Accurate Network Traffic Matrix Prediction via LEAD: a Large Language Model-Enhanced Adapter-Based Conditional Diffusion Model

TL;DR

This paper introduces LEAD, a novel traffic matrix prediction model that leverages large language models and diffusion techniques to improve accuracy and uncertainty modeling in network traffic forecasting.

Contribution

LEAD combines a traffic-to-image transformation, a frozen LLM with adapters, and a dual-conditioning diffusion strategy for superior traffic matrix prediction.

Findings

LEAD reduces RMSE by 45.2% on Abilene dataset.

LEAD achieves 27.3% lower RMSE on GEANT dataset.

LEAD maintains low error margins even at 20-step predictions.

Abstract

Driven by the evolution toward 6G and AI-native edge intelligence, network operations increasingly require predictive and risk-aware adaptation under stringent computation and latency constraints. Network Traffic Matrix (TM), which characterizes flow volumes between nodes, is a fundamental signal for proactive traffic engineering. However, accurate TM forecasting remains challenging due to the stochastic, non-linear, and bursty nature of network dynamics. Existing discriminative models often suffer from over-smoothing and provide limited uncertainty awareness, leading to poor fidelity under extreme bursts. To address these limitations, we propose LEAD, a Large Language Model (LLM)-Enhanced Adapter-based conditional Diffusion model. First, LEAD adopts a "Traffic-to-Image" paradigm to transform traffic matrices into RGB images, enabling global dependency modeling via vision backbones. Then, we design a "Frozen LLM with Trainable Adapter" model, which efficiently captures temporal semantics with limited computational cost. Moreover, we propose a Dual-Conditioning Strategy to precisely guide a diffusion model to generate complex, dynamic network traffic matrices. Experiments on the Abilene and GEANT datasets demonstrate that LEAD outperforms all baselines. On the Abilene dataset, LEAD attains a remarkable 45.2% reduction in RMSE against the best baseline, with the error margin rising only marginally from 0.1098 at one-step to 0.1134 at 20-step predictions. Meanwhile, on the GEANT dataset, LEAD achieves a 0.0258 RMSE at 20-step prediction horizon which is 27.3% lower than the best baseline.