@article{M385ECE2F,
title = "Total Link Service Rate Estimation with Packet Metadata",
journal = "The Journal of Korean Institute of Communications and Information Sciences",
year = "2024",
issn = "1226-4717",
doi = "10.7840/kics.2024.49.6.829",
author = "Jinoo Joung, Juhyeok Kwon",
keywords = "end-to-end latency, deterministic networking, flow states, TSN, finish time",
abstract = "Guaranteeing end-to-end network latency bounds is required in many applications. A necessary condition for ensuring end-to-end latency is to keep the total service rate for flows on each link lower than the maximum link capacity. To ensure this, before data transmission for each flow, through an admission control process, it is necessary to check whether the total service rate remains within the capacity in each link through which the flow passes. In this process, all nodes must maintain information such as the service rate of individual flows in order to respond to missing protocol signals or node failures. This flow-specific information is collectively referred to as “flow state.” However, as the number of flows increases, the complexity of managing state information increases. Therefore, it is needed a method to infer the total service rate of the link without flow state maintenance. This study proposes a method to accurately infer the total service rate of a link using only packet metadata so that admission control can be performed without state maintenance for each flow at the core node. By specifying the time of inference, the exact service rate can be inferred at the correct time. Its effectiveness is proven through simulation."
}