The forecasting of mobile data not only helps operators proactively perceive the network status, enabling them to arrange and schedule network resources in advance to improve user service quality, but also allows for the on-demand, flexible extrapolation of network changes under different strategies, effectively reducing the trial-and-error costs in the live network. Traditional prediction methods with tailored models for exclusive data types undoubtedly increase the design complexity and deployment costs. In this paper, we propose a Mobile Foundation Model (MobiFM) for data forecasting, which adopts a unified framework to forecast mobile data with diverse types (mobile traffic, users, and wireless channel), various time granularities (hourly and minute-level), and multiple spatial scales (cell-level and grid-level). MobiFM is a generative model built on diffusion and Transformer backbones. It incorporates a memory-network core that flexibly stores large amounts of contextual knowledge from urban environments, network configuration parameters, and spatio-temporal features. In parallel, MobiFM employs Mixture-of-Experts (MoE) networks to specialize and exploit the distinct characteristics of heterogeneous mobile data. We train the MobiFM using 10 real-world datasets with over 200,000 time-series points, totaling more than 1 billion tokens. The experimental results demonstrate that MobiFM achieves improvements of 20.24%, 10.92%, and 6.52% in the forecasting of mobile traffic, users, and wireless channel data, respectively, exhibiting good generalization performance compared to the baselines. Furthermore, based on MobiFM’s forecasting capability, we formulate an energy-saving optimization case, where the experimental results show the MobiFM-based scheme can improve energy efficiency up to 17.9%.

Mobile traffic forecasting allows operators to anticipate network dynamics and performance in advance, offering substantial potential for enhancing service quality and improving user experience. It involves multiple tasks, including long-term prediction, short-term prediction, and generation tasks that do not rely on historical data. By leveraging the different types of mobile network data generated from these tasks, operators can perform a variety of network optimizations and planning activities, such as base station (BS) deployment, resource allocation, energy optimization, etc. However, existing models are often designed for specific tasks and trained with specialized data, and there is a lack of universal models for traffic forecasting across different urban environments. In this paper, we propose a Universal model for Mobile traffic forecasting (UoMo), aiming to handle diverse forecasting tasks of short/long-term predictions and distribution generation across multiple cities to support network planning and optimization. UoMo combines diffusion models and transformers, where various spatio-temporal masks are proposed to enable UoMo to learn intrinsic features of different tasks, and a contrastive learning strategy is developed to capture the correlations between mobile traffic and urban contexts, thereby improving its transfer learning capability. Extensive evaluations on 9 real-world datasets demonstrate that UoMo outperforms current models in various forecasting tasks and zero/few-shot learning. It shows an average accuracy improvement of 27.85%, 18.57%, and 15.6% in long-term prediction, short-term prediction, and generation tasks, respectively, showcasing its strong forecasting capability. We deploy UoMo on China Mobile's JiuTian platform, leveraging the predicted mobile data to optimize live networks. This optimization includes BS deployment, resulting in a 25.3% increase in served users, and BS sleep control, which reduces equipment depreciation by 40.7%. The source code is available online: https://github.com/tsinghua-fib-lab/UoMo.

Generating mobile traffic in urban environments is important for network planning and optimization. However, existing models show weakness in capturing spatial-temporal dynamics between mobile traffic and urban environments. This makes it difficult for the models to generate high-fidelity traffic data and control the generation process across different regions in large-scale urban environments, ultimately affecting the effectiveness of optimization strategies. In this paper, we propose a Spatio-Temporal Knowledge-driven Diffusion model (STK-Diff) for controllable mobile traffic generation. We construct an Urban Knowledge Graph (UKG) to fully characterize the urban features, which incorporates both the spatial and semantic relations of different entities, such as base stations, business areas, and functional regions. Based on the constructed UKG, we design the denoising network of diffusion model with a temporal extraction module and a spatial connection module. These two modules capture the correlations of mobile traffic and environment features via a frequency attention mechanism and spatial graph learning scheme, so as to make a strong controllability on the generated mobile traffic. Extensive experiments on three real-world datasets show that the proposed framework not only improves generation fidelity by up to 19%, but also enhances the controllability to generate specific patterns, with a gain of surpassing 15%.

The fifth-generation (5G) mobile network has significantly enhanced people's lives with faster internet speed and more reliable connections. However, there is still insufficient coverage of 5G networks worldwide, requiring telecom operators to deploy more base stations to meet the increasing demand for 5G's further commercialization. In this regard, a major challenge is understanding user network behaviors and traffic demands in target areas where 5G has not yet been deployed, which is crucial for developing a more efficient base station deployment strategy. Mobile traffic generation is a potential approach that enables operators to preemptively estimate user network demands in target areas, thereby specifying corresponding deployment strategies to enhance network performance. However, existing methods have limitations in capturing spatio-temporal features of 5G mobile traffic, particularly in areas with insufficient 5G coverage and limited historical 5G traffic data. To fill this gap, we introduce a regional feature conditioned diffusion framework for 5G network traffic generation. Our models explore the relationship between 5G traffic and existing 4G traffic, utilizing a customized cross attention mechanism and graph convolutional networks (GCN) to capture the correlation between network traffic and regional features. Based on this relationship, the framework can characterize mobile network traffic demands, thereby achieving high-fidelity 5G traffic generation in target regions with insufficient 5G coverage. Extensive experiments on real-world datasets have shown that the proposed scheme outperforms state-of-the-art baselines by more than 10%, demonstrating its high-fidelity generation capability, controllability, and generalizability. Moreover, we have deployed our scheme on China Mobile's Jiutian Platform as a network traffic simulator to improve 5G base station deployment strategies.