On precision and scalability of elephant flow detection in data center with SDN

Bi, Conghui; Luo, Xuan; Ye, Tong; Jin, Yaohui

doi:10.1109/glocomw.2013.6825161

Cited by 12 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there is no unanimous settlement among the proposed flow classification approaches on what flow feature to adopt. However, the majority of the approaches used flow size [79], [84][85][86][87]. To set up the classification threshold, many other techniques used duration [88], rate [89][90][91], or burst as well.…”

Section: Flow Characteristicsmentioning

confidence: 99%

“…As a result, rather than being systematic, threshold selection in existing studies appears ad hoc. A study in [79] suggests that the preconfigured fixed threshold parameter for EF detection incurred high detection error rates because of its ability to adapt dynamically in real-time to constant traffic variability in a contemporary network. The tendency to report false positive and false negative errors is significant.…”

Section: Threshold Value Determination Challengementioning

confidence: 99%

“…Popular sampling method such as sFlow [35] has been incor-porated by several (EFDM). It is scalable and adaptable to traffic heterogeneity in DCN [79], as several switches can be monitored efficiently by the sFlow protocol. In contrast, polling techniques deal with every flow entry in the flow table.…”

Section: Flow Identification Overhead and Accuracy Challengementioning

confidence: 99%

See 2 more Smart Citations

Review of Path Selection Algorithms with Link Quality and Critical Switch Aware for Heterogeneous Traffic in SDN

Yusuf

Bakar

Isyaku

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Software Defined Networking (SDN) introduced network management flexibility that eludes traditional network architecture. Nevertheless, the pervasive demand for various cloud computing services with different levels of Quality of Service requirements in our contemporary world made network service provisioning challenging. One of these challenges is path selection (PS) for routing heterogeneous traffic with end-to-end quality of service support specific to each traffic class. The challenge had gotten the research community's attention to the extent that many PSAs were proposed. However, a gap still exists that calls for further study. This paper reviews the existing PSA and the Baseline Shortest Path Algorithms (BSPA) upon which many relevant PSA(s) are built to help identify these gaps. The paper categorizes the PSAs into four, based on their path selection criteria, (1) PSAs that use static or dynamic link quality to guide PSD, (2) PSAs that consider the criticality of switch in terms of an update operation, FlowTable limitation or port capacity to guide PSD, (3) PSAs that consider flow variabilities to guide PSD and (4) The PSAs that use ML optimization in their PSD. We then reviewed and compared the techniques' design in each category against the identified SDN PSA design objectives, solution approach, BSPA, and validation approaches. Finally, the paper recommends directions for further research.

show abstract

Section: Flow Characteristicsmentioning

confidence: 99%

Section: Threshold Value Determination Challengementioning

confidence: 99%

See 1 more Smart Citation

Review of Path Selection Algorithms with Link Quality and Critical Switch Aware for Heterogeneous Traffic in SDN

Yusuf

Bakar

Isyaku

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…The sampling method is a universal approach to collect traffic information. However, for long flow detection, the existing solution often does not meet the requirements of long flow detection accuracy and suffers from feasibility issues [25]. FlowMon fisrt captured the suspicious long flow through coarse-grained sampling method optimized the TCAM resource allocation [26].…”

Section: Samplingmentioning

confidence: 99%

Sonum: Software-Defined Synergetic Sampling Approach and Optimal Network Utilization Mechanism for Long Flow in a Data Center Network

Tan

Cheng

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Long flow detection and load balancing are crucial techniques for data center running and management. However, both of them have been independently studied in previous studies. In this paper, we propose a complete solution called Sonum, which can complete long flow detection and scheduling at the same time. Sonum consists of a software-defined synergetic sampling approach and an optimal network utilization mechanism. Sonum detects long flows through consolidating and processing sampling information from multiple switches. Compared with the existing prime solution, the missed detection rate of Sonum is reduced by 2.3%–5.1%. After obtaining the long flow information, Sonum minimizes the potential packet loss rate as the optimization target and then translates load balancing into an optimization problem of arranging a minimum packet loss path for long flows. This paper also introduces a heuristic algorithm for solving this optimization problem. The experimental results show that Sonum outperforms ECMP and Hedera in terms of network throughput and flow completion time.

show abstract

“…A large number of mice flows come and go too fast to wait the flow entries installation according to controller's policy. Therefore, differentiating elephant and mice flow is critical to make the optimized routing policy for various types of traffic flows [7]. In addition, [4,6] can be applied only for UDP traffic flows.…”

Section: Introductionmentioning

confidence: 99%

Traffic management with elephant flow detection in software defined networks (SDN)

Zaw

Maw

2019

IJECE

View full text Add to dashboard Cite

Multipath routing is to distribute the incoming traffic load among available paths between source and destination hosts. Instead of using the single best path, multipath scheme can avoid the congested path. Equal Cost Multi-Path (ECMP) performs the static traffic splitting based on some tuples of the packet headers. The limitation of ECMP does not consider the network parameters such as bandwidth and delay. Unlike the traditional networks, Software-Defined Network (SDN) has many advantages to support dynamic multipath forwarding due to its special characteristics, such as separation of control and data planes, global centralized control, and programmability of network behavior. In this paper, we propose a new architecture design for dynamic multipath-based traffic management approach in the SDN, which comprises of five components: detecting long (elephant) flow, computing shortest paths, estimating end-to-end delay and bandwidth utilization, calculating least cost path and rerouting traffic flow from the ongoing path to the best path. The simulation environment is created through the usage of Mininet emulator and ONOS controller. The evaluation outcomes show that the proposed traffic management method outperforms the ECMP and reactive forwarding method for both TCP and UDP traffic.

show abstract

On precision and scalability of elephant flow detection in data center with SDN

Cited by 12 publications

References 17 publications

Review of Path Selection Algorithms with Link Quality and Critical Switch Aware for Heterogeneous Traffic in SDN

Review of Path Selection Algorithms with Link Quality and Critical Switch Aware for Heterogeneous Traffic in SDN

Sonum: Software-Defined Synergetic Sampling Approach and Optimal Network Utilization Mechanism for Long Flow in a Data Center Network

Traffic management with elephant flow detection in software defined networks (SDN)

Contact Info

Product

Resources

About