With the commercial deployment of low earth orbit (LEO) satellites, the future integrated 6G-satellite system represents an excellent solution for ubiquitous connectivity and high-throughput data service to massive users. Due to the heterogeneity of users’ traffic profiles, uneven traffic distribution among beams or users often occurs in LEO satellite systems. Conventional satellite payloads with fixed beam radiation patterns may result in large gaps between requested and allocated capacity. The advances of flexible satellite payloads with dynamic beamforming capabilities enable spot beams to adjust their coverage and adaptively schedule users, thus offering spatial-temporal domain flexibility. Motivated by this, as an early attempt, we investigate how adaptive beam patterns with flexible user scheduling schemes can help alleviate mismatches of requested-transmitted data in uneven-traffic and full-frequency reuse LEO systems. We formulate an optimization problem to jointly determine beam patterns, power allocation, user-LEO association, and user-slot scheduling. The problem is identified as mixed-integer nonconvex programming. We propose an efficient iterative algorithm to solve the problem by first determining beam patterns and user associations at the frame scale, followed by optimizing power allocation and user scheduling at the timeslot scale. The four-decision components are iteratively updated to improve the overall performance. Numerical results demonstrate the benefits brought by adaptive beam patterns and their effectiveness in reducing the mismatch effect in uneven-traffic LEO systems.

The low earth orbit (LEO) satellite system is one of the promising solutions to provide broadband services to a wide-coverage area for future integrated LEO-6G networks, where users' demands vary with time and geographical locations. Conventional satellites with fixed beam pattern and footprint planning may not be capable of meeting such dynamic requests and irregular traffic distributions. As the development of flexible satellite payload with beamforming capabilities, spot beams with flexible size and shape are considered potential solutions to this issue. As an early investigation, in this paper, we consider the scenarios where satellite payloads are equipped with multiple beam patterns and study the optimal beam pattern selection. We exploit the potential synergies of joint resource optimization between adaptive beam patterns and non-orthogonal multiple access (NOMA) in a LEO satellite system, where NOMA is employed to reduce intra-beam interference and flexible beam pattern is adopted to mitigate inter-satellite interference. The formulated problem is to minimize the capacity-demand gap of terminals, which falls into mixed-integer nonconvex pro-gramming (MINCP). To tackle the discrete variables and non-convexity, we design a joint approach to allocate power and select beam patterns. Numerical results show that the proposed scheme achieves capacity-demand gap reduction of 37.8% over conventional orthogonal multiple access (OMA) and 42.5% over the fixed-beam-pattern scheme.

The ground traffic demand of multi-beam satellites is growing rapidly, but resources such as satellite power and bandwidth are limited. Beam hopping (BH) alleviates the problem of insuffident satellite transmitters, but how to improve the utilization of limited resources to increase satellite throughput is still a challenge in the future. In this paper, starting from beam hopping, the bandwidth allocation in beam hopping systems is analyzed first. The results show that the effect of full frequency reuse works better than that of partial frequency reuse in the beam hopping system with fewer beams, but the former can reduce the complexity of problems. Afterwards, a deep reinforcement learning strategy combining power allocation and beam hopping (PABH) is proposed, which improves power utilization and satellite throughput to a certain extent, which proves that power allocation is feasible.

The inertial navigation system (INS) has been widely used to provide self-contained and continuous motion estimation in intelligent transportation systems. Recently, the emergence of chip-level inertial sensors has expanded the relevant applications from positioning, navigation, and mobile mapping to location-based services, unmanned systems, and transportation big data. Meanwhile, benefit from the emergence of big data and the improvement of algorithms and computing power, machine learning (ML) has become a consensus tool that has been successfully applied in various fields. This article reviews the research on using ML technology to enhance inertial sensing from various aspects, including sensor design and selection, calibration and error modeling, navigation and motion-sensing algorithms, multi-sensor information fusion, system evaluation, and practical application. It summarizes the state of the art, advantages, and challenges on each aspect, and points out future research directions.

Power amplifier (PA) models, such as the neural network (NN) models and the multilayer NN models, have problems with high complexity. In this article, we first propose a novel behavior model for wideband PAs, using a real-valued time-delay convolutional NN (RVTDCNN). The input data of the model is sorted and arranged as a graph composed of the in-phase and quadrature ( I/Q ) components and envelope-dependent terms of current and past signals. Then, we created a predesigned filter using the convolutional layer to extract the basis functions required for the PA forward or reverse modeling. Finally, the generated rich basis functions are input into a simple, fully connected layer to build the model. Due to the weight sharing characteristics of the convolutional model's structure, the strong memory effect does not lead to a significant increase in the complexity of the model. Meanwhile, the extraction effect of the predesigned filter also reduces the training complexity of the model. The experimental results show that the performance of the RVTDCNN model is almost the same as the NN models and the multilayer NN models. Meanwhile, compared with the abovementioned models, the coefficient number and computational complexity of the RVTDCNN model are significantly reduced. This advantage is noticeable when the memory effects of the PA are increased by using wider signal bandwidths.

