2022
Zhiyuan Yao; Yoann Desmouceaux; Juan Antonio Cordero; Mark Townsley; Thomas Heide Clausen
Efficient Data-Driven Network Functions Proceedings Article
In: 30th International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2022), 2022.
Abstract | Links | BibTeX | Tags: Chaire Cisco, Infrastructure for Big Data, Machine Learning, Network Management
@inproceedings{nokeyg,
title = {Efficient Data-Driven Network Functions},
author = {Zhiyuan Yao and Yoann Desmouceaux and Juan Antonio Cordero and Mark Townsley and Thomas Heide Clausen},
url = {https://arxiv.org/pdf/2208.11385},
year = {2022},
date = {2022-10-18},
urldate = {2022-10-18},
booktitle = {30th International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2022)},
abstract = {Cloud environments require dynamic and adaptive networking policies. It is preferred to use heuristics over advanced learning algorithms in Virtual Network Functions (VNFs) in production becuase of high-performance constraints. This paper proposes Aquarius to passively yet efficiently gather observations and enable the use of machine learning to collect, infer, and supply accurate networking state information-without incurring additional signalling and management overhead. This paper illustrates the use of Aquarius with a traffic classifier, an autoscaling system, and a load balancer-and demonstrates the use of three different machine learning paradigms-unsupervised, supervised, and reinforcement learning, within Aquarius, for inferring network state. Testbed evaluations show that Aquarius increases network state visibility and brings notable performance gains with low overhead.},
keywords = {Chaire Cisco, Infrastructure for Big Data, Machine Learning, Network Management},
pubstate = {published},
tppubtype = {inproceedings}
}
2020
Thomas Feltin; Parisa Foroughi; Wenqin Shao; Frank Brockners; Thomas Clausen
Semantic feature selection for network telemetry event description Proceedings Article
In: NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium, pp. 1-6, 2020, ISBN: 2374-9709.
Abstract | Links | BibTeX | Tags: contextual information, cross-entropy based metric, data analysis, data behavior, data structures, Decision support, explanation, explanation process, feature selection, large-scale networks, model driven telemetry, Network Management, network telemetry event description, real-time systems, Selection process, semantic feature selection, telemetry, telemetry data structure
@inproceedings{Feltin2020,
title = {Semantic feature selection for network telemetry event description},
author = {Thomas Feltin and Parisa Foroughi and Wenqin Shao and Frank Brockners and Thomas Clausen},
url = {https://www.thomasclausen.net/wp-content/uploads/2020/08/AnNet20201-1.pdf},
doi = {10.1109/NOMS47738.2020.9110382},
isbn = {2374-9709},
year = {2020},
date = {2020-04-20},
booktitle = {NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium},
pages = {1-6},
abstract = {Model driven telemetry (MDT) enables the real-time collection of hundreds of thousands of counters on large-scale networks, with contextual information to each counter provided in the telemetry data structure definition. Explaining network events in such datasets implies substantial analysis by a domain expert. This paper presents an semantic feature selection method, to find the most important counters which describe a given event in a telemetry dataset, and facilitate the explanation process. This paper proposes a metric for estimating the importance of features in a dataset with descriptive feature names, to find those that are most meaningful to a human. With this estimation, this paper presents a cross-entropy based metric describing the quality of a selection of counters, which is combined with the data behavior to define an optimization goal. The computation of optimal selections distills intelligible and precise selections of counters with adjustable verbosity, and describes events with a few selected counters outlining the root cause of network events.},
keywords = {contextual information, cross-entropy based metric, data analysis, data behavior, data structures, Decision support, explanation, explanation process, feature selection, large-scale networks, model driven telemetry, Network Management, network telemetry event description, real-time systems, Selection process, semantic feature selection, telemetry, telemetry data structure},
pubstate = {published},
tppubtype = {inproceedings}
}
2010
Ulrich Herberg; Thomas Clausen; Robert G. Cole
MANET Network Management and Performance Monitoring for NHDP and OLSRv2 Proceedings Article
In: Proceedings of the 6th International Conference on Network and Services Management, 2010.
Abstract | Links | BibTeX | Tags: Ad-Hoc, MANET, MESH, Network Management, Network Monitoring, OLSR, OLSRv2
@inproceedings{Herberg2010,
title = {MANET Network Management and Performance Monitoring for NHDP and OLSRv2},
author = {Ulrich Herberg and Thomas Clausen and Robert G. Cole},
url = {http://www.thomasclausen.net/wp-content/uploads/2015/12/2010-CNSM-MANET-Network-Management-and-Performance-Monitoring-for-NHDP-and-OLSRv2.pdf},
doi = {10.1109/CNSM.2010.5691209},
year = {2010},
date = {2010-10-01},
publisher = {Proceedings of the 6th International Conference on Network and Services Management},
abstract = {Mobile Ad Hoc NETworks (MANETs) are gener-ally thought of as infrastructureless and largely “un-managed” network deployments, capable of accommodating highly dynamic network topologies. Yet, while the network infrastructure may be “un-managed”, monitoring the network performance and setting configuration parameters once deployed, remains important in order to ensure proper “tuning” and maintenance of a MANET. This paper describes a management framework for the MANET routing protocol OLSRv2, and its constituent protocol NHDP. It does so by presenting considerations for “what to monitor and manage” in an OLSRv2 network, and how. The approach developed is based on the Simple Network Management Protocol (SNMP), and thus this paper details the various Management Information Bases (MIBs) for router status monitoring and control – as well as a novel approach to history-based perfor-mance monitoring. While SNMP may not be optimally designed for MANETs, it is chosen due to it being the predominant protocol for IP network management – and thus, efforts are made in this paper to “adapt” the management tools within the SNMP framework for reasonable behavior also in a MANET environment.},
keywords = {Ad-Hoc, MANET, MESH, Network Management, Network Monitoring, OLSR, OLSRv2},
pubstate = {published},
tppubtype = {inproceedings}
}