Yawen Zheng

Yawen Zheng

Auto-generated profile, based on publicly available information

Yawen Zheng

China Southern Power Grid Co., Ltd., Guangzhou 510663, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 January 2026 in Energies
Verified
Journal Article
Open access
PDF file
RYRuotian Yao
Ruotian Yao
BHBai Hao
Bai Hao
SJShiqi Jiang
Shiqi Jiang
TLTong Liu
Tong Liu
YLYiyong Lei
Yiyong Lei
YZYawen Zheng
Yawen Zheng
Accurate localization of voltage sag sources is crucial for maintaining reliable and stable operation in microgrids with high penetration of distributed generation (DG). However, the complex topology, bidirectional and time-varying power flows, and measurement uncertainty make it difficult for these conventional model-based approaches to achieve high accuracy. To address these challenges, this paper proposes a two-stage voltage sag source localization method that integrates a data-driven spatio-temporal learning model with a model-based binary search refinement. In the first stage, an improved spatial-temporal graph convolutional network (STGCN) is developed to extract temporal and spatial correlations among voltage and current measurements, enabling section-level localization of sag sources. In the second stage, a binary search–based refinement strategy is applied within the candidate section to iteratively converge on the exact fault location with high precision and robustness. Simulations are conducted on a modified IEEE 33-node system with diverse PV output scenarios, covering combinations of fault types and locations. The results demonstrate that the proposed method maintains stable localization performance under high DG penetration and achieves high accuracy despite multiple fault types and noise interference.

7 March 2026 in Energies
Verified
Journal Article
Open access
PDF file
BHBai Hao
Bai Hao
YLYipeng Liu
Yipeng Liu
YZYawen Zheng
Yawen Zheng
MDMing Dong
Ming Dong
QDQiaoyi Ding
Qiaoyi Ding
HWHao Wang
Hao Wang
The frequency of extreme weather events has become higher, and electricity consumption has also become more complex. These changes increase the risk of overload in distribution transformers (DTs), and this risk threatens the stability and reliability of the power grid. Existing methods have significant limitations. Traditional static threshold methods (based on DGA gas ratios and electrical signal thresholds) fail to consider temporal changes and complex links between factors, while modern machine learning models lack cause–effect relationships over time and clear ways to describe uncertainty. With such motivations, this paper proposes a causal-enhanced hybrid framework, which combines Long Short-Term Memory (LSTM) networks and Random Forest (RF) algorithms. The framework uses causal Seasonal Trend decomposition using Loess (STL) to reveal load patterns at different time scales. The mutual information index and spatiotemporal graph convolutional network (ST-GCN) are used to explore nonlinear relations and reveal how temperature affects load changes. The LSTM model captures time dependence in load series, and the Bayesian optimized Random Forest is used to solve the problem of data imbalance and quantify uncertainty. In addition, the framework constructs an early warning system that combines data from many sources in real time. Test results show that the proposed algorithm exhibits excellent performance in multi-source data environments.

8 November 2025 in Energies
Verified
Journal Article
Open access
PDF file
BHBai Hao
Bai Hao
RYRuotian Yao
Ruotian Yao
TLTong Liu
Tong Liu
YLYiyong Lei
Yiyong Lei
YZYawen Zheng
Yawen Zheng
To address the problem of uncoordinated operation between distributed generation (DG) inverters and dedicated power quality devices, this paper proposes a coordinated optimization model for harmonic and voltage compensation in microgrids. The model considers the capacity constraints of DG inverters and compensation devices, aiming to realize efficient utilization of multi-resource compensation capabilities. A dual-objective optimization framework is established, which simultaneously minimizes total economic cost and enhances overall power quality performance. The first objective function reflects investment and operational costs, while the second quantifies system performance through total harmonic distortion (THD) and average voltage deviation (AVD). The Normal–Normal Constraint (NNC) method is adopted to ensure optimization stability and feasible trade-offs between the two objectives. The proposed approach is validated on the IEEE 33-bus microgrid system, and its results are compared with traditional heuristic algorithms such as PSO. Simulation results show that the proposed method effectively reduces total operating cost while significantly improving harmonic and voltage compensation performance. This study provides a practical reference for coordinated power quality management in microgrids.

12 January 2026 in Energies
Verified
Journal Article
Open access
PDF file
BHBai Hao
Bai Hao
RYRuotian Yao
Ruotian Yao
TLTong Liu
Tong Liu
ZMZiji Ma
Ziji Ma
SLShangyu Liu
Shangyu Liu
YZYawen Zheng
Yawen Zheng
To address the dual demands of accuracy and real-time performance in power quality disturbance (PQD) recognition for new power system, this paper proposes a lightweight model named the Cross-Channel Attention Three-Layer Convolutional Model (1D-CCANet-3), specifically designed for edge deployment. Based on the one-dimensional convolutional neural network (1D-CNN), the model features an ultra-compact architecture with only three convolutional layers and one fully connected layer. By incorporating a set of cross-channel attention (CCA) mechanisms in the final convolutional layer, the model further enhances disturbance recognition accuracy. Compared to other deep learning models, 1D-CCANet-3 significantly reduces computational and storage requirements for edge devices while achieving accurate and efficient PQD recognition. The model demonstrates robust performance in recognizing 10 types of PQD under varying signal-to-noise ratio (SNR) conditions. Furthermore, the model has been successfully deployed on the FPGA platform and exhibits high recognition accuracy and efficiency in real-world data validation. This work provides a feasible and effective solution for accurate and real-time PQD monitoring on edge devices in new power systems.

13 January 2026 in Electronics
Verified
Journal Article
Open access
PDF file
SCShiran Cao
Shiran Cao
RYRuotian Yao
Ruotian Yao
WSWeihao Shuai
Weihao Shuai
BHBai Hao
Bai Hao
SJShiqi Jiang
Shiqi Jiang
YZYawen Zheng
Yawen Zheng
Microgrids are commonly connected through medium-voltage cables in coastal distribution networks and other microgrids. However, a faulted microgrid may increase the collapse risk if the supporting microgrids are disconnected due to voltage sags. Conventional voltage support methods, which primarily rely on the impedance characteristics of the transmission line, typically regulate the active-to-reactive current ratio (hereafter referred to as “current ratio”) to maximize positive sequence voltage while minimizing negative sequence voltage. Nevertheless, the distributed capacitance inherent in cables induces deviations in both the amplitude and phase of the transmitted current, while simultaneously intensifying the coupling between voltage and current. These effects complicate the voltage fluctuation behavior and impair the effectiveness of voltage support, thereby increasing the risk of disconnection and collapse for the faulted microgrid (hereafter referred to as “fault region”). To address this challenge, this study focuses on non-faulted microgrids (hereafter referred to as “microgrids”), proposing a method for active current correction and transient voltage support that considers the influence of cable distributed capacitance. By analyzing the voltage and current characteristics on both ends of the interconnecting cables, the method optimizes the current injection ratio. It mitigates deviation caused by cable capacitance effects, thereby enhancing the voltage support performance of the microgrid. Notably, the proposed method operates independently of real-time voltage and current measurements from the fault region, significantly reducing communication demands. Experimental results based on a practical microgrid validate the effectiveness of the proposed method, demonstrating a 27.9% improvement in voltage support performance compared to conventional methods.