Changyong Pan

The rapid development of mobile communication services in recent years has resulted in a scarcity of spectrum resources. This paper addresses the problem of multi-dimensional resource allocation in cognitive radio systems. Deep reinforcement learning (DRL) combines deep learning and reinforcement learning to enable agents to solve complex problems. In this study, we propose a training approach based on DRL to design a strategy for secondary users in the communication system to share the spectrum and control their transmission power. The neural networks are constructed using the Deep Q-Network and Deep Recurrent Q-Network structures. The results of the conducted simulation experiments demonstrate that the proposed method can effectively improve the user’s reward and reduce collisions. In terms of reward, the proposed method outperforms opportunistic multichannel ALOHA by about 10% and about 30% for the single SU scenario and the multi-SU scenario, respectively. Furthermore, we explore the complexity of the algorithm and the influence of parameters in the DRL algorithm on the training.

For reliable synchronization and transmission parameter signalling (TPS) detection, the preamble based on distance detection (PBDD) is adopted in the digital terrestrial television multimedia broadcasting -advanced (DTMB-A) standard. However, the conventional signalling detection methods do not take the channel information into consideration and will undergo severe performance loss over frequency-selective channels, especially those with strong and long delay echos. In this paper, a novel two-stage TPS detection method is proposed based on the preamble for DTMB-A system, which utilizes the channel information to enhance the detection accuracy. After coarse distance evaluation, the equalization will be performed on the possible candidate subcarriers to reconstruct the OFDM signalling block, hence a more reliable correlation statistic can be obtained to achieve more accurate signalling detection. As demonstrated in the simulations, the detection accuracy can be improved remarkably by compensating the impact of the transmission channel compared with the traditional detection schemes, while the increment of the computational complexity is acceptable.

Radio signal recognition has a wide application in future communication systems and the vehicular communication, whose core is the extraction of signal features such as electromagnetic fingerprints. With the rapid development of artificial intelligence technology, deep learning has made amazing breakthroughs in image recognition, speech recognition and other fields. Deep learning is applied to electromagnetic fingerprint extraction in this paper. Firstly, thousands of the downlink aircraft communications addressing and reporting system (ACARS) signals used for communication between civil aircraft and airport tower are collected and generated. Then a pre-transformation network suitable for electromagnetic signals is constructed to convert one-dimensional signals into two-dimensional feature maps, and afterwards the feature maps are input into the convolutional neural network (CNN) for classification. By adopting the attention modules, the classification results were improved by a few percentage points over the baseline with a little cost. The method proposed in this paper achieves an accuracy rate of 94.1% and can obtain the aircraft type in a shorter time than traditional method. Moreover, the robustness of the proposed model in response to additive Gaussian white noise (AWGN) and phase deviation is studied and tested.

Considering high path loss (PL) of the non-line-of-sight (NLOS) ultraviolet communications (UVC) realized by the atmospheric scattering effect of ultraviolet light, we propose to use a reflective plane to improve the received optical power and further reduce the PL. More specifically, a channel model for NLOS UVC with not only scattering but also reflection considered is proposed via Monte-Carlo (MC) photon-tracing method. Both scattering and reflective events are called collision-induced events (CIEs). The proposed channel model can obtain the PL and channel impulse response (CIR) performances of the NLOS UVC system with multiple-order CIEs. It is shown that the reflective plane could reduce the PL and the time delay of CIR, which could be a benefit for designing high data-rate NLOS UVC systems. Finally, experimental results in two representative scenarios are also given to verify the effectiveness of the proposed channel model for reflection-assisted NLOS UVC systems.

Spectrum sensing for the Digital Television Terrestrial Multimedia Broadcasting (DTMB) system is considered in this paper. A novel method, which contains a preprocessing method of partition and averaging, a convolutional neural network (CNN) and a threshold chosen scheme, is proposed to solve this problem. In the spectrum sensing process, the received signal is firstly preprocessed by a scheme of partition and averaging. Then it is fed into the well-trained CNN. The posterior probability of the signal being noise is output. Based on the Neyman-Pearson theorem, a threshold can be chosen by the Monte Carlo method. The result of spectrum sensing can be obtained by comparing the posterior probability with the threshold and the complexity of the proposed method is also analyzed. Through computer simulations, the advantage of the proposed method is demonstrated. At a low signal-to-noise ratio (SNR), the proposed method can achieve a satisfactory detection probability. Besides, the proposed method is robust to different SNRs and has good generalization performance under different noise assumptions. When the proposed method is transferred to sense DTMB signal under time dispersive channels, the performance does not deteriorate and even can be better, which shows the robustness of the proposed method to the time dispersive channels.

