An Efficient Elephant Flow Detection with Cost-Sensitive in SDN

Xiao, Peng; Qu, Wenyu; Qi, Heng; Xu, Yujie; Li, Zhiyang

doi:10.4108/icst.iniscom.2015.258274

Cited by 52 publications

(29 citation statements)

References 17 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 7 shows the accuracy of our purposed classification for various training sizes. We observed that our EF detection method on the controller-side achieves a higher accuracy than the existing EEFD method [21] by up to 0.7%, and the classification-based EDMAR [22] by up to 0.5%.…”

Section: ) Classification Accuracymentioning

confidence: 80%

“…A real-time EF detection system was proposed in [21]. The proposed method is comprised of two stages according to the statistical thresholding of the flow stream features.…”

Section: ) Switch Based Detectionmentioning

confidence: 99%

“…By considering limitations as mentioned earlier, several improved EF detection techniques have been proposed [21]- [24]. However, these techniques are weakened by a slow convergence for several reasons, including the switch-controller interaction which requires a high bandwidth and long detection time.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Flow-Aware Elephant Flow Detection for Software-Defined Networks

et al. 2020

View full text Add to dashboard Cite

Software-defined networking (SDN) separates the network control plane from the packet forwarding plane, which provides comprehensive network-state visibility for better network management and resilience. Traffic classification, particularly for elephant flow detection, can lead to improved flow control and resource provisioning in SDN networks. Existing elephant flow detection techniques use pre-set thresholds that cannot scale with the changes in the traffic concept and distribution. This paper proposes a flow-aware elephant flow detection applied to SDN. The proposed technique employs two classifiers, each respectively on SDN switches and controller, to achieve accurate elephant flow detection efficiently. Moreover, this technique allows sharing the elephant flow classification tasks between the controller and switches. Hence, most mice flows can be filtered in the switches, thus avoiding the need to send large numbers of classification requests and signaling messages to the controller. Experimental findings reveal that the proposed technique outperforms contemporary methods in terms of the running time, accuracy, F-measure, and recall. INDEX TERMS Software-defined networking, flow classification, elephant flow detection.

show abstract

Section: ) Classification Accuracymentioning

confidence: 80%

“…A real-time EF detection system was proposed in [21]. The proposed method is comprised of two stages according to the statistical thresholding of the flow stream features.…”

Section: ) Switch Based Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Flow-Aware Elephant Flow Detection for Software-Defined Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Pouper et al [21] propose the use of neural networks, Gaussian mixture models and Gaussian process regression for the prediction of the flow size. Xiao et al [22] use C4.5 decision trees and Viljoen et al [23] are using a neural network to classify flows into mice and elephant. Chao et al [24] uses a 2-stage detection scheme with C4.5 trees as a first stage and stream mining with Hoeffding trees in the second stage.…”

Section: B Elephant Flow Detectionmentioning

confidence: 99%

Network Function Offloading Through Classification of Elephant Flows

Durner

Kellerer

2020

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

With the move from traditional hardware appliance based network functions to Network Function Virtualization, software development is decoupled from the hardware. However, as a network function is no longer optimized for hardware, beneficial features of networking hardware may not be used any more. Solutions such as SDN or NIC offloading aim to overcome this antipodes by integrating networking hardware into the packet processing pipelines. On the one hand, offloading traffic of network functions to hardware can increase throughput and reduce resource consumption. On the other hand, the number of parallel flows in a network can be very high, exhausting the capacity of the tables of the networking hardware and force the system to fall back to software processing. Fortunately, it is known that a large portion of the flows in the internet are mice flows, whereas the majority of the traffic is constituted by elephant flows. If the elephant flows can be detected efficiently, the hardware tables can be used more efficiently as a larger share of the traffic can be offloaded. We introduce a machine learning based approach that takes its decision with the first packet of a flow. A fundamentally different approach is using packet sampling for the offloading decision. We are evaluating both approaches in terms of complexity, offloaded share of the traffic and table occupation. The results show that a machine learning based offloading decision is possible with the first packet. The sampling approach only reaches a comparable performance at very high sampling rates.

show abstract

“…According to Benson et al, for interdata center communication, 80% of the flows are smaller than 10 KB in size, and most of the bytes are in the top 10% of the flows that we called elephant flows. Elephant Flow Detection and CheetahFlow both predict the elephant flows and reroute them to other paths to prevent congestion. In addition, CheetahFlow also utilizes the support vector machine (SVM) to construct frequent communication pairs and pre‐establish their flow entries into switches to decrease provisioning latency.…”

Section: Introductionmentioning

confidence: 99%

Proactive multipath routing with a predictive mechanism in software‐defined networks

Lin

Liu

Wang

et al. 2019

Int J Communication

View full text Add to dashboard Cite

With the growth of network traffic volume, link congestion cannot be avoided efficiently with conventional routing protocols. By utilizing the single shortestpath routing algorithm from link state advertisement information, standard routing protocols lack of global awareness and are difficult to be modified in a traditional network environment. Recently, software-defined network (SDN) provided innovative architecture for researchers to program their own network protocols. With SDN, we can divert heavy traffic to multiple paths in order to resolve link congestion. Furthermore, certain network traffics come in periodic fashion such as peak hours at working days so that we can leverage forecasting for resource management to improve its performance. In this paper, we propose a proactive multipath routing with a predictive mechanism (PMRP) to achieve high-performance congestion resolution. PMRP has two main concepts: (a) a proactive mechanism where PMRP deploys M/M/1 queue and traffic statistics to simulate weighted delay for possible combinations of multipaths placement of all subnet pairs, and leverage genetic algorithm for accelerating selection of optimized solution, and (b) a predictive mechanism whereby PMRP uses exponential smoothing for demand traffic volumes and variance predictions. Experimental results show a 49% reduction in average delay as compared with single shortest routing, and a 16% reduction in average delay compared with utilization & topology-aware multipath routing (UTAMP). With the predictive mechanism, PMRP can decrease an additional 20% average delay. Furthermore, PMRP reduces 93% of flow table usage on average as compared with UTAMP.links. Furthermore, periodically updating the link weights provided by link state advertisement is insensitive for network congestions. In addition to congestion resolution, there are no forecasting functions for resource management. The network pattern also has locality phenomenon such as daily rush hours so that we can leverage it for bandwidth allocation in routing mechanism. However, it is difficult to modify standard routing protocols in conventional distributed network architecture, and it is impossible to replace every individual commodity router to provide better congestion control algorithms.Recent work on software-defined network (SDN) architecture 1 separates the control plane from data plane and provides programmable Application Programming Interface (API) for provisioning and management. With a centralized controller, a global view of network topology with status can be obtained, and researchers could implement network protocols easily in the SDN environment. However, flow tables in SDN switches are limited resources, and care has to be taken with use of flow entries. If we design a routing management mechanism according to host pairs, the number of flow entries will increase dramatically and will rapidly exceed the limits of the hardware. One would consequently like to manage the flows based on subnet pairs for better flow table utilization. For exa...

show abstract

An Efficient Elephant Flow Detection with Cost-Sensitive in SDN

Cited by 52 publications

References 17 publications

Flow-Aware Elephant Flow Detection for Software-Defined Networks

Flow-Aware Elephant Flow Detection for Software-Defined Networks

Network Function Offloading Through Classification of Elephant Flows

Proactive multipath routing with a predictive mechanism in software‐defined networks

Contact Info

Product

Resources

About