Self-Refined Generative Foundation Models for Wireless Traffic Prediction

TL;DR

This paper introduces TrafficLLM, a self-refined large language model that iteratively improves wireless traffic prediction accuracy in non-stationary 6G networks using in-context learning without additional training.

Contribution

It presents a novel self-refinement framework for LLMs in wireless traffic prediction, leveraging feedback and iterative prompts to enhance prediction accuracy without parameter fine-tuning.

Findings

TrafficLLM outperforms existing LLM-based methods by 23.17% and 17.09%.

The iterative refinement process significantly improves prediction stability.

The approach effectively handles non-stationary wireless traffic distributions.

Abstract

With a broad range of emerging applications in 6G networks, wireless traffic prediction has become a critical component of network management. However, the dynamically shifting distribution of wireless traffic in non-stationary 6G networks presents significant challenges to achieving accurate and stable predictions. Motivated by recent advancements in Generative AI (GenAI)-enabled 6G networks, this paper proposes a novel self-refined Large Language Model (LLM) for wireless traffic prediction, namely TrafficLLM, through in-context learning without parameter fine-tuning or model training. The proposed TrafficLLM harnesses the powerful few-shot learning abilities of LLMs to enhance the scalability of traffic prediction in dynamically changing wireless environments. Specifically, our proposed TrafficLLM embraces an LLM to iteratively refine its predictions through a three-step process: traffic prediction, feedback generation, and prediction refinement. Initially, the proposed TrafficLLM conducts traffic predictions using task-specific demonstration prompts. Recognizing that LLMs may generate incorrect predictions on the first attempt, this paper designs feedback demonstration prompts to provide multifaceted and valuable feedback related to these initial predictions. The validation scheme is further incorporated to systematically enhance the accuracy of mathematical calculations during the feedback generation process. Following this comprehensive feedback, our proposed TrafficLLM introduces refinement demonstration prompts, enabling the same LLM to further refine its predictions and thereby enhance prediction performance. Evaluations on two realistic datasets demonstrate that the proposed TrafficLLM outperforms LLM-based in-context learning methods, achieving performance improvements of 23.17% and 17.09%, respectively.