Cross-network transferable neural models for WLAN interference estimation

TL;DR

This paper develops a graph convolutional neural network approach to accurately estimate WLAN interference, demonstrating its effectiveness and generalization in real-world deployments, which can improve WLAN resource management.

Contribution

It introduces a GCN-based interference estimation model for WLANs, highlighting its superior accuracy and ability to generalize across different network deployments.

Findings

GCNs outperform other architectures in interference estimation

GCNs require node indexing for specific node behavior learning

Trained GCN models generalize well to unseen WLAN deployments

Abstract

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.