Computing, as the cornerstone of information processing, plays a crucial role in the digital service era. The “network” and “computing” are traditionally used for information transmission and processing, respectively, belonging to different stakeholders and evolving independently. Recently, the trend of collaboration and convergence between networks and computing has gained widespread attention from both industry and academia. Accordingly, concepts such as “computing power network” and “computing network” have been proposed, and the International Telecommunication Union (ITU-T) has initiated the standardization work on the coordination of networking and computing (CNC), focusing particularly on architecture and framework design. The collaboration between networking and computing will bring several direct benefits:
1. Effective resource scheduling across wide areas, achieving energy savings. The national project “Eastern Data Western Computing” initiated in China in 2022 serves as an example, aiming to guide the industry to process and store data in the energy-rich western regions of China, efficiently utilizing energy, especially renewable energy.
2. Promoting computing power as a public infrastructure service. This vision was proposed by artificial intelligence pioneer John McCarthy in the 1960s, aiming to make computing power as easily accessible as household water and electricity, bridging the gap in the availability of computing resources. Academician Sun Ninghui and his team named this capability “computility”, which refers to ubiquitous information processing capabilities provided based on the network.
3. Significantly enhancing user experience. For example, immersive communication is characterized by high traffic, low latency, frequent interactions, and high computational complexity. The quality of service assessment must consider both data transmission and processing simultaneously. The synergy between connectivity and computing can achieve an optimized balance, such as selecting appropriate computing nodes and network transmission paths.
Against this backdrop, the journal “Frontiers of Information Technology & Electronic Engineering” has organized this special issue on “Computing and Networking Convergence: Architecture, Theory, and Practice”. This special issue includes six articles—one perspective, one review, and four research papers. It can be seen as a re-exploration of the long-standing classic issue of designing systems as a network-connected supercomputer. Achieving end-to-end service optimization through collaborative management of computing resources across terminals, edge clouds, and central clouds is crucial. The core idea is to “exchange computation for transmission”, reducing data processing latency through enhanced computing power, thereby easing the stringent requirements for ultra-low latency during network transmission. Through systematic collaboration and integration, the synergy between network and computing capabilities can be amplified. To achieve these advantages, three important issues need to be addressed:
1. Identifying the demands and resources of networks and computing power, recognizing the required computing power and network transmission capabilities for applications.. Understanding how to identify and model these demands is crucial, especially for heterogeneous and distributed computing resources. The challenge lies in ensuring effective allocation of raw data or processing logic to utilize available computing resources.
2. Timely and joint perception of computing power and network resources, collecting load information related to networks or computing power. Computing power metrics are usually obtained from computing infrastructure components such as cloud services, virtual machines, or containers using different monitoring methods. In contrast, network connectivity metrics typically rely on measurements of end-to-end data path transmission.
3. Collaborative scheduling of computing and network resources requires systematic optimization. Promoting cooperation between terminal devices, edge computing, and cloud services involves establishing a unified “brain” for the network, enabling resource providers within this networked “distributed computing system” to collaboratively address the challenges of multidimensional resource scheduling.
In addition to the above core aspects, the implementation of these systems also involves tasks such as application task decomposition. Furthermore, it is crucial to assess whether network and computing resources can collaborate throughout the entire lifecycle of information processing—covering generation, transmission, processing, and consumption. In the context of digital transformation, the collaboration between networking and computing signifies a promising new research field with many challenges yet to be discovered and addressed.
The architectural design of systems is key to realizing these new functionalities. Wang Xiaoyun and others proposed the concept of Computing-Aware Networks (CAN), which is a new framework integrating a perception plane that promotes wide-area collaboration between computing and networks. This framework identifies three key technologies: Computing-Aware Routing (CATS), Elastic Broadcasting, and Wide-Area High-Throughput Transmission. Although further research is needed to incorporate computing into routing strategies, the Internet Engineering Task Force (IETF) has initiated discussions on computing-aware routing to explore potential scenarios and architectural designs. Elastic Broadcasting is custom-designed for “one-to-many” communications in wide-area networks, which is crucial for cross-data-center AI model training and inference. Although high-throughput transmission is not a new concept, the physical latency caused by long distances, data packet loss, and server limitations pose significant challenges to its application in wide-area networks.
