Search for: All records

Advanced air mobility (AAM) has introduced a new mode of air transportation that can be integrated, providing services including air taxis, which can quickly transport people and cargo from one place to another. However, urban airspace is already congested with commercial air traffic, so there is a need for an efficient and autonomous airspace management system. Establishing structured air corridors and enabling UAS-to-UAS (U2U) communications are essential to achieve autonomy. Air corridors are designated airspace primarily reserved for AAM traffic, which will streamline the movement of unmanned aircraft systems (UAS). Meanwhile, U2U communications facilitate efficient collision avoidance strategies (CAS). A key aspect of this system is the development of CAS, which requires advanced communication protocols to monitor traffic patterns and detect potential collisions. This paper explores designing and implementing CAS using U2U communications. Use cases for U2U communications include merging, minimum separation, information relay, collaborative sensing, and rerouting. All these use cases demand real-time solutions for managing traffic conflicts involving multiple UAS. The CAS discussed in this paper utilizes U2U communications to mitigate the risk of collisions in the airspace and demonstrates how U2U communications can assist in efficient AAM traffic management through simulations. 

Federated Learning (FL) revolutionizes collaborative machine learning among Internet of Things (IoT) devices by enabling them to train models collectively while preserving data privacy. FL algorithms fall into two primary categories: synchronous and asynchronous. While synchronous FL efficiently handles straggler devices, its convergence speed and model accuracy can be compromised. In contrast, asynchronous FL allows all devices to participate but incurs high communication overhead and potential model staleness. To overcome these limitations, the paper introduces a semi-synchronous FL framework that uses client tiering based on computing and communication latencies. Clients in different tiers upload their local models at distinct frequencies, striking a balance between straggler mitigation and communication costs. Building on this, the paper proposes the Dynamic client clustering, bandwidth allocation, and local training for semi-synchronous Federated learning (DecantFed) algorithm to dynamically optimize client clustering, bandwidth allocation, and local training workloads in order to maximize data sample processing rates in FL. DecantFed dynamically optimizes client clustering, bandwidth allocation, and local training workloads for maximizing data processing rates in FL. It also adapts client learning rates according to their tiers, thus addressing the model staleness issue. Extensive simulations using benchmark datasets like MNIST and CIFAR-10, under both IID and non-IID scenarios, demonstrate DecantFed’s superior performance. It outperforms FedAvg and FedProx in convergence speed and delivers at least a 28% improvement in model accuracy, compared to FedProx.