Benutzer: Gast  Login
Titel:

Modeling TCP Performance Using Graph Neural Networks

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Jaeger, Benedikt; Helm, Max; Schwegmann, Lars; Carle, Georg
Abstract:
TCP throughput and RTT prediction are essential to model TCP behavior and optimize network configurations. Flows adapt their sending rate to network parameters like link capacity or buffer size and interact with parallel flows. Especially the elastic behavior of TCP congestion control can vary, even when only slight changes in the network occur. Thus, existing analytical models for TCP behavior reach their limits due to the number and complexity of different algorithms. Machine learning approach...     »
Stichworte:
congestion control, graph neural networks, throughput, round-trip time, TCP modeling
Kongress- / Buchtitel:
Proceedings of the 1st International Workshop on Graph Neural Networking
Verlag / Institution:
Association for Computing Machinery
Verlagsort:
New York, NY, USA
Jahr:
2022
Monat:
December
Seiten:
18–23
Print-ISBN:
9781450399333
Serientitel:
GNNet ’22
Volltext / DOI:
doi:10.1145/3565473.3569190
WWW:
https://doi.org/10.1145/3565473.3569190
 BibTeX