DeePCCI: Deep Learning-based Passive Congestion Control Identification
This addresses the challenge for network researchers and operators in studying congestion control usage, especially with modern encrypted protocols, though it is incremental as it applies existing deep learning to a specific domain problem.
The paper tackles the problem of identifying which congestion control variant is used in transport protocols, which is hard with existing passive methods requiring domain knowledge and outdated assumptions. It presents DeePCCI, a deep learning-based approach that uses only packet arrival data and training traffic, achieving applicability to encrypted traffic like QUIC without domain knowledge.
Transport protocols use congestion control to avoid overloading a network. Nowadays, different congestion control variants exist that influence performance. Studying their use is thus relevant, but it is hard to identify which variant is used. While passive identification approaches exist, these require detailed domain knowledge and often also rely on outdated assumptions about how congestion control operates and what data is accessible. We present DeePCCI, a passive, deep learning-based congestion control identification approach which does not need any domain knowledge other than training traffic of a congestion control variant. By only using packet arrival data, it is also directly applicable to encrypted (transport header) traffic. DeePCCI is therefore more easily extendable and can also be used with QUIC.