Reinforcement Learning in Edge Intelligence for Next-Generation Communications and Security

Dear Colleagues,

Amidst the rapid strides in information technology, next-generation communication systems are evolving towards unprecedented intelligence, security, and efficiency levels. Edge intelligence, which embeds artificial intelligence (AI) capabilities directly at the network's periphery, is a transformative technique set to revolutionize communication and security. Reinforcement learning (RL), a promising approach to decision-making and optimization, holds immense potential to bolster the capabilities of edge intelligence in intricate and ever-changing environments.

The integration of reinforcement learning into edge intelligence architectures has emerged as a cornerstone technology for the next generation of communication systems. This Special Issue will explore innovative research on reinforcement learning, edge intelligence, next-generation communications, and security and privacy intersect, with an emphasis on zero-trust architectures that ensure robust defenses, federated learning-empowered edge intelligence fostering privacy-preserving collaboration, and resource allocation and optimization strategies that maximize system performance.

The Special Issue welcomes original, high-quality research articles that address theoretical and practical aspects of reinforcement learning in edge intelligence for next-generation communications and security. Topics of interest include, but are not limited to, the following:

Edge Intelligence Architectures and Frameworks: Novel architectures and frameworks that integrate reinforcement learning at the network edge to enable intelligent decision-making in communications and security.

Reinforcement Learning for Edge Intelligence: Research exploring novel reinforcement learning algorithms and techniques tailored to edge intelligence architectures, emphasizing their ability to enable intelligent decision-making at the network edge.

Next-Generation Communications and Edge Intelligence: Investigations into how reinforcement learning can enhance next-generation communication systems, including 5G/6G networks, Internet of Things (IoT), and satellite communications, through edge intelligence.

Security and Privacy in Edge Intelligence: Studies on leveraging reinforcement learning to strengthen security and privacy mechanisms in edge-enabled communication systems, including zero-trust architectures, intrusion detection, and access control.

Zero-Trust Architecture and Reinforcement Learning: Explorations into how reinforcement learning can be integrated into zero-trust security frameworks to dynamically adapt security policies and defenses at the edge, ensuring trustworthiness in untrusted environments.

Federated Learning-Enabled Edge Intelligence: Research on the use of federated learning in conjunction with reinforcement learning to enable privacy-preserving edge intelligence, where local models are trained collaboratively without sharing raw data.

Resource Allocation and Optimization: Investigations into reinforcement learning-based resource allocation and optimization strategies for edge-enabled communication systems, including dynamic spectrum access, energy management, and computation offloading.

Dynamic Network Management and Control: Exploration of reinforcement learning algorithms for dynamic network management and control, including traffic routing, congestion control, and quality-of-service optimization.

Adaptive and Robust Communication Protocols: Development of adaptive and robust communication protocols based on reinforcement learning, which can dynamically adjust to time-varying networks and security threats.

Cooperative and Multi-Agent Reinforcement Learning: Investigation of cooperative and multi-agent reinforcement learning approaches for distributed edge intelligence in large-scale communication networks.

Real-World Applications and Case Studies: Case studies and real-world applications showcasing the effectiveness of reinforcement learning in edge intelligence for communications and security, including smart cities, industrial IoT, autonomous vehicles, and remote healthcare.

Interdisciplinary Challenges and Opportunities: Discussions on the interdisciplinary challenges faced in integrating reinforcement learning, edge intelligence, and next-generation communications, as well as opportunities for future research and collaboration.

Dr. Xiaozhen Lu
Guest Editor

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. Mathematics 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 2600 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.

• reinforcement learning
• edge intelligence architecture
• next-generation communications
• security and privacy
• zero-trust architecture
• federated learning-enabled edge intelligence
• resource allocation and optimization