23 August 2020 in Journal of Signal Processing Systems
25 December 2023 in IEEE Transactions on Vehicular Technology
In 6G systems, non-terrestrial networks (NTNs) are poised to address the limitations of terrestrial systems, particularly in unserved or underserved areas, by providing infrastructure with mobility that enhances reliability, availability, and responsiveness. Among various types of mobile infrastructures, low earth orbit (LEO) satellite communication (SATCOM) has the potential to offer extended coverage that supports numerous devices simultaneously with low latency. Consequently, LEO SATCOM attracts significant attention from academia, government, and industry. The dynamic formation problem must be solved to form a swarm connecting to the ground station with the most appropriate satellites to achieve LEO SATCOM systems with higher throughput. Existing solutions use computationally demanding methods to solve the NP-hard problem and cannot be employed for SATCOM systems with short coherence time. Furthermore, precise channel state information (CSI) between the ground station and all candidate satellites is required for formation designs, resulting in significant signaling overheads. To overcome these drawbacks, we propose a learning-based dynamic formation method for real-time dynamic formation capability. Specifically, motivated by the channel features of LEO SATCOM, we develop a CSI estimation method to provide coarse CSI (i.e., imperfect CSI) solely based on available geometrical information of LEO SATCOM and without any signaling overhead. Then, our approach can utilize the obtained coarse CSI as inputs and provide valuable guidelines as priorities to access specific satellites for fine-grained CSI (i.e., precise CSI). The prediction results are validated using a small-scale brute force method to determine the final formation. Our intensive simulation results suggest that the proposed method can aid current LEO SATCOM by providing real-time formation results, particularly in low-transmit power regions. Specifically, the proposed method can achieve 90% of full capacity with only 32% signaling overhead to build high-throughput LEO SATCOM.
29 May 2023 in IEEE Network
In next-generation (i.e., 6G) networking systems, the data-driven approach will play an essential role, being an efficient tool for networking system management and bringing popular user applications. With those unprecedented and novel usages, existing frameworks fail to consider the complex nature of the next-generation networking system and consequently fail to be applied to future communication systems directly. Moreover, existing frameworks also fail to support popular privacy-preserving learning strategies efficiently by presenting special designs to respond to the resource-demanding nature of the aforementioned strategies. To fill this gap, this paper extends conventional serverless platforms with serverless edge learning architectures, providing a mature and efficient distributed training framework by fully exploiting limited wireless communication and edge computation resources in the considered networking system with the following three features. Firstly, this framework dynamically orchestrates resources among heterogeneous physical units to efficiently fulfill privacy-preserving learning objectives. The design jointly considers learning task requests and underlying infrastructure heterogeneity, including last-mile transmissions, computation abilities of edge and cloud computing centers, and loading status of infrastructure. Secondly, the proposed framework can easily work with data-driven approaches to improve network management efficiency, realizing AI for network promise of next-generation networking systems to provide efficient network automation. Lastly, to significantly reduce distributed training overheads, small-scale data training is proposed by integrating with a general, simple data classifier. This low-load enhancement can seamlessly work with various distributed deep models in the proposed framework to improve communications and computation efficiencies during the training phase. Based on the above innovations, open challenges, and future research directions encourage the research community to develop efficient privacy-preserving learning techniques.
18 May 2023 in Journal of Signal Processing Systems
2 June 2023 in Research Square
Industry 4.0-enabled smart factories are expected to realize the next revolution for manufacturers. Although artificial intelligence (AI) technologies have improved productivity, current use cases belong mainly to small-scale and single-task operations.A zero-touch network platform is developed for intelligent manufacturing, which unbound the potential of a smart factory by facilitating distributed AI applications in both training and inferring stages in a large-scale manner.The open radio access network (O-RAN) architecture is first introduced for the zero-touch network platform to enable globally controlling communications and computation infrastructure capability in the field.Then, a devised serverless-based framework allows intelligent and efficient learning assignments and resource allocations.Hence, requested learning tasks can be assigned to appropriate robots, and the underlying infrastructure can be used to support the learning tasks without expert knowledge.Due to the proposed network system's flexibility, powerful AI-enabled networking algorithms can ensure service-level agreements and superior performance for factory workloads.Finally, three open research directions related to backward compatibility, end-to-end enhancements, and cybersecurity are discussed for a zero-touch smart factory.