, the creation of TUN/TAP (Tunnel/ Test Access Point virtual network adapters slow down the program, and since the DPI system must function at least with the rate of the input flow, then the rate plays an important role. However, for software development, using WinDivert, you need to undergo a certification procedure and a digital signature for drivers [68][69][70]. Certification is performed to minimize the risk of operating system crash, since WinDivert works at a kernel level where any developer error can lead to an OS (Operating System) failure.…”

Section: Development Of Software Dpi System For Network Traffic Analymentioning

confidence: 99%

A Software Deep Packet Inspection System for Network Traffic Analysis and Anomaly Detection

Song

Beshley

Przystupa

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, to solve the problem of detecting network anomalies, a method of forming a set of informative features formalizing the normal and anomalous behavior of the system on the basis of evaluating the Hurst (H) parameter of the network traffic has been proposed. Criteria to detect and prevent various types of network anomalies using the Three Sigma Rule and Hurst parameter have been defined. A rescaled range (RS) method to evaluate the Hurst parameter has been chosen. The practical value of the proposed method is conditioned by a set of the following factors: low time spent on calculations, short time required for monitoring, the possibility of self-training, as well as the possibility of observing a wide range of traffic types. For new DPI (Deep Packet Inspection) system implementation, algorithms for analyzing and captured traffic with protocol detection and determining statistical load parameters have been developed. In addition, algorithms that are responsible for flow regulation to ensure the QoS (Quality of Services) based on the conducted static analysis of flows and the proposed method of detection of anomalies using the parameter Hurst have been developed. We compared the proposed software DPI system with the existing SolarWinds Deep Packet Inspection for the possibility of network traffic anomaly detection and prevention. The created software components of the proposed DPI system increase the efficiency of using standard intrusion detection and prevention systems by identifying and taking into account new non-standard factors and dependencies. The use of the developed system in the IoT communication infrastructure will increase the level of information security and significantly reduce the risks of its loss.

show abstract

“…The advantage of the developed traffic generator is that, unlike the known ones, it allows you to control the generated flow without the need for synchronize the input and output interfaces and to determine the packets delay of flow. It allows you to evaluate the parameters of service of hardware and software telecommunications facilities of any purpose [53][54][55][56][57][58][59].…”

Section: Performance Analysis Of the Software-based Router Using The mentioning

confidence: 99%

A Cost-Efficient Software Based Router and Traffic Generator for Simulation and Testing of IP Network

Przystupa

Beshley

et al. 2019

Electronics

Self Cite

View full text Add to dashboard Cite

The development was carried out using the Qt5.2 integrated development environment, which uses the programming language C++. The main advantage of this environment is that the code written in it can be compiled to different platforms (for example, Windows, Linux, Mac OS). A software router based on a modular architecture has been developed. It uses the socket technology, which allows forming a program-oriented packet network with any topology, including full-coupled topology. A network traffic generator to test the developed software router has been designed. We proposed a scheme to measure the packet processing time of a router using a specialized packet-capture network interface cards (NIC 1 and NIC 2) and a novel traffic generator installed on PC. Based on an experimental test bed we confirmed that our software router provides a cost-efficient alternative to the expensive, special hardware router CISCO 2801.

show abstract

Adaptive flow routing model in SDN

Cited by 40 publications

References 13 publications

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

QR-SDN: Towards Reinforcement Learning States, Actions, and Rewards for Direct Flow Routing in Software-Defined Networks

A Software Deep Packet Inspection System for Network Traffic Analysis and Anomaly Detection

A Cost-Efficient Software Based Router and Traffic Generator for Simulation and Testing of IP Network

Contact Info

Product

Resources

About