With the rapid development of 5G mobile communication and intelligent vehicles, efficient and reliable vehicle-to-vehicle communication is recognized as one of the key technologies for the next generation of wireless networks in the future. Due to the rapid changes in the wireless channel due to the high mobility of vehicles, the traditional resource allocation technology is no longer suitable for the current vehicle network. This paper proposes a joint resource allocation method for the internet of vehicles communication based on the proximal policy optimization algorithm. In this paper, a joint optimization scheme of discrete and continuous resources suitable for the internet of vehicles communication is designed to effectively meet the strict requirements of vehicle-mounted communication. Simulation results show that the proposed allocation method can maximize the system capacity and satisfy the delay constraints of vehicle-to-vehicle communication.

Localization techniques are becoming key to add location context to the Internet-of-Things (IoT) data without human perception and intervention. Meanwhile, the newly emerged low-power wide-area network (LPWAN) and 5G technologies have become strong candidates for mass-market localization applications. However, various error sources have limited localization performance by using such IoT signals. This article reviews the IoT localization system through the following sequence: IoT localization system review, localization data sources, localization algorithms, localization error sources and mitigation, and localization performance evaluation. Compared to the related surveys, this article has a more comprehensive and state-of-the-art review on IoT localization methods, an original review on IoT localization error sources and mitigation, an original review on IoT localization performance evaluation, and a more comprehensive review of IoT localization applications, opportunities, and challenges. Thus, this survey provides comprehensive guidance for peers who are interested in enabling localization ability in the existing IoT systems, using IoT systems for localization, or integrating IoT signals with the existing localization sensors.

Orthogonal frequency division multiplexing (OFDM) is extensively applied in the downlink of narrowband Internet of Things (NB‐IoT). However, the high peak‐to‐average power ratio (PAPR) of OFDM systems leads to a decrease in transmitter efficiency. Therefore, the researchers proposed the artificial neural network (ANN) based PAPR reduction schemes. However, these schemes have the disadvantages of high complexity or cannot overcome the defects of traditional schemes. In this paper, a novel PAPR reduction scheme based on neural networks (NNs) is proposed for OFDM systems. This scheme establishes a PAPR reduction module based on NN, which is trained using the low PAPR data obtained by the simplified clipping and filtering (SCF) method. To overcome the defect of poor BER performance of the SCF scheme, a recovery module is introduced at the receiver, to recover the distorted signal. To realize the improvement of BER performance and the reduction of PAPR simultaneously, the two modules are jointly trained based on multiobjective optimization. Experimental results based on a 100 MHz OFDM signal show that this scheme can reduce PAPR by 4.5 dB. Meanwhile, the BER of this scheme can be reduced to 0.001 times that of the SCF scheme.

Location is key to spatialize Internet of Things (IoT) data. However, it is challenging to use low-cost IoT devices for robust unsupervised localization (i.e., localization without training data that have known location labels). Thus, this article proposes a deep-reinforcement-learning (DRL)-based unsupervised wireless-localization method. The main contributions are as follows: 1) this article proposes an approach to model a continuous wireless-localization process as a Markov decision process and process it within a DRL framework; 2) to alleviate the challenge of obtaining rewards when using unlabeled data (e.g., daily life crowdsourced data), this article presents a reward-setting mechanism, which extracts robust landmark data from unlabeled wireless received signal strengths (RSS); and 3) to ease requirements for model retraining when using DRL for localization, this article uses RSS measurements together with agent location to construct DRL inputs. The proposed method is tested by using field testing data from multiple Bluetooth 5 smart ear tags in a pasture. Meanwhile, the experimental verification process reflects the advantages and challenges for using DRL in wireless localization.

In this paper, a low-feedback-sampling-rate digital predistortion (DPD) method is proposed for wideband wireless transmitters and radio-frequency power amplifiers (PAs). This DPD method inserts a non-ideal real band-pass filter into the feedback loop to limit the feedback bandwidth. Meanwhile, to recover the band-limited feedback signal, it introduces a signal-recovery module that is based on the deep neural network (DNN). A data-preprocessing technique is proposed to reduce the amount of input data for the DNN and thereby significantly reducing its structural complexity. Also, the use of DNN makes it feasible to implement off-line training. Both the simplicity of the proposed DNN and the availability of off-line training reduce the system complexity in DPD. Experimental validation was performed on a PA driven by wideband orthogonal-frequency-division-multiplexing (OFDM) signals. The results demonstrated the superiority of the proposed method in under-sampling applications. The proposed DPD method achieved the same linearization performance as the state-of-art DPD methods while requiring a sampling rate that was approximately 5% less. Meanwhile, the proposed DPD method has been validated to have stronger anti-noise and generalization capabilities.

Beam hopping (BH) is the key technology to improve the system throughput and decrease the transmission delay in multibeam satellite systems. The objective of this study is to find a policy to maximise the expected long‐term resource utilisation. The BH illumination plan (BHIP) optimisation problem aimed at minimising the transmission delay is formulated and modelled as a partially observable Markov decision process. To tackle the issue of unknown dynamics and prohibitive computation, an artificial intelligence method named deep reinforcement learning (DRL) is first proposed to solve the BHIP problem in multibeam satellite systems. The proposed DRL‐BHIP algorithm considers a series of realistic conditions, including the traffic demands in spatial distribution and temporal variation, ModCod constraints, antenna radiation pattern and inter‐beam interference. The state reformulation concept is adopted to characterise the traffic spatial and temporal features. Simulation results show that the proposed DRL‐BHIP algorithm can decrease the transmission delay and improve the system throughput compared with existing algorithms.