A Comparison of Performance and Accuracy of Measurement Algorithms in Software

Alipourfard, Omid; Moshref, Masoud; Zhou, Yang; Yang, Tong; Yu, Minlan

doi:10.1145/3185467.3185475

Cited by 23 publications

(23 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process of initializing the online ML algorithms is usually referred to as "bootstrapping". To bootstrap an online ML model we always used the first 2 The code used for our experiments can be found at https://github.com/ yuvalnezri/CardEst. batch of packets as a training batch.…”

Section: Implementation Detailsmentioning

confidence: 99%

Cardinality Estimation in a Virtualized Network Device Using Online Machine Learning

Cohen

Nezri

2019

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

Cardinality estimation algorithms receive a stream of elements, with possible repetitions, and return the number of distinct elements in the stream. Such algorithms seek to minimize the required memory and CPU resource consumption at the price of inaccuracy in their output. In computer networks, cardinality estimation algorithms are mainly used for counting the number of distinct flows, and they are divided into two categories: sketching algorithms and sampling algorithms. Sketching algorithms require the processing of all packets, and they are therefore usually implemented by dedicated hardware. Sampling algorithms do not require processing of all packets, but they are known for their inaccuracy. In this work we identify one of the major drawbacks of sampling-based cardinality estimation algorithms: their inability to adapt to changes in flow size distribution. To address this problem, we propose a new sampling-based adaptive cardinality estimation framework, which uses online machine learning. We evaluate our framework using real traffic traces, and show significantly better accuracy compared to the best known sampling-based algorithms, for the same fraction of processed packets.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

Cardinality Estimation in a Virtualized Network Device Using Online Machine Learning

Cohen

Nezri

2019

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

show abstract

“…Sampling in the case of heavy-tailed processing time distributions proves to be difficult due to the rarity of events with high impact. In order to overcome limitations regarding performance and accuracy, more sophisticated measurement algorithms and data structures need to be revisited [14].…”

Section: Characterizationmentioning

confidence: 99%

KOMon — Kernel-based Online Monitoring of VNF Packet Processing Times

Geissler

Lange

Wamser

et al. 2019

2019 International Conference on Networked Systems (NetSys)

View full text Add to dashboard Cite

The ongoing softwarization of networks comes with several advantages like cost efficiency, increased scalability, and better flexibility by migrating functionality from static, application specific hardware appliances to flexible, lightweight software solutions running on COTS hardware. In order to maximize the performance gains promised by the NFV paradigm, several challenges remain to be solved. In this work, we address the accurate acquisition of key performance indicators, specifically the packet processing time, of softwarized network functions. To this end, we present KOMon, a Kernel-based online monitoring tool to reliably measure the packet processing times of network functions through lightweight in-stack monitoring. We show that KOMon reports highly accurate values in different scenarios and discuss the applicability of the proposed mechanism for different use cases.

show abstract

“…PayLess [14] is an adaptive SDN monitoring algorithm which adapts the frequency of collecting statistics to control the monitoring overhead. More generally, the question of such a trade-off is studied in [15], where the authors argue that considering the amount of system resources of modern servers, packet processing performance (e.g., throughput and latency) becomes a key challenge in the process of software networks measurement.…”

Section: Related Workmentioning

confidence: 99%

Tuning optimal traffic measurement parameters in virtual networks with machine learning

Gogunska¹,

Barakat²,

Urvoy-Keller

2019

2019 IEEE 8th International Conference on Cloud Networking (CloudNet)

View full text Add to dashboard Cite

With the increasing popularity of cloud networking and the widespread usage of virtualization as a way to offer flexible and virtual network and computing resources, it becomes more and more complex to monitor this new virtual environment. Yet, monitoring remains crucial for network troubleshooting and analysis. Controlling the measurement footprint in the virtual network is one of the main priorities in the process of monitoring as resources are shared between the compute nodes of tenants and the measurement process itself. In this paper, first, we assess the capability of machine learning to predict measurement impact on the ongoing traffic between virtual machines; second, we propose a data-driven solution that is able to provide optimal monitoring parameters for virtual network measurement with minimum traffic interference.

show abstract

A Comparison of Performance and Accuracy of Measurement Algorithms in Software

Cited by 23 publications

References 41 publications

Cardinality Estimation in a Virtualized Network Device Using Online Machine Learning

Cardinality Estimation in a Virtualized Network Device Using Online Machine Learning

KOMon — Kernel-based Online Monitoring of VNF Packet Processing Times

Tuning optimal traffic measurement parameters in virtual networks with machine learning

Contact Info

Product

Resources

About