Generative Artificial Intelligence in Cloud-Edge Collaboration: Service Optimization and Efficient Inference Exploration

Dear Colleagues,

Generative Artificial Intelligence (GAI) has achieved remarkable success in relation to cloud technology, demonstrating powerful generative capabilities and a broad range of application prospects. Additionally, edge computing is playing an increasingly critical role in GAI by optimizing computational efficiency, reducing latency, and enabling localized data processing, particularly in tasks such as big data analytics and real-time inference. In scenarios that combine cloud and edge computing, GAI is presented with new growth opportunities. Cloud computing provides robust support for the training and fine-tuning of large generative models; however, as application demands increase, decentralizing these capabilities to edge devices is becoming increasingly important to enhance service coverage and real-time responsiveness. GAI technology is widely applied in fields such as image generation, natural language processing, and personalized recommendation, where low latency and real-time processing are essential. Therefore, offloading computational tasks from the cloud to edge devices, while leveraging the cloud’s powerful computational capabilities, not only optimizes model service quality but also enhances inference efficiency and user experience.

This Special Issue seeks to explore service optimization and efficient inference of GAI in cloud–edge collaborative environments. We welcome research on the following topics:

• GAI-based IoT services and applications;
• Cloud–edge collaborative training for GAI;
• Continuous learning and the adaptability of GAI in cloud–edge scenarios;
• Efficient inference and heterogeneous acceleration for GAI at the edge;
• Energy management and power consumption optimization techniques for GAI;
• Memory overhead optimization for GAI;
• Communication optimization and service enhancement for GAI;
• Training and inference acceleration in heterogeneous environments for GAI;
• Security and privacy protection for GAI;
• Efficient computing architectures for GAI;
• Hardware accelerator design for GAI.

Additionally, this Special Issue aims to foster collaboration between academia and industry in optimizing GAI through cloud–edge collaboration, showcasing the latest research achievements in integrating GAI with IoT and its innovative practical applications.

Dr. Zongwei Zhu
Dr. Changlong Li
Dr. Xianzhang Chen
Dr. Shouzhen Gu
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. Applied Sciences 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.

• cloud–edge collaboration
• generative AI
• efficient inference
• distributed training
• edge computing
• energy optimization
• resource overhead
• real-time processing
• IoT applications