Due to the environmental and cost impacts of high-power computing, energy efficiency is critical. In recent years, federated learning, which has gained attention in the industry, requires energy-saving approaches, especially in edge computing environments. Yan Kang and others conducted a comprehensive survey on energy-saving strategies in edge federated learning, including system and energy consumption models. They explored three categories of strategies: learning-based strategies, resource allocation strategies, and user selection strategies, and pointed out several potential research directions for energy-saving federated learning.
Effectively providing computing services or solving complex problems requires a collaborative approach to task decomposition. This includes task offloading between user devices, edge networks, and cloud data centers, promoting collaboration among infrastructures such as clouds, edges, and terminal devices. Bai Xiaojun and others categorized different tasks into latency-sensitive and latency-tolerant types, modeling the system using continuous-time Markov chains. By optimizing the access threshold of edge network buffers, they achieved a balance between average latency and blocking rate.
When multiple computing and network resource providers are available, selecting the appropriate provider is crucial for task completion. Fu Yuexia and others utilized a reputation model based on the beta distribution function to evaluate the credibility of resource providers and introduced a performance-based reputation update model. This method is modeled as a constrained multi-objective optimization problem, with feasible solutions determined through an improved fast elitist non-dominated sorting genetic algorithm. Extensive simulation experiments confirmed the model’s effectiveness and efficacy in improving user satisfaction and resource utilization.
The essence of collaboration between networking and computing lies in the joint consideration of computing resource and network resource allocation. Han Xueying and others proposed an intelligent resource allocation method that combines deep reinforcement learning with graph neural networks. This method optimizes network and computing resources across network topologies, overcoming routing challenges in computing power networks even under structural changes.
The synergy between computing power and networks is crucial across various scenarios and fields. Cai Yizhuo and others are dedicated to improving communication efficiency in federated learning scenarios within 6G networks, surveying traditional and peer-to-peer federated learning architectures. The article demonstrates that computing power scheduling based on real-time resource status optimization can significantly enhance performance.
This special issue has received strong support from both academia and industry, covering multiple aspects of networking and computing collaboration, such as Internet Protocol (IP), cellular networks, etc. It should be noted that related research is still in its infancy, and many issues and technologies warrant further in-depth study.
Finally, heartfelt thanks to all the authors, reviewers, and journal editors for their support and contributions.
Scan the QR code below to read the full article:
Special Article Directory
Editorial
Coordination of Networking and Computing: Toward New Information Infrastructure and New Services Mode
Xiaoyun WANG, Tao SUN*, Yong CUI, Rajkumar BUYYA, Deke GUO, Qun HUANG, Hassnaa MOUSTAFA, Chen TIAN, Shangguang WANG
Perspective
Computing-Aware Network (CAN): A Systematic Design of Computing and Network Convergence
Xiaoyun WANG, Xiaodong DUAN, Kehan YAO, Tao SUN*, Peng LIU, Hongwei YANG, Zhiqiang LI
Review Article
A Survey of Energy-Efficient Strategies for Federated Learning in Mobile Edge Computing
Kang YAN, Nina SHU, Tao WU*, Chunsheng LIU, Panlong YANG
Research Articles
A Cloud-Edge-Device Collaborative Offloading Scheme with Heterogeneous Tasks and Its Performance Evaluation
Xiaojun BAI, Yang ZHANG, Haixing WU, Yuting WANG, Shunfu JIN*
Reputation-Based Joint Optimization of User Satisfaction and Resource Utilization in a Computing Force Network
Yuexia FU, Jing WANG, Lu LU*, Qinqin TANG, Sheng ZHANG
Combining Graph Neural Network with Deep Reinforcement Learning for Resource Allocation in Computing Force Networks
Xueying HAN, Mingxi XIE, Ke YU*, Xiaohong HUANG, Zongpeng DU, Huijuan YAO
Communication Efficiency Optimization of Federated Learning for Computing and Network Convergence of 6G Networks
Yizhuo CAI, Bo LEI*, Qianying ZHAO, Jing PENG, Min WEI, Yushun ZHANG, Xing ZHANG
Guest Editor Introduction
Wang Xiaoyun (Special Issue Editor), Chief Scientist of China Mobile Communications Group. He has received the National Science and Technology Progress Award multiple times and has been awarded the National Innovation Pioneer Award and the China Youth Science and Technology Award. His research interests include networking technology strategies, system architecture, and network technology.
