Sifan Long
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sifan Long has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Fengxiao Tang
Central South University
4 shared publications - Ming Zhao
Central South University
4 shared publications - Nei Kato
Tohoku University
4 shared publications - Bomin Mao
School of Cybersecurity, Northwestern Polytechnical University, Xian, Shaanxi, China
1 shared publication Canqun Yang
1 shared publication- Jie Tang
School of Computer Science and engineering, Central South University, Changsha, China
1 shared publication
Latest Publications
- Open Access
- 29 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 1507-1522
An Ensemble Deep Reinforcement Learning-Based Asynchronous Scheduling Mechanism for 5G-TSN
Integrating Time-Sensitive Networking (TSN) with 5G enables Industrial IoT (IIoT) systems to achieve low latency and high reliability. However, deterministic cross-domain scheduling remains challenging due to strict synchronization demands and wireless channel variations. This paper proposes an asynchronous scheduling mechanism that consists of Ensemble Deep Reinforcement Learning and Online Asynchronous Flow Scheduling. The former integrates three reinforcement learning agents to generate a near-optimal Gate Control List (GCL) in complex asynchronous network environments, and the latter reallocates time-slot paths online based on the GCL to make fuller use of idle slot resources. Extensive OMNeT++ simulations show that the proposed asynchronous scheduling mechanism efficiently utilizes network resources, reduces delay from wireless fluctuations and asynchrony, and improves throughput.
- 29 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 1507-1522
Open AccessAn Ensemble Deep Reinforcement Learning-Based Asynchronous Scheduling Mechanism for 5G-TSN
Integrating Time-Sensitive Networking (TSN) with 5G enables Industrial IoT (IIoT) systems to achieve low latency and high reliability. However, deterministic cross-domain scheduling remains challenging due to strict synchronization demands and wireless channel variations. This paper proposes an asynchronous scheduling mechanism that consists of Ensemble Deep Reinforcement Learning and Online Asynchronous Flow Scheduling. The former integrates three reinforcement learning agents to generate a near-optimal Gate Control List (GCL) in complex asynchronous network environments, and the latter reallocates time-slot paths online based on the GCL to make fuller use of idle slot resources. Extensive OMNeT++ simulations show that the proposed asynchronous scheduling mechanism efficiently utilizes network resources, reduces delay from wireless fluctuations and asynchrony, and improves throughput.
- Top Cited Papers
- 7 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Surveys & Tutorials
- Vol. 27 (6) , 3915-3949
A Survey on Intelligent Network Operations and Performance Optimization Based on Large Language Models
As Large Language Models (LLMs) have achieved significant success in handling multi-modal tasks such as text, images, videos, and sounds, particularly showcasing emergent capabilities in natural language tasks, they hold great potential for network operations that similarly involve vast amounts of text data, fault data, and log files. This paper focuses on the development of LLMs, detailing their fundamental principles and application scenarios across different domains. It highlights the remarkable capabilities of LLMs in tasks such as fault diagnosis, causal inference, and intelligent question answering, and applies these abilities to the field of network operations. Moreover, the paper reviews some of the key issues and technical barriers faced by intelligent networks, such as efficiently monitoring networks in real-time and providing timely alerts when necessary. In addition to examining the utilization of LLM in network operations, this paper introduces a framework for intelligent network operations and performance optimization, leveraging LLM. The objective of this framework is to bolster network robustness and furnish users with exceptional, personalized network services. Ultimately, we conclude by delineating the challenges encountered in LLM-based intelligent network operations and performance optimization, while presenting potential solutions to overcome these hurdles and propel the comprehensive deployment of LLM-driven network intelligence.
