Because of their low latency, cost-effective construction, and rapid product updating, low-Earth-orbit (LEO) satellite networks have become an important part of the space infrastructure system. Software-defined network technology provides a candidate solution to adapt quickly and flexibly to network conditions and users’ requirements. However, with the numerical increase in satellites and expansion on the network scale, the multiple controller placement and the division of network control rights (MCP-DCR) problem in software-defined-network-enabled LEO satellite networks is a tough challenge with limited onboard resources and high dynamic topology. Aiming at the MCP-DCR problem in LEO satellite networks, this paper proposes a spectral clustering-based controller placement approach (SCCP) with reliability, latency, and load considered. In the proposed approach, a similarity matrix is adopted to cluster satellites firstly, and then a reliability model is constructed in which partial switch nodes are enabled with programmability. Finally, the network utility function is used to comprehensively measure network performance, and multiple controllers are determined based on network utility function optimization. Simulation results validate the effectiveness and adaptation of the proposed SCCP in multiple LEO satellite networks, which can improve the reliability and latency of controllers compared to those of the K-means-based method and exhaustive method.

A space-ground integrated network (SGIN) will be a future network for the heterogeneous convergence of space- and ground-based networks. The SGIN envisions satellites with the capability to adapt to various communication protocols, enabling the convergence of diverse network systems. A crucial aspect of satellite payload in the SGIN is the recognition of satellite signal types and their modulation modes, which substantially enhances the processing of heterogeneous wireless signals at the baseband processing. A multitask learning (MTL) model-based convolutional neural network (CNN) architecture is proposed, which addresses the recognition problem. An MTL model-based CNN architecture is proposed, which addresses the recognition problem. This model is composed of 3 key components: A multi-input part that processes in-phase/quadrature (IQ) complex signals and power spectral density data, a set of shared part that facilitates the model’s efficiency and mitigate overfitting, and a multitask output part capable of concurrently recognizing signal types and modulation modes. Furthermore, we have developed a dataset that encompasses 5 satellite signal protocols, i.e., signal type, and 6 modulation modes, derived from the digital video broadcasting (DVB) protocols and the tracking, telemetry, and command (TT&C) standards of the consultative committee for space data systems (CCSDS). This dataset also takes into account the impact of the additive white Gaussian noise (AWGN) channel and land mobile satellite (LMS) channel models. Simulation experiments validate the effectiveness of the proposed MTL model in accurately identifying various satellite signal protocols and modulation techniques.