MobiMixer: A Multi-Scale Spatiotemporal Mixing Model for Mobile Traffic Prediction
- 8 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (11) , 11972-11986
Abstract
Understanding mobile traffic data and predicting future trends are essential for wireless operators and service providers to allocate resources efficiently and manage energy effectively. Despite the strong performance of existing models, accurately forecasting mobile traffic remains a challenge due to limited spatial and temporal modeling capabilities and high computational complexity. This paper introduces MobiMixer, a lightweight and efficient multi-scale spatiotemporal mixing model. Its core concept is to integrate multi-scale information from both spatial and temporal dimensions to improve performance on mobile traffic data. We develop a hierarchical interaction module that incorporates super nodes to enable global high-level feature interactions among nodes with common patterns. Additionally, we employ a dynamic time warping strategy to decouple mobile traffic sequences into stable and seasonal components, which are then modeled at different scales using a multi-scale temporal mixing module. We conduct extensive experiments on mobile traffic datasets collected from four international cities. Compared with 21 state-of-the-art benchmark models, MobiMixer demonstrates highly competitive performance, achieving a maximum improvement of 48.49% on the Milan mobile dataset. The model achieves an improvement in training efficiency of up to 10.69 times and reduces memory usage by 33.01%.Keywords
Funding Information
- National Natural Science Foundation of China (12227901)
- Robotic AI-Scientist Platform of Chinese Academy of Sciences through the AI-driven Experiments, Simulations and Model Training
This publication has 60 references indexed in Scilit:
- Disentangled traffic forecasting via efficient graph neural networkJournal of Physics: Conference Series, 2024
- On time demand traffic estimation based on DBN with Horse herd optimization for next generation wireless networkExpert Systems with Applications, 2024
- Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction2023
- Using support vector regression and K-nearest neighbors for short-term traffic flow prediction based on maximal information coefficientInformation Sciences, 2022
- Graph neural network for traffic forecasting: A surveyExpert Systems with Applications, 2022
- Traffic prediction forInternet of Thingsthrough support vector regression modelInternet Technology Letters, 2021
- SST-GNN: Simplified Spatio-Temporal Traffic Forecasting Model Using Graph Neural Network2021
- Hierarchical organization of urban mobility and its connection with city livabilityNature Communications, 2019
- User allocation‐aware edge cloud placement in mobile edge computingSoftware: Practice and Experience, 2019
- A multi-source dataset of urban life in the city of Milan and the Province of TrentinoScientific Data, 2015