- 7 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Surveys & Tutorials
- Vol. 27 (6) , 3915-3949
Top Cited PapersA Survey on Intelligent Network Operations and Performance Optimization Based on Large Language Models
As Large Language Models (LLMs) have achieved significant success in handling multi-modal tasks such as text, images, videos, and sounds, particularly showcasing emergent capabilities in natural language tasks, they hold great potential for network operations that similarly involve vast amounts of text data, fault data, and log files. This paper focuses on the development of LLMs, detailing their fundamental principles and application scenarios across different domains. It highlights the remarkable capabilities of LLMs in tasks such as fault diagnosis, causal inference, and intelligent question answering, and applies these abilities to the field of network operations. Moreover, the paper reviews some of the key issues and technical barriers faced by intelligent networks, such as efficiently monitoring networks in real-time and providing timely alerts when necessary. In addition to examining the utilization of LLM in network operations, this paper introduces a framework for intelligent network operations and performance optimization, leveraging LLM. The objective of this framework is to bolster network robustness and furnish users with exceptional, personalized network services. Ultimately, we conclude by delineating the challenges encountered in LLM-based intelligent network operations and performance optimization, while presenting potential solutions to overcome these hurdles and propel the comprehensive deployment of LLM-driven network intelligence.
- 18 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. PP (08908044) , 1
Utilizing Large Language Models for Advanced Optimization and Intelligent Management in Space-Air-Ground Integrated Networks
Space-Air-Ground Integrated Networks (SAGIN) present stringent and complex requirements for network design and management due to their heterogeneity, self-organizing nature, dynamic characteristics and so on. Despite extensive research on deep learning in the context of SAGIN, challenges such as inflexibility, lack of generalization, limited robustness, and insufficient scalability persist. Large language models (LLMs), with their powerful natural language processing, understanding, and generation capabilities, show significant potential in meeting the complex demands of SAGIN. We thoroughly analyze the application of LLMs in optimizing channel models, improving communication algorithms, and enhancing network management and security performance to address the unique characteristics and requirements of SAGIN. Additionally, it identifies the challenges faced during the deployment of LLMs, including computational resource constraints, data transmission limitations, model updates, real-time processing, and system integration. Corresponding solutions are proposed to ensure the efficient operation and reliability of SAGIN. Through this research, we aim to provide innovative solutions for the intelligent management of SAGIN, promoting the continuous development and application of SAGIN.
- 18 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. PP (08908044) , 1
Utilizing Large Language Models for Advanced Optimization and Intelligent Management in Space-Air-Ground Integrated Networks
Space-Air-Ground Integrated Networks (SAGIN) present stringent and complex requirements for network design and management due to their heterogeneity, self-organizing nature, dynamic characteristics and so on. Despite extensive research on deep learning in the context of SAGIN, challenges such as inflexibility, lack of generalization, limited robustness, and insufficient scalability persist. Large language models (LLMs), with their powerful natural language processing, understanding, and generation capabilities, show significant potential in meeting the complex demands of SAGIN. We thoroughly analyze the application of LLMs in optimizing channel models, improving communication algorithms, and enhancing network management and security performance to address the unique characteristics and requirements of SAGIN. Additionally, it identifies the challenges faced during the deployment of LLMs, including computational resource constraints, data transmission limitations, model updates, real-time processing, and system integration. Corresponding solutions are proposed to ensure the efficient operation and reliability of SAGIN. Through this research, we aim to provide innovative solutions for the intelligent management of SAGIN, promoting the continuous development and application of SAGIN.
- Top Cited Papers
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 39 (4) , 192-201
6G Comprehensive Intelligence: Network Operations and Optimization Based on Large Language Models
The sixth generation mobile communication standard (6G) can promote the development of Industrial Internet and Internet of Things (IoT). To achieve comprehensive intelligent development of the network and provide customers with higher quality personalized services. This paper proposes a network performance optimization and intelligent operation network architecture based on Large Language Model (LLM), aiming to build a comprehensive intelligent 6G network system. The Large Language Model, with more parameters and stronger learning ability, can more accurately capture patterns and features in data, which can achieve more accurate content output and high intelligence and provide strong support for related research such as network data security, privacy protection, and health assessment. This paper also presents the design framework of a network health assessment system based on LLM and focuses on its potential application scenarios, through the case of network health management system, it is fully demonstrated that the 6G intelligent network system based on LLM has important practical significance for the comprehensive realization of intelligence.
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 39 (4) , 192-201
Top Cited Papers6G Comprehensive Intelligence: Network Operations and Optimization Based on Large Language Models
The sixth generation mobile communication standard (6G) can promote the development of Industrial Internet and Internet of Things (IoT). To achieve comprehensive intelligent development of the network and provide customers with higher quality personalized services. This paper proposes a network performance optimization and intelligent operation network architecture based on Large Language Model (LLM), aiming to build a comprehensive intelligent 6G network system. The Large Language Model, with more parameters and stronger learning ability, can more accurately capture patterns and features in data, which can achieve more accurate content output and high intelligence and provide strong support for related research such as network data security, privacy protection, and health assessment. This paper also presents the design framework of a network health assessment system based on LLM and focuses on its potential application scenarios, through the case of network health management system, it is fully demonstrated that the 6G intelligent network system based on LLM has important practical significance for the comprehensive realization of intelligence.
- 1 September 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (9)
A highly extensible smoothed particle hydrodynamics with meshless fluid-end general interpolation method based on precise code interaction coupling environment for fluid–structure interaction surface coupling
Solving fluid–structure interaction (FSI) problems using traditional methods poses significant challenges in the field of numerical simulation. The multiphysics coupling library precise code interaction coupling environment (preCICE), renowned for its robust multiphysics coupling capabilities, offers a promising solution for FSI problems. It supports various open/closed source software and commercial computational fluid dynamics solvers in a black box manner. However, preCICE currently mainly supports coupling schemes of mesh-based methods as well as few meshless methods. This paper proposes a critical grid interpolation (CGI) method as an intermediate medium to enable the particle method to interface with preCICE. The CGI method leverages particles and critical meshes to interpolate displacement and force, thereby allowing the pure Lagrangian smoothed particle hydrodynamics (SPH) method to solve FSI problems. The critical mesh serves as a coupling interface between particles and meshes, theoretically resolving the mesh mismatch issue inherent in particle methods when connecting to preCICE. To validate the performance of the proposed CGI method, we conducted experiments where the fluid and the structure were discretized using SPH and the finite element method, respectively. The results demonstrate the effectiveness of the CGI method in solving FSI problems. Additionally, we have made our source code for the SPH fluid adapter open-source and available on (https://github.com/terrylongsifan/AdapterSPH), facilitating further development of preCICE compatibility with more meshless methods. This study significantly advances the application of SPH in FSI problems by integrating it with preCICE, thereby expanding the versatility and applicability of multiphysics simulations.
- 1 September 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (9)
A highly extensible smoothed particle hydrodynamics with meshless fluid-end general interpolation method based on precise code interaction coupling environment for fluid–structure interaction surface coupling
Solving fluid–structure interaction (FSI) problems using traditional methods poses significant challenges in the field of numerical simulation. The multiphysics coupling library precise code interaction coupling environment (preCICE), renowned for its robust multiphysics coupling capabilities, offers a promising solution for FSI problems. It supports various open/closed source software and commercial computational fluid dynamics solvers in a black box manner. However, preCICE currently mainly supports coupling schemes of mesh-based methods as well as few meshless methods. This paper proposes a critical grid interpolation (CGI) method as an intermediate medium to enable the particle method to interface with preCICE. The CGI method leverages particles and critical meshes to interpolate displacement and force, thereby allowing the pure Lagrangian smoothed particle hydrodynamics (SPH) method to solve FSI problems. The critical mesh serves as a coupling interface between particles and meshes, theoretically resolving the mesh mismatch issue inherent in particle methods when connecting to preCICE. To validate the performance of the proposed CGI method, we conducted experiments where the fluid and the structure were discretized using SPH and the finite element method, respectively. The results demonstrate the effectiveness of the CGI method in solving FSI problems. Additionally, we have made our source code for the SPH fluid adapter open-source and available on (https://github.com/terrylongsifan/AdapterSPH), facilitating further development of preCICE compatibility with more meshless methods. This study significantly advances the application of SPH in FSI problems by integrating it with preCICE, thereby expanding the versatility and applicability of multiphysics simulations.