Li ZHOU,
National University of Defense Technology
Generative AI Meets Semantic Communication: Optimizing Radio Map Construction and Distribution in Future Mobile Networks
Abstract: With the rapid development of the Internet of Things and smart cities, the demand for effective spectrum collaboration has grown significantly. Radio maps play a crucial role in understanding the spatial radio environment, which is essential for wireless applications such as cell planning and radio resource management. However, generating radio maps is a resource-intensive task, as the construction process is complex and the distribution process consumes substantial bandwidth. We propose a method that combines semantic communication (SemCom) and generative artificial intelligence (GAI) to optimize the construction and distribution processes of radio maps. By incorporating SemCom, our method transmits only key semantic information during the distribution process, significantly reducing bandwidth usage while ensuring accurate and efficient information transfer. While the diverse generative capabilities of GAI introduce some instability, which could be a limitation in radio map construction, this article achieves precise content decoding through prompts based on multi-modal semantic information, enabling accurate construction and restoration of radio maps. By utilizing SemCom and GAI technologies, the cost of applications of radio maps can be significantly reduced, which is beneficial for stimulating the pace of intelligence evolution in future mobile networks.
Bio: Li Zhou received the B.S., M.S., and Ph.D. degrees from the National University of Defense Technology (NUDT), Changsha, China, in 2009, 2011, and 2015, respectively. From September 2013 to September 2014, he was a Visiting Scholar with The University of British Columbia, Vancouver, BC, Canada. He is currently an Associate Professor with the College 999 of Electronic Science and Technology, NUDT. His research contributions have been published and presented in more than 70 prestigious journals and conferences. His research interests are in the area of mobile edge computing networks, intelligent networks, and software defined communication systems. Dr. Zhou regularly serves as a TPC Member in flagship conferences in IEEE ComSoc.
Liangtian Wan,
Dalian University of Technology
Parameter Estimation Based on Passive Radar
Abstract: We proposed a new algorithm for range-Doppler estimation in PBR within the framework of sparse recovery in compressed sensing. By using a simulated scenario, we show that the algorithm is effective to reduce the masking effects of strong targets over weak ones. In addition, we have implemented the PBR system to collect real data and validate the proposed algorithms based on the real data. Compared with the conventional beamforming, our proposed method has better estimation performance for direct path. When the beam we observe and the beam of the direct path are too closed, compared with the beamforming, more number of frames can be observed using our proposed method. Since the effect among the target has been reduced, the M-OMP has better estimation performance for range-Doppler-angle estimation compared with the conventional MF method, especially for DOA estimation.
Bio: Liangtian Wan received the B.S. degree and the Ph.D. degree in the College of Information and Communication Engineering from Harbin Engineering University, Harbin, China, in 2011 and 2015, respectively. From Oct. 2015 to Apr. 2017, he has been a Research Fellow of School of Electrical and Electrical Engineering, Nanyang Technological University, Singapore. He is currently an Associate Professor of School of Software, Dalian University of Technology, China. Dr. Wan has been serving as an Associate Editor for IEEE Access and Journal of Information Processing Systems. His current research interests include array signal processing, graph learning and data science.
Lu Sun,
Dalian Maritime University
Intelligent Resource Allocation in Mobile Egde Computing
Abstract: With the increasing popularity of resource-intensive mobile applications, offloading computationally expensive tasks to the edge nodes such as base stations and access points will be a key feature of Mobile Edge Computing (MEC) networks. However, compared to the classical remote cloud, these edge nodes are typically equipped with low-power computational resources with limited computational capability. Therefore, efficient computation offloading systems need to be designed where the servers are efficiently utilized while fulfilling the users’ latency constraints. In this talk, we focus on the challenges of mobility and energy constraints at edge nodes, constructing UAV-enabled MEC model and WPT enabled MEC model. We propose intelligent optimization methods based on reinforcement learning to optimize task allocation and computation offloading jointly in both offline and online task scenarios, reducing task computation latency and meeting users’ quality of experience (QoE) requirements.
