Mobile Network Configuration Recommendation using Deep Generative Graph Neural Network

TL;DR

This paper introduces a deep generative graph neural network framework that encodes telecom networks as graphs to recommend optimal configuration parameters and detect misconfigurations, outperforming traditional domain knowledge-based methods.

Contribution

It presents a novel GNN-based framework for network configuration recommendation that handles network expansion and reconfiguration, improving accuracy and robustness.

Findings

Outperforms baseline methods in real-world tests

Demonstrates high accuracy and generalizability

Robust against concept drift in network data

Abstract

There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift.