Energy-Efficient Dynamic Training and Inference for GNN-Based Network Modeling

2025-03-24

AI Summary

Traditional queuing models and packet-level simulations suffer from low efficiency, strong assumptions, and high computational overhead in resource optimization and planning for large-scale complex networks. To address these limitations, this paper proposes a dynamic, collaborative graph neural network (GNN) training and inference framework enabling context-aware energy-efficiency modeling and real-time prediction. Our approach innovatively integrates a quantum approximate optimization (QAO)-based adaptive GNN orchestration mechanism with tripartite graph modeling and constrained graph partitioning to jointly optimize energy efficiency and application requirements. Experimental results demonstrate that, compared to optimal baselines, the proposed method reduces energy consumption by ≥50%, decreases configuration oscillation rate by 60%, while maintaining high modeling accuracy and achieving millisecond-scale inference latency.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Efficient network modeling is essential for resource optimization and network planning in next-generation large-scale complex networks. Traditional approaches, such as queuing theory-based modeling and packet-based simulators, can be inefficient due to the assumption made and the computational expense, respectively. To address these challenges, we propose an innovative energy-efficient dynamic orchestration of Graph Neural Networks (GNN) based model training and inference framework for context-aware network modeling and predictions. We have developed a low-complexity solution framework, QAG, that is a Quantum approximation optimization (QAO) algorithm for Adaptive orchestration of GNN-based network modeling. We leverage the tripartite graph model to represent a multi-application system with many compute nodes. Thereafter, we apply the constrained graph-cutting using QAO to find the feasible energy-efficient configurations of the GNN-based model and deploying them on the available compute nodes to meet the network modeling application requirements. The proposed QAG scheme closely matches the optimum and offers atleast a 50% energy saving while meeting the application requirements with 60% lower churn-rate.

Problem

• Energy-efficient dynamic training for GNN-based network modeling
• Low-complexity quantum-optimized GNN orchestration framework
• Reducing energy use while meeting network application demands

Innovation

• Energy-efficient dynamic GNN training and inference
• Quantum approximation optimization for adaptive orchestration
• Constrained graph-cutting for energy-efficient configurations