Sun Tao (Special Issue Executive Editor), received his Bachelor’s degree in Automation from Tsinghua University in 2003 and his Ph.D. in Control Science and Engineering from Tsinghua University in 2008. He is currently a chief expert at China Mobile Group with over 10 years of research experience in mobile network architecture design and IP technology research and standardization, having served as Vice Chair of 3GPP SA2 (System Architecture). His research interests include 6G architecture, IP network evolution, and computing-network convergence.
Cui Yong (Special Issue Executive Editor), received his Bachelor’s and Ph.D. degrees in Computer Science and Engineering from Tsinghua University in 1999 and 2004 respectively. He is currently a professor in the Department of Computer Science and Technology at Tsinghua University. He has published over 100 papers in academic conferences and journals, winning multiple best paper awards, and is a co-author of seven Internet standards (RFC) related to IPv6 technology. He has served as an editorial board member for IEEE TPDS, IEEE TCC, and IEEE Int Comput, and is currently a co-chair of related working groups at IETF. His main research interests include mobile cloud computing and network architecture.
Rajkumar Buyya, Director of the CLOUDS Lab at the University of Melbourne. He is the author or co-author of over 800 publications, including seven textbooks. He is one of the most cited scholars in the fields of computer science and software engineering; as of 2023, his h-index is 166, g-index is 360, and his articles have been cited over 146,600 times. His research interests include cloud computing, distributed systems, service-oriented computing, and energy-efficient computing.
Guo Deke, received his Bachelor’s and Ph.D. degrees from Beihang University and National University of Defense Technology, respectively. He is currently a professor at the School of Systems Engineering, National University of Defense Technology. His research interests include distributed systems, software-defined networks, data center networks, wireless and mobile communication systems, etc.
Huang Qun, received his Bachelor’s degree in Computer Science from Peking University in 2011 and his Ph.D. from The Chinese University of Hong Kong in 2015. He is currently an assistant professor at the School of Computer Science, Peking University. From September 2017 to May 2020, he worked at the Institute of Computing Technology, Chinese Academy of Sciences, and from September 2015 to September 2017, he worked at Huawei. His research interests include network measurement, networked systems, and distributed systems.
Hassnaa Moustafa, received her Master’s degree in Distributed Systems from the University of Paris XI and her Ph.D. in Wireless and Mobile Networks from Paris Telecom. She is a Principal Engineer at Intel, focusing on edge computing and artificial intelligence solutions for IoT and network edge infrastructure. Previously, she was responsible for vehicle-cloud collaborative technologies and various IoT connectivity technology R&D at Intel. She has also served as a senior R&D engineer at Orange in France, actively participating in developing wireless network solutions for the EMEA region. She has published over 80 papers and has filed over 300 patents, with more than 100 granted. Her research interests include edge computing, converged networks, and edge AI for IoT services, as well as media and IoT services and protocols.
Tian Chen, received his Bachelor’s, Master’s, and Ph.D. degrees in Electronic and Information Engineering from Huazhong University of Science and Technology in 2000, 2003, and 2008, respectively. From 2012 to 2013, he was a postdoctoral researcher in the Department of Computer Science at Yale University; from 2013 to 2016, he served as an associate professor at the School of Electronic Information and Communication, Huazhong University of Science and Technology. He is currently a professor at the National Key Laboratory of Computer Software New Technologies, Nanjing University. His research interests include data center networks, network function virtualization, distributed systems, Internet streaming processing, and urban computing.
