Shiyuan Zhang

Shiyuan Zhang

Auto-generated profile, based on publicly available information

Shiyuan Zhang

Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 February 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
TLTong Li
Tong Li
QLQingyue Long
Qingyue Long
HCHaoye Chai
Haoye Chai
SZShiyuan Zhang
Shiyuan Zhang
FJFenyu Jiang
Fenyu Jiang
YLYong Li
Yong Li
The rapid advancement of mobile networks highlights the limitations of traditional network planning and optimization methods, particularly in modeling, evaluation, and application. Network Digital Twins, which simulate networks in the digital domain for evaluation, offer a solution to these challenges. This concept is further enhanced by generative AI technology, which promises more efficient and accurate AI-driven data generation for network simulation and optimization. This survey provides insights into generative AI-empowered network digital twins. We begin by outlining the architecture of a network digital twin, which encompasses both digital and physical domains. This architecture involves four key steps: data processing and network monitoring, digital replication and network simulation, designing and training network optimizers, Sim2Real, and network control. Next, we systematically discuss the related studies in each step and make a detailed taxonomy of the problem studied, the methods used, and the key designs leveraged. Each step is examined with a focus on the role of generative AI, from estimating missing data and simulating network behaviors to designing control strategies and bridging the gap between digital and physical domains. Finally, we discuss the open issues and challenges of generative AI-based network digital twins.

4 August 2023
Verified
Conference Paper
Open access
SZShiyuan Zhang
Shiyuan Zhang
TLTong Li
Tong Li
SHShuodi Hui
Shuodi Hui
GLGuangyu Li
Guangyu Li
YLYanping Liang
Yanping Liang
YLYong Li
Yong Li
The problem of cellular traffic generation in cities without historical traffic data is critical and urgently needs to be solved to assist 5G base station deployments in mobile networks. In this paper, we propose ADAPTIVE, a deep transfer learning framework for city-scale cellular traffic generation through the urban knowledge graph. ADAPTIVE leverages historical data from other cities that have deployed 5G networks to assist cities that are newly deploying 5G networks through deep transfer learning. Specifically, ADAPTIVE can align the representations of base stations in the target city and source city while considering the environmental factors of cities, spatial and environmental contextual relations between base stations, and traffic temporal patterns at base stations. We next design a feature-enhanced generative adversarial network, which is trained based on the historical traffic data and representations of base stations in the source city. By feeding the aligned target city's base station representations into the trained model, we can then obtain the generated traffic data for the target city. Extensive experiments on real-world cellular traffic datasets show that ADAPTIVE generally outperforms state-of-the-art baselines by more than 40% in terms of Jensen-Shannon divergence and root-mean-square error. Also, ADAPTIVE has strong robustness based on the results of various cross-city experiments. ADAPTIVE has been successfully deployed on the 'Jiutian' Artificial Intelligence Platform of China Mobile to support cellular traffic generation and assist in the construction and operation of mobile networks.

18 August 2024 in Proceedings of the ACM on Networking
Verified
Journal Article
Open access
SZShiyuan Zhang
Shiyuan Zhang
TLTong Li
Tong Li
DJDepeng Jin
Depeng Jin
YLYong Li
Yong Li
Network flow traces are fundamental to many network management workflows. In this paper, we aim to generate high-fidelity network flow traces by explicitly modeling users' dynamic network usage intents. We propose NetDiff, a service-guided hierarchical diffusion model for network flow trace generation. NetDiff employs a hierarchical generation structure that includes a layer to model mobile users' interactions with network services, such as app usage traces, and leverages these generated app usage traces to guide network flow generation. NetDiff avoids pattern collapse and generates controlled samples by gradually eliminating noise and using service conditions to guide each step more precisely. It captures the co-usage and sequential relationships across network service usage through a pre-trained embedding model and an encoder-decoder structure. Additionally, NetDiff captures the temporal and feature correlations present in multidimensional network flow data through a two-layer transformer network. Extensive experiments on real-world network flow datasets demonstrate that NetDiff significantly outperforms state-of-the-art baselines regarding Jensen-Shannon divergence, total variation distance, and cumulative residual probability sum squares. Furthermore, NetDiff is robust across various datasets from different cities, meeting users' requirements for downstream tasks by maintaining algorithm accuracy and order.

26 July 2024 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
TLTong Li
Tong Li
SHShuodi Hui
Shuodi Hui
SZShiyuan Zhang
Shiyuan Zhang
HWHuandong Wang
Huandong Wang
YZYuheng Zhang
Yuheng Zhang
YLYong Li
Yong Li
Mobile user traffic facilitates diverse applications, including network planning and optimization, whereas large-scale mobile user traffic is hardly available due to privacy concerns. One alternative solution is to generate mobile user traffic data for downstream applications. However, existing generation models cannot simulate the multi-scale temporal dynamics in mobile user traffic on individual and aggregate levels. In this work, we propose a multi-scale hierarchical generative adversarial network (MSH-GAN) containing multiple generators and a multi-class discriminator. Specifically, the mobile traffic usage behavior exhibits a mixture of multiple behavior patterns, which are called micro-scale behavior patterns and are modeled by different pattern generators in our model. Moreover, the traffic usage behavior of different users exhibits strong clustering characteristics, with the co-existence of users with similar and different traffic usage behaviors. Thus, we model each cluster of users as a class in the discriminator’s output, referred to as macro-scale user clusters. Then, the gap between micro-scale behavior patterns and macro-scale user clusters is bridged by introducing the switch mode generators, which describe the traffic usage behavior in switching between different patterns. All users share the pattern generators. In contrast, the switch mode generators are only shared by a specific cluster of users, which models the multi-scale hierarchical structure of the traffic usage behavior of massive users. Finally, we urge MSH-GAN to learn the multi-scale temporal dynamics via a combined loss function, including adversarial loss, clustering loss, aggregated loss, and regularity terms. Extensive experiment results demonstrate that MSH-GAN outperforms state-of-art baselines by at least 118.17% in critical data fidelity and usability metrics. Moreover, observations show that MSH-GAN can simulate traffic patterns and pattern switch behaviors.