In this paper, we study a spectrum-sharing satellite system, consisting of a pair of geosynchronous earth orbit (GEO) and low earth orbit (LEO) constellation, where the LEO satellites perform wireless transmissions relying on the shared spectrum of the GEO. In order to characterize spectrum-utilization law of the GEO and guide the access of the LEO users, we propose a deep learning based prediction model to generate the spectrum situation, termed as the convolutional neural network and bidirectional long short-term memory (CNN-BiLSTM). Specifically, the historical spectrum occupancy data of the GEO are first preprocessed and then sent into the proposed CNN-BiLSTM model for prediction purposes. Moreover, due to the fact that a user of the GEO always occupies multi-channel, the proposed CNN-BiLSTM model may generate multiple predicted results concurrently. Thus, a fusing network is designed to effectively combine the multiple predicted results. Additionally, the conventional long short-term memory (LSTM), the bidirectional long short-term memory (BiLSTM), the convolutional neural network and long short-term memory (CNN-LSTM) models are also considered for comparison purposes. Performance evaluations show that the proposed CNN-BiLSTM outperforms the LSTM, the BiLSTM and the CNN-LSTM models in terms of both the accuracy and the mean absolute error of the spectrum prediction.

In this paper, we investigate the spectrum-sharing for a space information network comprised of a geostationary orbit (GEO) satellite and a pair of low earth orbit (LEO) satellites, where one spectrum-sensing LEO (SLEO) is used to sense the status of spectrum occupancy of the GEO, and one data-transmission LEO (DLEO) satellite is allowed to access the shared spectrum of the GEO with the aid of the SLEO. In order to improve the throughput of the DLEO satellite, a spectrum sharing framework has been conceived relying on two stages. Differing from the conventional spectrum-sharing scheme, the data-transmission LEO satellite has the ability to access the shared spectrum both in overlay mode and in underlay mode. In overlay mode, the DLEO can perform transmission at any required transmit power. By contrast, in underlay mode, a spectrum-sensing and power allocation aided spectrum-sharing (SPA-SS) scheme is proposed to guarantee that the maximal amount of interference is imposed on the GEO caused by the DLEO. To be specific, in the first stage, the SLEO is invoked for performing spectrum-sensing, where the time intervals of spectrum-sensing have been specifically optimized to alleviate the interference received at the GEO in the second stage. Moreover, an adaptive power allocation is designed to maximal the throughput of the DLEO in the second stage, whilst maintaining the maximal interference imposed on the GEO is lower than the tolerable interference temperature of the GEO. Numerical results show that the proposed SPA-SS scheme outperforms the traditional spectrum-sharing scheme in terms of not only the average throughput, but also of the time-utilization ratio.

Beam hopping technology provides a foundation for the flexible allocation and efficient utilization of satellite resources, which is considered as a key technology for the next generation of high throughput satellite systems. To alleviate the contradiction between resource utilization and co-frequency interference in beam hopping technology, this paper firstly studies dynamic clustering to balance traffic between clusters and proposes cluster hopping pool optimization method to avoid inter-cluster interference. Then based on the optimization results, a novel joint beam hopping and precoding algorithm is provided to combine resource allocation and intra-cluster interference suppression, which can make efficient utilization of system resources and achieve reliable and near-optimal transmission capacity. The simulation results show that, compared with traditional methods, the proposed algorithms can dynamically adjust to balance demand traffic between clusters and meet the service requirements of each beam, also eliminate the co-channel interference to improve the performance of satellite network.

We study the physical-layer security of a cognitive radio system in the face of multiple eavesdroppers (EDs), which is composed of a secondary base station (SBS), multiple secondary users (SUs) as well as a pair of primary transmitter (PT) and primary receiver (PR), where the SUs first harvest energy from their received radio frequency signals transmitted by the PT and then communicate with the SBS relying on opportunistic scheduling. We consider two specific user scheduling schemes, namely the channel-aware user scheduling (CaUS) and energyaware user scheduling (EaUS). In the CaUS scheme, an SU having the best instantaneous SU-SBS link (spanning from SUs to SBS) will be activated to communicate with the SBS. By contrast, the EHbUS scheme takes into account both the amount of energy harvested from the PT and the instantaneous quality of the SU-SBS link. We analyze the security-reliability tradeoff (SRT) of both the CaUS and of the EaUS schemes in terms of their intercept vs outage probability. We also provide the SRT analysis of traditional round-robin user scheduling (RrUS) used as a benchmarker of the CaUS and EaUS schemes. We demonstrate that the EaUS scheme achieves the best outage and secrecy performance in the high main-to-eavesdropper ratio (MER) region, but a worse secrecy performance than the CaUS method in the low-MER region. Moreover, from a security vs reliability perspective, the CaUS outperforms both the EaUS and the RrUS in the low-MER region. Surprisingly, this also implies that although the user scheduling criterion of EaUS exploits the knowledge of both the amount of harvested power and instantaneous channel state information (CSI), it exhibits a degraded physical-layer security in the low-MER region, due to the increased harvested energy is beneficial not only for the legitimate SBS receiver, but also for the EDs.

We investigate a satellites-based spectrum sensing system in the presence of low signal-to-noise ratio (SNR) conditions. Such a low SNR is also called SNR wall in the energy detection (ED) method. To eliminate the SNR-wall effect, we propose a combined convolutional neural network and long short-term memory (C-CNN-LSTM) aided spectrum-sensing scheme. Specifically, the CNN and the LSTM are concurrently utilized, where the CNN extracts relationships among spectrum-sensing data (SSD) received at different satellites, and the LSTM excavates time-domain relationships among SSD from one satellite. Then, the outputs of the CNN and the LSTM will be combined. Performance evaluations indicate that the C-CNN-LSTM outperforms the CNN and the ED methods in terms of a higher probability of correct detection ( $P_{d}$ ) and a lower probability of false alarm ( $P_{f}$ ). Moreover, the C-CNN-LSTM can achieve a bit better $P_{d}$ versus $P_{f}$ than that of the cooperative detection DetectNets, which requires multiple DetectNets deployed on multiple sensing nodes, and is used for comparison purposes. These beneficial results demonstrate the superiority of the C-CNN-LSTM in terms of a lower implementation and computational complexity having a high $P_{d}$ and a low $P_{f}$ .

Although fingerprint-based methods could achieve high location accuracy for device-free indoor localization, it requires cost-expensive massive labeling. In order to fully exploit the previously collected CSI fingerprints for various indoor localization tasks, this letter proposes a meta-learning approach for indoor localization, with which an excellent initialization solution for a new localization task is resorted and further training with a few labeled samples results in sound performance improvement over the state-of-the-art deep learning (DL) approach. By recognizing the unequal contribution of an individual training task to the target task, a novel weighted loss is introduced under the framework of meta-learning. Experiments show that the proposed meta-learning approach can gain improvement of 20% Root-Mean-Square-Error (RMSE) enhancement over the DL approach.