Wang Shangguang, received his Ph.D. from Beijing University of Posts and Telecommunications in 2011. He is currently a professor at the School of Computer Science, Beijing University of Posts and Telecommunications. He serves as the chair of the IEEE Services Computing Technical Community and the vice chair of the IEEE Cloud Computing Technical Community. He has served as the chair or project chair for over 10 IEEE conferences and is an advisor or associate editor for various journals including IEEE Trans Serv Comput, J Cloud Comput, J Softw Pract Exp, and Int J Web Grid Serv. He is a fellow of the IET and a senior member of the IEEE. His research interests include service computing, edge computing, and satellite computing. Hot Articles
1. Academician Pan Yunhe | On Visual Knowledge
2. Academician Pan Yunhe | Five Fundamental Questions of Visual Knowledge3. Academician Pan Yunhe | On Visual Understanding4. Ma Yi, Shen Xiangyang, et al. | On the Principles of Simplicity and Self-consistency in Intelligent Origins
5. Academician Duan Baoyan | Special Introduction to the Evolution and Innovation of Antenna Systems in the Post-5G and 6G Era
6. Academician Zhang Ping, Professor Peng Mugeng, et al. | Special Introduction to the Theory and Technology of Intelligent Simplification Wireless Networks
7. Academician Wu Jiangxing’s team | Discussion on the New Paradigm of Inherent Security in 6G Networks
8. Zhe University’s Yang Yi, Zhuang Yueting, et al. | Multiple Knowledge Representation under Big Data Artificial Intelligence: Framework, Applications, and Case Studies
9. National Defense University Su Jinshu, Zhao Baokang, et al. | Development Trends of Network Technologies in Large-scale Efficient Network Computing
10. Chinese Academy of Sciences Automation Institute Ye Peijun, Wang Feiyue, et al. | Parallel Cognition: Hybrid Intelligence for Human-Computer Interaction and Management
11. Chinese Academy of Sciences Wang Feiyue, Wuhan University Zhang Jun, et al. | Knowledge Automation and Hybrid Enhanced Intelligence of Human-Computer Mutual Trust: Cognitive Control Mechanisms of Complex Systems and Their Applications
12. Southwest University Liu Zhiming, National Defense University Wang Ji | Human-Machine-Object Integration Systems: Concepts, Challenges, and Research Opportunities
13. Northwestern Polytechnical University Hu Jinwen, et al. | Research on Obstacle Detection of Intelligent Vehicles in Outdoor Environments Based on Multi-Sensor Fusion
14. Beijing University of Posts and Telecommunications Zhang Jianhua, et al. | Channel Measurement and Modeling for 6G: Current Status and Prospects
15. National Defense University Wang Haonan, Li Dongsheng, et al. | Review of Deep Reinforcement Learning
16. University of Electronic Science and Technology Niu Zhongqian, Zhang Bo, et al. | Mechanical Reliability Research of 3-dB Branch Waveguide Directional Couplers in the Submillimeter and Terahertz Bands
17. Southeast University Lu Jianquan, et al. | Bipartite Asynchronous Pulse Tracking Consistency of Multi-Agent Systems
18. National Defense University Da Kai, Northwestern Polytechnical University Li Tiancheng, et al. | Research Progress on Multi-Sensor Multi-Target Tracking Based on Random Finite Sets
19. Lanzhou University of Technology Xie Ying, Ma Jun, et al. | Phase Synchronization and Energy Balance between Neurons
20. University of Illinois Zhang Kaiqing, et al. | Progress in Decentralized Multi-Agent Reinforcement Learning with Networked Agents
21. Branislav Rehak, et al. | Leader-Follower Synchronization of Multi-Agent Systems with Heterogeneous Delays
22. Huazhong University of Science and Technology Xiao Renbin, et al. | Role Division Firefly Algorithm for Complex Optimization Scheduling
23. Southeast University Wen Guanghui, et al. | Research Progress on Distributed Economic Dispatch in Smart Grids: A Review
24. Zhe University Bu Mingxuan, Pi Xiaodong, et al. | Semiconductor Nanocrystal-based Synaptic Devices
25. Peking University Yu Junzhi, et al. | Visual Detection Algorithm for Underwater Garbage Cleaning Robots Based on Improved YOLOv4
26. Fudan University Zhou Jie, Zhang Junping, et al. | ChatGPT: Potential, Prospects, and Limitations
27. Beijing University of Posts and Telecommunications Zhang Ping, Xu Xiaodong, Dong Chen, Niu Kai, et al. | Modulation Division Multiple Access Technology for Semantic Communication28. Chinese Academy of Sciences Shenyang Automation Institute Xu Chi, Yu Haibin, et al. | Industrial Wireless Network Edge Collaboration Resource Allocation Based on Multi-Agent Deep Reinforcement Learning
29. China Academy of Space Technology Wang Yuying, Li Jindong, et al. | Progress in Space Applications of Mid-Long Wave Infrared Detection Technology
