2025/1

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 15
  • Item
    Intelligent Layout and Optimization of EV Charging Stations: Initial Configuration via Enhanced K-Means and Subsequent Refinement through Integrated GCN
    (Radioengineering Society, 2025-04) Yang, H.; Liu, M.; Zou, J.; Xu, R.; Huang, J.; Geng, P.
    This paper proposes an optimization model for the layout of EV charging stations, aiming to ensure a wide and efficient service area to meet the increasing demand for charging. Through an in-depth study of the deployment optimization of EV charging stations, a layout algorithm based on K-Means and simulated annealing is first introduced to determine the optimal locations for new charging stations. Building on this, a layout optimization algorithm utilizing a Residual Attention Graph Convolutional Network (RAGCN) is proposed, which leverages the efficient learning capability of Graph Convolutional Networks (GCN) on graph-structured data to learn and obtain the best layout for charging stations. Finally, the effectiveness of the model is validated in Nanjing, Jiangsu Province. The results show that the optimized layout of charging stations, which added 493 new stations in high-demand areas such as business districts and corporate enterprises, significantly enhances the convenience and utilization rate of charging for EV users. Additionally, sensitivity analysis and ablation experiments based on Points of Interest (POI) data are conducted to evaluate the impact of various POI features on the layout of charging stations and to explore the contribution of different model components to classification performance.
  • Item
    Enhanced Reliability Assessment in Distribution Network Planning via Optimal Double Q Strategy with Explicit Topology-Variable Consideration
    (Radioengineering Society, 2025-04) Jiang, J.; Luo, Q.; Xu, Z.; Li, H.; Gao, C.
    In the planning of distribution networks, assessing reliability is essential for enhancing network design and selection. This research introduces a new distribution network planning model that aims to balance economic performance and system reliability through a double Q strategy. The model integrates important reliability assessment metrics with the optimized design of the distribution network's topology. To address the computational difficulties associated with traditional power flow calculations in complex network configurations, this study employs a linearized power flow method, which enhances the model's practicality and adaptability. Additionally, recognizing the discrete decision-making aspects of the planning issue, a mixed-integer linear programming model is developed. By utilizing the adaptive ε-constraint method, the study investigates the global Pareto frontier between reliability and cost, offering valuable decision-making support for planners. Results from case studies demonstrate that the proposed method effectively lowers the overall construction and operational costs of the distribution network, albeit with a minor reduction in system reliability.
  • Item
    Binary Quasi-differential Stochastic Process Keying Modulation Scheme for Covert Communications
    (Radioengineering Society, 2025-04) Xu, Z. J.; Zhang, S.; Liu, Z. W.; Lin, J. L.; Huang, X. S.; Gong, Y.
    Covert communication working at the physical layer provides an important means for ensuring the security of private user data. This work proposes a novel covert communication system based on binary quasi-differential stochastic process keying (BQDSPK). At the transmitter, the polarity of the correlation coefficient of two consecutive stochastic sequences is modulated by one binary covert bit. At the receiver, the correlation between two consecutively received random sequences is computed, and the transmitted covert bit is inferred through a hard decision process. A pseudo-random sequence is introduced to eliminate the transmitted sequences' correlation. The transmitted signal has the same statistical characteristics as the ambient noise to avoid attracting the attention of eavesdroppers. We theoretically demonstrate that the proposed system fully satisfies the requirement of covert communication when the signal-to-noise ratio (SNR) is less than a certain threshold value. In addition, theoretical bit error rate (BER) expressions are derived under additive white Gaussian noise (AWGN) channels and frequency-flat fading channels. The simulation results show that the theoretical BERs are very close to the BERs obtained from the simulations, regardless of which stochastic process is used as the carrier. Specifically, when the number of samples within a bit period is 400, the BER approaches approximately 10^-5 at a SNR of -5 dB under an AWGN channel, which adequately satisfies the communication requirements.
  • Item
    Youth Depression Diagnosis Algorithm Based on 3D-WGMobileNet and Transfer Learning
    (Radioengineering Society, 2025-04) Wang, Y.; Guo, Z. H.; Sun, K.; Xiao, H. B.; Wang, W. M.
    Depression is a common mental illness that not only profoundly infests the psychological state of patients, but also tends to cause damage to the functioning of patients' brain areas. To construct a comprehensive and detailed framework for a supporting diagnostic network that will help physicians make accurate and timely diagnoses when dealing with patients at different stages of depression, a network model based on three-dimensional (3D) weight group MobileNet (3D-WGMobileNet) and transfer learningis proposed. Firstly, fMRI data is preprocessed, and regional homogeneity analysis is used to reduce the dimension of the image. Then, the characteristics of Alzheimer's disease are learned by transfer learning and transferred to the proposed model. Next, the dynamic group convolution was used to construct the expert weight matrix of the convolution kernel, and the sliding window group convolution was used to compress the parameters of the model to improve the expression ability and computing power of the model. By using 5-fold cross-validation, we conducted experiments using data from HCP and REST-meta-MDD. The experiment results show that the proposed model gives a superior performance compared with other state-of-the-art methods, especially on the classification of the healthy group with major depression groups, where the two datasets achieve 88% and 91% accuracy, respectively, which verifies the feasibility and effectiveness of our model.
  • Item
    A Wide-band High-performance Voltage-controlled Oscillator for 5G IoT Wireless Communication
    (Radioengineering Society, 2025-04) Wang, J.; Luo, Y.; Zhang, J.; Hou, L.; Wang, J.; Liu, B.
    A low phase noise and power-efficient class-B/C hybrid voltage-controlled oscillator (VCO) is presented for applying to 5G Internet of Things (IoT) wireless communication in this paper. The proposed three sets of switch capacitor array (SCA) are adopted first to widen the bandwidth by dividing the VCO output into eight overlapped frequency bands while maintaining the flexible frequency tuning. Then a multiple bias variable capacitor array (VCA) is designed to realize the fine-grain tuning of output frequency, which also improves the linearity within frequency-voltage tuning, the curvature variation in tunable gain, while minimizes the phase noise and stabilize tuning control on output frequency. After circuit implementation based on 180nm/1.2V CMOS standard process, the post-layout simulation results demonstrate that the proposed VCO achieves a wide frequency output from 4.63 GHz to 5.13 GHz, with consuming a total consumption of 0.19 mW at 1.2 V power supply voltage. The key phase noise is -115.1 dBc/Hz@1MHz on the 4.82 GHz center frequency, and the figure of merit (FoM) value can reach up to -195.6 dBc/Hz, which can surpass the performance to comparable similar class VCO design cases.