Space-air-ground integrated network (SAGIN) is envisioned as a key network architecture for achieving ubiquitous coverage in the next-generation communication system. To manage SAGIN’s inherent complexity, artificial intelligence (AI) provides essential control capabilities, driving enhanced automation and flexibility. Despite this, there remains a significant research gap concerning the interaction between AI and SAGIN. In this context, we first present a promising approach for developing a generalized AI model capable of executing multiple tasks simultaneously in SAGIN. Subsequently, we propose a framework that leverages software-defined networking (SDN) and AI technologies to manage the resources and services across the entire SAGIN. Particularly, we demonstrate the real-world applicability of our proposed framework through a comprehensive case study. These works pave the way for the deep integration of SAGIN and AI in future wireless networks.
This paper addresses the challenge of managing service function chaining (SFC) in an unmanned aerial vehicle (UAV) IoT, a dynamic network that integrates UAVs and IoT devices for various scenarios. To enhance the service quality and user experience of the UAV IoT, network functions must be flexibly configured and adjusted based on varying service demands and network situations. This paper presents a model for calculating benefits and an agile algorithm for embedding and migrating SFC based on particle swarm optimization (PSO). The model takes into account multiple factors such as SFC quality, resource utilization, and migration cost. It aims to maximize the SFC benefit and minimize the migration times. The algorithm leverages PSO’s global search and fast convergence to identify the optimal or near-optimal SFC placement and update it when the network state changes. Simulation experiments demonstrate that the proposed method improves network resource efficiency and outperforms existing methods. This paper presents a new idea and method for managing SFC in UAV IoT.
We propose a heuristic connection rerouting scheme that iteratively bridges and rolls a subset of connections for improving network utilization. The proposed scheme has no disrupted connection and has low computation and control complexity.
In this paper, common mode (CM) and differential mode (DM) far-field radiation models of a typical digital inverter with cables are built up to predict electromagnetic field strength and analyze field characteristics. The CM current model and its analyses are based on the imbalance difference method. It is found out that the voltage between the drain and the source electrodes of upper transistor is the key equivalent source of electromagnetic interference (EMI). Far-field radiation strength of the digital inverter in free space is predicted by using the asymmetrical antenna radiation method and current loop radiation method. The accuracy of these methods is verified by the CST electromagnetic simulation results in the frequency range from 1 MHz to 400 MHz. Furthermore, the radiation models are improved by using the mirror method, which enables to include the reflection effect of the metal ground plane at the electromagnetic compatibility (EMC) test site. Both the results of measurements in a semi-anechoic chamber and the simulation results confirm the proposed electromagnetic radiation prediction method.