Facing the worldwide explosive growth of the wireless devices, the future wireless network is required to provide seamless access for the users with diverse Quality-of-Service (QoS) requirements. In this article, a novel multiple access scheme based on the principle of multidomain index modulation is proposed to address the downlink multiple access problem for users with diverse QoS requirements, including the Internet-of-Things (IoT) devices and the smart electronic devices. Unlike the conventional nonorthogonal multiple access (NOMA) schemes which utilize power-domain diversities to realize multiple access, in the proposed scheme, information for different users is conveyed by different domains of the transmitted signals, including the constellation domain, frequency domain, time domain, and spatial domain. As a result, the intracluster interference among users is alleviated and the successive interference cancellation is avoided to reduce the computational complexity of signal detection at the receiver side, which is well suited for the IoT devices. The closed form lower bounds and approximations of the achievable rate of the proposed scheme are further derived to provide accurate estimation of the achievable rate of the communication system. Simulation results validate the superior performance of the proposed scheme over the conventional orthogonal and NOMA schemes.

Generalized spatial modulation (GenSM) aided millimeter wave (mmWave) multiple-input multiple-output (MIMO) system has been recently considered as a new efficient technique due to the combination of numerous antennas and reduced number of radio frequency (RF) chains. However, the present hybrid precoding schemes for GenSM-aided system are still troubled by high computational complexity and performance loss in spectral efficiency (SE). In this paper we propose low-complexity hybrid precoding schemes based on Martin's expansion for logarithmic determinant (log-det) form in analytical SE lower bound. Digital and analog precoders are herein optimized separately, which means complicated alternating minimization iteration is omitted. Besides, we can adjust algorithmic complexity adaptively corresponding to different demand levels for users. Finally the numerical simulations show that the proposed methods outperform other GenSM-aided mmWave MIMO schemes and can achieve a better tradeoff between complexity and SE.

Mutual interference is a crucial issue for the visible light communication (VLC) systems to be addressed, including both co-channel interference (CCI) and inter-carrier interference (ICI). In this paper, to solve the CCI problem, a novel optical attocell network is introduced, which can be regarded as a hybrid network based on both single frequency network and multi-frequency network. Meanwhile, to eliminate the ICI, a pre-distorted enhanced asymmetrically clipped DC biased optical orthogonal frequency division multiplexing (PEADO-OFDM) approach is designed. In addition, the corresponding properties of PEADO-OFDM are analyzed, and different modulation schemes are employed for downlink and uplink in the same ADO-OFDM modulation framework to reduce the complexity of user processing. Simulation results indicate that the proposed PEADO-OFDM scheme outperforms the conventional ADO-OFDM approach in terms of bit error rate, while the processing latency and computational complexity are greatly reduced at the receiver.

In this paper, we consider a status updating system where the transmitter sends status updates of the signal it monitors to the destination through a rate-limited link. We consider the scenario where the status of the monitored signal only changes at discrete time points. The objective is to let the destination be synchronized with the source in a timely manner once a status change happens. What complicates the problem is that the transmission takes multiple time slots due to the link-rate constraint. Thus, the transmitter has to decide to switch or to skip a new update when the status of the monitored signal changes and it has not completed the transmission of the previous one yet. We adopt a metric called "Age of Synchronization" (AoS) to measure the "dissatisfaction" of the destination when it is desynchronized with the source. Then, the objective of this paper is to minimize the time-average AoS by designing optimal transmission policies for the transmitter. We formulate the problem as a Markov decision process (MDP) and prove the multi-threshold structure of the optimal policy. Based on that, we propose a low computational-complexity algorithm for the MDP value iteration. We then evaluate the performance of the multi-threshold policy through simulations and compare it with two baseline policies and the AoI-optimal policy.