TY - GEN

T1 - Predicting Latency Quantiles using Network Calculus-assisted GNNs

AU - Helm, Max

AU - Carle, Georg

N1 - Publisher Copyright:
© 2023 ACM.

PY - 2023/12/8

Y1 - 2023/12/8

N2 - Network digital twins commonly rely on Graph Neural Networks (GNNs) as functional models. They typically predict network performance metrics, such as latencies. Most approaches have one of the following restrictions: they use simulated data, predict mean values, or don't utilize formal method results as inputs. We introduce an approach that: (I) relies on data obtained from a hardware testbed, increasing realism, (II) predicts quantiles in addition to means, increasing flexibility and applicability, (III) uses the formal method of network calculus to obtain input features, increasing prediction accuracy. We show that latencies in hardware testbeds can be predicted at different quantiles with median relative errors between 8% and 29% using a simple GNN architecture. Furthermore, we show that network calculus bounds are especially useful for predicting higher quantiles and that they mostly correct large prediction errors.

AB - Network digital twins commonly rely on Graph Neural Networks (GNNs) as functional models. They typically predict network performance metrics, such as latencies. Most approaches have one of the following restrictions: they use simulated data, predict mean values, or don't utilize formal method results as inputs. We introduce an approach that: (I) relies on data obtained from a hardware testbed, increasing realism, (II) predicts quantiles in addition to means, increasing flexibility and applicability, (III) uses the formal method of network calculus to obtain input features, increasing prediction accuracy. We show that latencies in hardware testbeds can be predicted at different quantiles with median relative errors between 8% and 29% using a simple GNN architecture. Furthermore, we show that network calculus bounds are especially useful for predicting higher quantiles and that they mostly correct large prediction errors.

KW - delay model

KW - graph neural network

KW - hardware measurement

KW - latency model

KW - network calculus

UR - http://www.scopus.com/inward/record.url?scp=85180413928&partnerID=8YFLogxK

U2 - 10.1145/3630049.3630173

DO - 10.1145/3630049.3630173

M3 - Conference contribution

AN - SCOPUS:85180413928

T3 - GNNet 2023 - Proceedings of the 2nd Graph Neural Networking Workshop 2023

SP - 13

EP - 18

BT - GNNet 2023 - Proceedings of the 2nd Graph Neural Networking Workshop 2023

PB - Association for Computing Machinery, Inc

T2 - 2nd Graph Neural Networking Workshop, GNNet 2023

Y2 - 8 December 2023

ER -