About this Research Topic
This Research Topic aims to collect cutting-edge leapfrog submissions of distributed ledger and machine learning over future space networks from academia and industry, thereby advancing the development of fundamental theories for communication-efficient learning over space and the application of blockchain and machine learning algorithms to space network optimization.
Blockchain, Machine learning and data-driven space networking of satellite IoT have recently been highly regarded as important facilitators for the next generation's space networks. Most existing space network learning systems are based on the centralization of training and inference processes by transferring data to satellites from advanced smartphones and ground stations.
Nevertheless, such a centralized approach may lead to privacy issues, breach satellite applications' latency restrictions, or become ineffective due to high cost, bandwidth or border capacity constraints. The approach towards DLT-based machine learning in space is an exciting approach for solving these issues, by providing terrestrial devices that collaboratively train a locally standard model using mobile data generated in real-time. However, distributed preparation and deduction do involve connectivity through wireless connections between ground devices, satellites and servers.
Potential topics may include, but are not limited to, the following:
• Novel distributed ledger technology (DLT) theories and learning techniques for Satellite IoT, zero trust access, satellite edge computing, age of information, and multipath TCP diversity for improving the performance of the space system.
• Joint communication, computing, and sensing for DLT decentralized learning over future space networks.
• New Low Earth Orbit architectures for supporting decentralized learning and DLT.
• DLT-based Privacy and security issues of federated and zero trust access for the satellite IoT
• Role of DLT and machine learning in emerging satellite IoT applications, such as the autonomous shipping, autonomous vehicles, smart ocean, intelligent reflecting surfaces, and virtual reality systems.
• Building testbed and Satellite simulators for DLT and distributed learning over the space
• Rethink of satellite IoT using DLT, space communication and learning integrated DLT algorithms for realizing an intelligent remote communication.
• Adaptive DLT design and optimization for satellite IoT and space networks for improving the performance of remote federated learning.
• Revolutionary Satellite IoT network protocol designs for remote collaborative federated learning.
• DLT and decentralized learning for intelligent satellite data processing, signal processing, space signal detection and estimation.
Please note: There is currently a 50% publishing discount in place for the journal - this is already reflected in the fees page of our website. This is in effect until June 2021, and any submissions before the 16th June 2021 will receive this discount automatically. Our institutional agreements and fee support department are also in place to assist authors who cannot afford the APC charges.
Keywords: federated learning, satellite IoT, satellite edge computing, space communication, space networks
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.