- General Chairs:
- Massimo Cafaro,
- Jinoh Kim,
- Alex Sim
The 3rd International Workshop on Systems and Network Telemetry and Analytics (SNTA 2020), a full-day meeting at the HPDC 2020 conference in Stockholm, Sweden, aims at bridging the systems and network telemetry and the latest advances in machine learning and data science technologies, to advance the performance and reliability of HPC and distributed systems.
The tasks of systems and network telemetry are a key element for effective operations and management of HPC and distributed computing systems, by offering comprehensive monitoring and analysis capabilities to provide the visibility into what is occurring at any time. The tasks will be significantly complicated with the greater complexity of computing systems, increasing network speed, and the newly introduced mobile and IoT devices. Such changes will render the existing telemetry and analysis techniques outdated, and more scalable techniques may be in place for data-driven and deeper data analysis. In addition to the quantitative and qualitative challenges, data pressure in systems and networks also comes from various sources such as end systems, routers, firewalls, intrusion sensors, and the newly emerging network elements speaking with different syntax and semantics, which makes organizing and incorporating the generated data difficult for extensive analysis. This workshop aims at bridging the systems and network telemetry and the latest advances in machine learning and data science technologies, to advance the performance and reliability of HPC and distributed systems, and sharing visions of investigating new approaches and methods at the intersection of HPC systems and data sciences from the diverse angles of systems/network performance, availability, and security.
Proceeding Downloads
Analytics-Driven Networking: When the Computer becomes the Network
As the era of 'human-managed networking' passes to 'analytics-driven networking', more and more data about networks, including the constituent flows, is being tracked and retrieved. With networks now needing to be an effective sensor, new methods are ...
KDetect: Unsupervised Anomaly Detection for Cloud Systems Based on Time Series Clustering
To improve the user experience in Cloud systems, it is of major interest for Cloud management tools to be able to automatically detect and notify anomalies in the behavior of services executed in virtual machines in a non-intrusive manner. To this end, ...
Data-driven Learning to Predict WAN Network Traffic
In this paper, we explore both statistical and deep learning approaches for multi-step predictions in WAN traffic traces. Estimating future traffic can help improve link usage and optimize bandwidth utilization. In this paper, we study real network ...
Feature Selection Improves Tree-based Classification for Wireless Intrusion Detection
With the growth of 5G wireless technologies and IoT, it become urgent to develop robust network security systems, such as intrusions detection systems (IDS) to keep the networks secure. These IDS systems need to detect unauthorized access and attacks in ...
Using Machine Learning for Intent-based provisioning in High-Speed Science Networks
Smart and rapid provisioning of network resources that are easy to configure, monitor, and maintain is essential for high-speed network infrastructures. There is a need to allow users to interface directly with networks to easily navigate their use-...
2020 Vision for Web Privacy
Privacy is getting eroded as more surveillance is happening. The history of web privacy will be discussed along with a vision for the future. This talk will discuss how web users are tracked, what can be done about it, the impact of web surveillance on ...
HPC Workload Characterization Using Feature Selection and Clustering
Large high-performance computers (HPC) are expensive tools responsible for supporting thousands of scientific applications. However, it is not easy to determine the best set of configurations for workloads to best utilize the storage and I/O systems. ...
Transfer Learning Approach for Botnet Detection Based on Recurrent Variational Autoencoder
Machine Learning (ML) methods have been widely used in Intrusion Detection Systems (IDS). In particular, many botnet detection methods are based on ML. However, due to the fast-evolving nature of network security threats, it is necessary to frequently ...
Finding the Optimal Reconfiguration for Network Function Virtualization Orchestration with Time-varied Workload
Network Function Virtualization (NFV) replaces proprietary network appliances by softwarizing them in commodity servers and they are called as Virtual Network Functions(VNFs). As the network traffic changes dynamically, it is challenging to find the ...
Evaluation of Deep Learning Models for Network Performance Prediction for Scientific Facilities
Large data transfers are getting more critical with the increasing volume of data in scientific computing. While scientific facilities manage dedicated infrastructures to support large data transfers, predicting network performance based on the ...
Index Terms
- Proceedings of the 3rd International Workshop on Systems and Network Telemetry and Analytics
Recommendations
Acceptance Rates
| Year | Submitted | Accepted | Rate |
|---|---|---|---|
| SNTA '19 | 106 | 22 | 21% |
| Overall | 106 | 22 | 21% |