Device-to-device (D2D) communications are envisioned as a critical technology to support future ubiquitous mobile communications applications. However, the requirements of high mobility and low latency seriously constrain the performance improvement of D2D communications. In this letter, we investigate a deep reinforcement learning (DRL) based scheme of power and resource allocation for maximizing the throughput of D2D users (DUEs) and cellular users (CUEs). Based on DRL theory, D2D pairs are defined as distributed multiple agents, which aim to adaptively select the transmission power and resources to ease the co-channel interference without any prior information. Furthermore, a priority sampling based dueling double deep Q-network (PS-D3QN) distributed algorithm is proposed to help agents to learn the predominant features. Simulation results show that the proposed algorithm has higher throughput than the existing DRL algorithms with a strict delay constraint. Particularly, the probability that the agent selects high power decreases with the increase of remaining transmission time, which proves the agents effectively learn and dynamically sense the impacts of the delay constraint.
This letter investigates a deep reinforcement learning (DRL)-based spectrum access scheme for device-to-device (D2D) communication underlay cellular networks. Specifically, cellular users (CUEs) and D2D pairs attempt to access the time slots (TSs) of a shared spectrum, and TSs are dynamically scheduled to CUEs in different frames. Based on the DRL theory, D2D pairs can be seen as a centralized agent which aims to learn an optimal spectrum access strategy to maximize the sum throughput without any prior information. In particular, with different locations of CUEs, the spectrum access manners for D2D communication are changed to ensure the communication quality of CUEs at the cell edge. Then, a double deep Q-network (DDQN) based D2D spectrum access (D 4 SA) algorithm is proposed, which makes D2D pairs learn to decide whether to access the spectrum in different TSs. Moreover, to ensure the fairness of resource allocation among D2D pairs, we improve the proposed algorithm and incorporate fairness into the objective function. Simulation results show that our proposed algorithm can achieve an optimal sum throughput close to the theoretical upper bound, where the performance is significantly improved compared to the scheme based on base station cooperation.
F–TiO2 was prepared by a simple precipitation method using titanium sulfate as the titanium source, hydrogen fluoride as the fluorine source and ammonia as the precipitant. CdS/F–TiO2 composites were prepared by hydrothermal synthesis of CdS and F–TiO2. The surface morphology, crystal phase composition, ultraviolet absorption band, fluorescence intensity, element composition, valence state, specific surface and pore structure of the samples were characterized by using field emission scanning electron microscopy (FESEM), X-ray diffraction (XRD), ultraviolet visible absorption spectrum (UV-Vis-Abs), Molecular fluorescence spectrophotometer (PL) and X-Ray photoelectron spectroscopy (XPS) and Surface area analyzer (BET), respectively. The effects of the dosage of the photocatalyst, pH value, the concentration of methyl orange and the addition of H2O2 on the photocatalytic performance were investigated with methyl orange solution as the target degradation product. The results showed the optimum condition for photodegradation of methyl orange by 1% CdS/F–TiO2 is that the pH value, the solid-liquid ratio, the concentration of methyl orange and the dosage of H2O2 is 2, 2 g/L, 10 mg/L and 3%, respectively. Under the same conditions, the degradation rate of methyl orange by 1% CdS/F–TiO2 was 93.36% when 300 W metal halide lamp was irradiated for 20 minutes, which was significantly higher than that of F–TiO2. CdS has a significant effect on the morphology, crystallinity, grain size and the compound probability of electrons and holes after the F–TiO2 modification. The composite causes a significant red shift at the edge of the F–TiO2 light absorption band. The photocatalytic degradation of methyl orange by 1% CdS/F–TiO2 follows the Langmuir-Hinshelwood first-order kinetic model.
3 April 2023 in IEEE Wireless Communications Letters
Channel estimation (CE) is a critical part for intelligent reflecting surface (IRS) aided multi-user communication (MUC) systems. However, the cascaded channel of the IRS-aided MUC (IRS-MUC) is a complex multi-dimensional channel, which is difficult to estimate the precise channel matrix in practice. In this letter, we propose a dilated convolution and self-attention based neural network (DCSaNet) to handle the CE in the IRS-MUC system. Specifically, the dilated convolution block is used to improve the feature extraction for CE during the network training. Further, the weighed features are obtained by the self-attention block. Last, a lightweight model, DCSaNet-l is applied to reduce the network parameters for the practical IRS deployment. Experimental results show that the proposed DCSaNet can significantly lower the normalized mean square error (NMSE), accelerate the training speed under different SNR cases and different channel dimensions. The results also verify that the lightweight DCSaNet-l can reach a near optimal performance of the proposed DCSaNet, but further significantly reduce the parameter amount by more than 83.7%.
8 May 2023 in Biomechanics and Modeling in Mechanobiology
Channel state information (CSI) is a critical part for massive multiple-input multiple-output (MIMO) system. However, it is a big challenge to send a large amount of CSI from the receiver to the transmitter with limited channel resources. In this letter, we propose asymmetric convolution-based autoencoder framework (ACCsiNet) to handle the CSI compression and decompression problem. Specifically, asymmetric convolution block (AC-Block) is used to enhance the feature extraction ability of convolution. Further, a lightweight method is applied, which can greatly reduce the storage space at the receiver. Considering the practical deployment, multi-model fusion schemes including multi-rate and multi-scenario fusion are also discussed to strengthen the generalization ability of the network. Experimental results show that the proposed ACCsiNet can improve the NMSE and cosine similarity $\rho $ performance, especially for outdoor scenario. The results also verify that both the lightweight and multi-model fusion schemes can reach a near-optimal performance of the proposed ACCsiNet, but further significantly reduce the parameter amount by more than 83% and 90%, respectively.