Distributed Machine Learning and Federated Learning for Network Optimization towards 6G

Dear Colleagues,

The Beyond 5G (B5G)/6G Ecosystem will involve the cooperation of a highly heterogeneous set of network technologies, including both Terrestrial and Satellite/Aerial Networks, to fulfill requirements of the future fully connected digital society, anticipating the Internet of Everything (IoE). In IoE, sensors are embedded with processes, people, data and things, to monitor, identify the status and act intelligently to generate new opportunities for the society. The 6G Ecosystem is expected to take the 5G softwarization and virtualization to the next level by empowering the network with Artificial Intelligence (AI)/Machine Learning (ML) approaches to optimize the network operation.

ML is increasingly being used in real-world applications; thus, recent trends even surpass the fundamental requirement for high prediction accuracy, paving the way for increased robustness, resilience, reasoning and conformity to safety, security and legal aspects. In addition to centralized ML, distributed ML and federated learning (FL) have emerged, each intended to serve a different set of applications. As computing moves closer to the edge, distributed ML and FL offer a way of harnessing the vast sensor data, streamed in real time from land, sea, air and space. FL enables mobile devices to collaboratively learn a shared prediction model, while keeping all the training data on device, performing the training to the device as well, resulting in lower latency and less power consumption, while ensuring privacy. However, distributed ML and FL come with the cost of higher communication overhead. Verticals that might benefit from distributed ML and FL include virtual reality/augmented reality (VR/AR) applications running on the edge, Industry 4.0 with Time Sensitive Networking function, transport applications, such as autonomous driving, and so on.

The objective of this Special Issue is to present studies in the field of network optimization with ML, towards the 6G Ecosystem, with an emphasis on distributed ML and FL. The topics of interest include, but are not limited to, autonomous slice management, control and orchestration, cross-layer optimization, anomaly detection, and analytics.

Researchers are invited to submit their manuscripts to this Special Issue, contributing with both theoretical and practical studies, including new theories, techniques, concepts, algorithms, and analyses and/or system experiments, prototypes and new applications.

Dr. Adamantia Stamou
Dr. Vasos Vassiliou
Dr. Jose Costa-Requena
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning (ML)
• edge intelligence
• federated learning (FL)
• native ML
• cloud-based ML
• Beyond 5G (B5G)
• 6G
• Internet of Everything (IoE)
• network optimization