Knowledge Transfer and Reuse: A Case Study of Ai-Enabled Resource Management in RAN Slicing

Efficient resource management scheme is critical to enable network slicing in 5G networks, in envisioned 6G networks, and artificial intelligence (AI) techniques offer promising solutions. Considering rapidly emerging new machine learning (ML) techniques, such as graph learning, federated learning (FL), and transfer learning, a timely survey is needed to provide an overview of resource management and network slicing techniques for AI-enabled wireless networks. This article provides such a survey along with an application of knowledge transfer in radio access network (RAN) slicing. In particular, we first provide some background on resource management and network slicing, and review relevant state-of-the-art AI and ML techniques and their applications. Then, we introduce our AI-enabled knowledge transfer and reusebased resource management (AKRM) scheme, where we apply transfer learning to improve system performance. Compared with most existing works, which focus on the training of standalone agents from scratch, the main difference of AKRM lies in its knowledge transfer, and reuse capability between different tasks. Our article provides a roadmap for researchers for applying knowledge transfer schemes in AI-enabled wireless networks, as well as a case study of resource allocation problem in RAN slicing.