Accurate indoor localization information of the quadrotor plays an important role in many Internet of Things applications. To improve the estimation accuracy and robustness, a fix-lag extended finite impulse response smoother (FEFIRS) algorithm is proposed for fusing the inertial navigation system (INS) and ultra wide band (UWB) data tightly, which employs distance between the UWB reference nodes and a blind node measured by the INS and UWB. The FEFIRS algorithm consists of an extended unbiased finite impulse response (EFIR) filter and a fix-lag unbiased FIR (UFIR) smoother. The EFIR filter is employed to improve the robustness, and the fix-lag UFIR smoother is capable of improving the accuracy. Based on extensive test investigations employing real data, the proposed FEFIRS has a higher accuracy and robustness than the Kalman-based solutions in tightly integrated INS/UWB-based indoor quadrotor localization.

When regarding the inherent uncertainty of \nobreak differentiated services requirements as well as the non-uniform spatial distribution of capacity requests, it is essential to \nobreak flexibility adjust resources of the satellite to satisfy the different conditions. How to match the system capacity demand with efficient \nobreak utilization of beam is a brand-new challenge. The convention beam hopping methods ignores the intrinsic correlation between decisions, do not consider the long-term reward, and only achieve the optimal solution at the current time. Therefore, system complexity increases significantly as the increase of the demand for differentiated services or beam number. This paper investigates the optimal policy for beam hopping in DVB-S2X satellite with multiple purposes of assuring the fairness of each beam services, minimizing the delay of real-time services transmission, and maximizing the throughput of non-instant services transmission. Since wireless channel conditions, differentiated services arrival rates have stochastic properties, and the multi-beam satellite environment's dynamics are unknown, the model-free multi-objective deep reinforcement learning approach is used to learn the optimal policy through interactions with the situation. To solve the problem with action dimensional disaster, a novel multi-action selection method based on a Double-Loop Learning (DLL) is proposed. Moreover, the multi-dimensional state is reformulated and obtained by the deep neural network. Under realistic conditions achieving evaluation results demonstrate that the proposed method can pursue multiple objectives simultaneously, and it can also allocate resource intelligently adapting to the user requirements and channel conditions.

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.

Dynamic resource allocation (DRA) is the key technology to improve the network performance in resource-limited multibeam satellite (MBS) systems. The aim is to find a policy that maximizes the expected long-term resource utilization. Existing iterative metaheuristics DRA optimization algorithms are not practical due to the high computational complexity. To solve the problem of unknown dynamics and prohibitive computation, a deep reinforcement learning-based framework (DRLF) is proposed for DRA problems in MBS systems. A novel image-like tensor reformulation on the system environments is adopted to extract traffic spatial and temporal features. A use case of dynamic channel allocation in DRLF is simulated and shows the effectiveness of the proposed DRLF in time-varying scenarios.

Centralized radio resource management method puts all of the computational burdens in an agent, which is unbearable with the increasing of data dimensionality. This paper focuses on how to schedule limited satellite-based radio resources efficiently to enhance transmission efficiency and extend broadband coverage with low complexity. We propose a cooperative multi-agent deep reinforcement learning (CMDRL) framework to achieve the radio resources management strategy. The bandwidth allocation problem is taken as an example to analyze the proposed novel method in simulation. The experimental results show that this approach is capable of enhancing transmission efficiency and be flexible to achieve the desired goal with low complexity.