With the rapid innovation of communication techniques, huge amounts of data from mobile social networks, industrial sensors, the Internet of Things, etc., are collected to extract value through data analytics, thereby offering big data services and meeting diverse Quality of Experience (QoE) requirements of users. Machine Learning (ML) owning to its ability is used to learn from data and provide data-driven insights, decisions, and predictions. Considering the diverse characteristics of big data, traditional ML techniques are facing obstacles.
Meanwhile, valuable information as vital resources for future networks can be optimized for improving the Quality of Service (QoS) of networks. Deep Reinforcement Learning (DRL) technology empowers intelligent decision-making of resources, i.e., the allocation of radio resources, the control of computing resources,s and the replacement of caching resources for future wireless communications through powerful learning and automatic adaptation capabilities, while supervised ML may help to predict the coming resources via capturing the time-varying data features, etc. As a powerful approach, AI is expected to play a game-changing role in future communications and networking since it can be exploited to provide innovative solutions to lots of emerging research issues, e.g., channel assignment and power allocation for improving the accessible data rate, computing resource (i.e., CPU cycle) control for the tradeoff between energy-saving and execution delay of large-scale distributed training, caching replacement for the coming demands of mobile users.
In addition, with the increasing prevalence of massive datasets, large numbers of concerns regarding the security of cached information, the privacy of accessing desired information, the reliability of distributed computing, distributed training, and learning systems are raised. Current methods based on coding, communication, and information-theoretic have achieved exciting goals for the security of privacy. Many theoretical and practical can also open the proposed problems.
To better support future communications and networking, new ideas, theories, designs, mechanisms, frameworks, and technologies are called by us.
This workshop program will be included as a part of the IEEE BigDataService 2022 program. This year’s conference is scheduled to take place in the San Francisco Bay Area, from 22-25 August 2022. The topics include, but are not limited to, the following:
- Machine learning, data mining, and big data analytics in networking
- Software-defined network and network function virtualization for big data
- Cloud, Edge, End computing for big data
- Distributed network monitoring architectures for big data
- Scalability and efficiency for big data
- Acquisition, integration, cleaning, and practice for big data
- Computational modeling and intelligent algorithms for big data
- QoS-oriented intelligent network architecture in future communication systems
- Intelligent decision-making systems for QoE-based big data services.
- Learning-based and other innovative approaches for intelligent big data services.
- Artificial intelligence, big data analytics, resource management in networking
- Big data analytics and visualization for network traffic
- Big data analytics for intelligent computing and caching
- Novel Communication protocols and systems for throughput in networking
- Intelligent management for radio resources and caching resources
- Distributed intelligence for supporting edge computing
- Cloud-edge-end converged computing, communication, and caching in learning-based networking architectures
- Distributed learning-based big data analytics in networking
- Distributed model training and inference in future communications and networking.
- Emerging methods for joint optimization of computation, caching, and communication in future communications and networking.
- Security and privacy solutions learning-based in future communications and networking
- Security and privacy of distributed learning systems for collaborative edge-end
- Security and privacy of federated learning systems on mobile devices
- Learning-based security protocols for secure communications
- Learning-based message authentication in future communications systems
- New cryptographic algorithms for data security and privacy in networking
- Learning-based data security in networking
- Blockchain-based data privacy protection in networking
- Secure data application and service provisioning in future communications and networking
All papers have to be submitted in PDF format through the BDS Easychair account, selecting the option: WORKSHOP – Big Data Service-oriented Intelligent Resource Management, Information Security, and Privacy Preservation for Future Communications and Networking.
A paper submitted at this forum is expected to be original research not previously published. A submission may not be concurrently submitted to another conference, workshop, or journal. The length of a camera-ready paper will be limited to 5 pages double column proceedings format with up to 2 additional pages (with charges for each additional page). Authors must follow IEEE Proceedings Author Guidelines to prepare papers with the template. Please see the following link for details: http://www.ieee.org/conferences_events/conferences/publishing/templates.html.
At least one of the authors of each accepted paper is required to pay the full registration fee and present the paper at the workshop in person.
The accepted papers will be published as part of IEEE BigDataService 2022 Proceedings by IEEE CPS and included inside IEEE Xplore digital library. The workshop program will be included as a part of the IEEE BigDataService 2022 program. Selected Papers will be invited to submit to a journal special issue with 40% updates and enhancements.
Full paper submission: May 30, 2022
Notification: June 15, 2022
Final Paper and Registration: June 15, 2022
Conference: 15-18 August, 2022
Yingchi Mao, Hohai University, China
Ping Ping, Hohai University, China
Program Committee Chairs
Wankou Yang，Southeast University