With the widespread deployment of 5G networks, efficient network optimization and planning have become increasingly important. The generation of mobile traffic and user data can help network operators understand and grasp the network’s operational status from different perspectives, enabling customized strategies such as wireless resource allocation and user access control. However, existing research primarily focuses on the generation of single-type data and lacks exploration of the interplay between mobile traffic and user data. Moreover, current generative models struggle to capture the spatio-temporal correlations between multimodal environmental data and mobile data. In this paper, we propose a Multimodal Context-aware Diffusion Model (MCDiff) for simultaneously generating mobile traffic and users. The model incorporates an interplay perception module to capture the correlation between mobile traffic and users. To better characterize the complex and dynamic features of urban environments, we innovatively propose extracting both spatial and temporal variations from multimodal contextual data and employing contrastive learning to align multimodal contextual features with mobile data. Extensive experiments on two real-world datasets demonstrate that MCDiff can accurately generate both mobile traffic and users, achieving up to a 23.11% improvement in fidelity metrics. Facilitated by our multimodal contextual fusion module, MCDiff exhibits strong controllable and generalization capabilities, with a minimal transfer gap of only 1.19%. Furthermore, by leveraging the generated mobile traffic and user data, we formulate network planning and optimization strategies. Experimental results highlight the superiority and practicality of our method.

Mobile traffic generation helps analysts predict network performance and synthesize high-fidelity traffic data based on environmental factors, supporting optimization and planning in 5G networks, such as base station sleep management and digital twins. However, existing methods mainly explore spatio-temporal (ST) relationships implicitly and lack explicit modeling of regional features. In this paper, we introduce a Regional Features Enhanced Diffusion Model (Re-Diff) to explicitly models regional features for accurate mobile traffic generation. We integrate an average mobile traffic predictor into the diffusion model’s denoising network. By using POI and AOI distributions, we establish relationships between the environment and average network traffic usage, thereby explicitly representing regional features. We then utilize a cross-attention mechanism to actively explore the dependencies at different scales between mobile traffic’s periodic characteristics and regional features, further improving the generation accuracy of mobile traffic. We validate Re-Diff on two real-world datasets, showing a 9.20% improvement in generation accuracy over current baselines. More importantly, the model’s transferability across different cities improves by over 14.57%, which highlights the importance of explicitly modeling the relationship between traffic and the environment. This capability helps understand the universal correlations between POI, AOI, and mobile traffic in different regions, enhancing the model’s generalizability. Our code is now available at https://github.com/tsinghua-fib-lab/Re-Diff.

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.

In large-scale Internet of Things (IoT) networks, generating high-fidelity packet trace data (e.g., packet size, packet time interval) is crucial for developing more powerful and precise network analysis tools. The packet data facilitates improved monitoring, threat detection, and the design of tailored resource allocation strategies to enhance user experiences. However, due to the inherent variability of IoT services and the complex temporal dependencies between network packets, producing detailed packet trace data for multiple services remains a challenging task. In this paper, we propose PacketDiff, a novel diffusion model that generates network packet trace data for diverse services based on statistical network data (i.e., network flow data). We first design an IP graph to characterize and learn the preference relationships between different IoT devices in terms of service usage. Afterward, a classifier-free guidance denoising network that integrates network flow information is designed with dual-layer transformer architectures to enhance the controllability of the generation process. Unlike traditional methods, which often rely on the simple replication of statistical patterns within IoT traffic data and fail to account for the dynamic and varied nature of IoT networks, our approach offers a more robust and accurate solution. Extensive experiments conducted on two real-world IoT datasets demonstrate that PacketDiff closely approximates real network packet data, particularly concerning key characteristics such as average packet size and time interval, with improvements of 43.4% and 39.02%.