Mobile Network Configuration Recommendation using Deep Generative Graph Neural Network
This work addresses the challenge of optimizing configurable parameters in Radio Access Telecom Networks for telecom operators, representing an incremental improvement over traditional domain-knowledge methods.
The paper tackles the problem of suboptimal mobile network configuration by proposing a Deep Generative Graph Neural Network framework that encodes the network as a graph and uses a Siamese GNN to learn embeddings, achieving improved accuracy, generalizability, and robustness against concept drift in real-world tests.
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.