Non-intrusive QoE prediction in WLAN

Jimenez-Padilla, M. L.; Romero-Hierro, P.; Aguayo-Torres, Mari Carmen; Cárdenas, César; Banos-Polglase, J.

doi:10.1109/wimob.2017.8115753

Cited by 1 publication

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4.2.3 the advantages of adding kernel 𝑇 3 . We use a GCN with 4 graph convolution layers, each having 100 units, that is, 𝑑 (1) , 𝑑 (2) , 𝑑 (3) , 𝑑 (4) = 100, 𝑑 (5) = 1 and 𝑑 (0) = 1 or 1 + 𝑛, depending if node IDs are used. Using multiple convolutions allows to use distant neighbor information as well as to learn representations that capture structural equivalence between different nodes.…”

Section: Graph Convolutional Modelmentioning

confidence: 99%

See 1 more Smart Citation

Cross-network transferable neural models for WLAN interference estimation

Fernandes¹,

Krolikowski²,

Houidi³

et al. 2022

Proceedings of the 1st International Workshop on Graph Neural Networking

View full text Add to dashboard Cite

Airtime interference is a key performance indicator for WLANs, measuring, for a given time period, the percentage of time during which a node is forced to wait for other transmissions before to transmitting or receiving. Being able to accurately estimate interference resulting from a given state change (e.g., channel, bandwidth, power) would allow a better control of WLAN resources, assessing the impact of a given configuration before actually implementing it.In this paper, we adopt a principled approach to interference estimation in WLANs. We first use real data to characterize the factors that impact it, and derive a set of relevant synthetic workloads for a controlled comparison of various deep learning architectures in terms of accuracy, generalization and robustness to outlier data. We find, unsurprisingly, that Graph Convolutional Networks (GCNs) yield the best performance overall, leveraging the graph structure inherent to campus WLANs. We notice that, unlike e.g. LSTMs, they struggle to learn the behavior of specific nodes, unless given the node indexes in addition. We finally verify GCN model generalization capabilities, by applying trained models on operational deployments unseen at training time.

show abstract

Section: Graph Convolutional Modelmentioning

confidence: 99%

“…The authors of [12] predict physical WLAN interference based on fine-grained packet-level data. Similarly, authors of [4] aim at predicting WLAN QoE metrics from WLAN frames. Such approach is not suitable for what-if scenarios that we are aiming for.…”

Section: Related Workmentioning

confidence: 99%