30. Huazhong University of Science and Technology Xiao Renbin: Four Development Stages of Collective Intelligence Journal Dynamics Latest impact factor 3.0, Q2 area, comprehensive journal in information electronics | FITEE calls for papers! The China Association for Science and Technology published the “Comprehensive Directory of High-Quality Scientific Journals”, and FITEE was included in the T1 directory of the information and communication field! The first academic frontier forum for youth in the field of information and electronic engineering was successfully held, led by Academician Duan Baoyan. The latest impact factor for 2021 was announced, and FITEE broke through 2.0 for the first time. FITEE’s impact factor increased by 55%, entering the Q2 area for the first time. FITEE published the first outstanding paper/special issue, outstanding editorial board members/communication experts list! FITEE’s editor-in-chief and editorial board article list (2019.1~2021.8) FITEE’s communication expert article list (2019.1~2021.8) Focusing on advanced integrated circuit technology and industrial innovation, the 5th “Chinese Academy of Engineering Information and Electronic Engineering Frontier Forum” was successfully held! The Chinese Academy of Engineering released the 10+10 global engineering frontiers in the information electronics field. FITEE WeChat has launched a new feature, allowing users to read the abstracts and full texts of each issue in both Chinese and English without downloading PDFs. The second expanded meeting of the editorial board of “Frontiers of Information Technology & Electronic Engineering” (FITEE) was successfully held in 2020. The first meeting of the first editorial board of FITEE was held at Zhejiang University. The first meeting of the second editorial board of FITEE was held at Zhejiang University.
About This Journal
Frontiers of Information Technology & Electronic Engineering (abbreviated as FITEE, Chinese name 《信息与电子工程前沿（英文）》，ISSN 2095-9184, CN 33-1389/TP) is a comprehensive English academic monthly journal in the field of information electronics, indexed in SCI-E and EI, with the latest impact factor of 3.0, located in the JCR Q2 area. It originated from the English edition C of the Journal of Zhejiang University, founded in 2010, and was renamed to its current name in 2015. It is now a sub-journal of the Chinese Academy of Engineering in the field of information and electronic engineering, covering computer, information and communication, control, electronics, optics, and other fields. Article types include research papers, reviews, personal views, commentaries, etc. The current editors-in-chief are Academician Pan Yunhe and Fei Aiguo. It operates under an international peer review system, with initial feedback typically within 2-3 months. Once accepted, articles are published online quickly.
In 2019, it received funding from the Chinese Association for Science and Technology and other seven ministries as part of the Excellent Action Plan for Chinese Scientific Journals (Tier Journals). From 2021 to 2022, it was successively selected as a high-quality scientific journal grading directory in the fields of information communication (organized by the China Communications Society) and computing (organized by the China Computer Federation), both listed at the highest T1 level; it was also included in the recommended directory of international academic conferences and journals by the China Computer Federation-2022 (cross-disciplinary/comprehensive/emerging).
Official Website: http://www.fitee.zjujournals.com
Journal Springer Homepage:
http://www.springer.com/computer/journal/11714
Submission: http://www.editorialmanager.com/zusc
Postal Code: 32-324
Address: 148 Tianmushan Road, Xihu District, Hangzhou, Zhejiang Province, China
Phone: +86-571-88273162
Email: [email protected]
WeChat Group Invitation To facilitate communication and discussion among researchers, we have established the following subject WeChat groups. Users who wish to join the group should add the editor’s personal WeChat ID: fitee_xb and leave a message indicating their institution and the group they wish to join. The editor will add you to the group. Marketing personnel, please refrain from contacting.
|
Computer Science and Technology Group |
Optical Engineering and Technology Group |
|
Control Science and Technology Group |
Information and Communication Group |
|
Electronics Discussion Group |
Artificial Intelligence Group |
Follow Us ID: fitee_cae This official WeChat account serves the journal “Frontiers of Information Technology & Electronic Engineering” (FITEE, SCI-E and EI indexed journal) and includes functions such as: disseminating academic articles from the journal; providing convenient services for related scholars (readers, authors, reviewers, editorial board members, etc.); publishing information related to academic writing, reviewing, editing, and publishing; introducing academic figures, thoughts, and achievements in the field of information and electronic engineering, showcasing cutting-edge progress in scientific research in this field; and providing a friendly interactive platform for scholars at home and abroad in this field.