Progressive Supervision via Label Decomposition: An Long-Term and Large-Scale Wireless Traffic Forecasting Method

TL;DR

This paper introduces PSLD, a novel method for long-term large-scale wireless traffic forecasting that employs label decomposition and subgraph sampling to improve prediction accuracy on city-scale datasets.

Contribution

The paper proposes PSLD, a progressive supervision approach with label decomposition and subgraph sampling, advancing long-term large-scale wireless traffic forecasting methods.

Findings

PSLD outperforms state-of-the-art methods with 2-11% accuracy improvements.

Introduces a scalable subgraph sampling algorithm for large datasets.

Provides an open-source benchmarking library for wireless traffic forecasting.

Abstract

Long-term and Large-scale Wireless Traffic Forecasting (LL-WTF) is pivotal for strategic network management and comprehensive planning on a macro scale. However, LL-WTF poses greater challenges than short-term ones due to the pronounced non-stationarity of extended wireless traffic and the vast number of nodes distributed at the city scale. To cope with this, we propose a Progressive Supervision method based on Label Decomposition (PSLD). Specifically, we first introduce a Random Subgraph Sampling (RSS) algorithm designed to sample a tractable subset from large-scale traffic data, thereby enabling efficient network training. Then, PSLD employs label decomposition to obtain multiple easy-to-learn components, which are learned progressively at shallow layers and combined at deep layers to effectively cope with the non-stationary problem raised by LL-WTF tasks. Finally, we compare the proposed method with various state-of-the-art (SOTA) methods on three large-scale WT datasets. Extensive experimental results demonstrate that the proposed PSLD significantly outperforms existing methods, with an average 2%, 4%, and 11% performance improvement on three WT datasets, respectively. In addition, we built an open source library for WT forecasting (WTFlib) to facilitate related research, which contains numerous SOTA methods and provides a strong benchmark.Experiments can be reproduced through https://github.com/Anoise/WTFlib.