Yihua Zhu

Yihua Zhu

Auto-generated profile, based on publicly available information

Yihua Zhu

Electric Power Research Institute, China Southern Power Grid, Guangzhou 510663, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
15 January 2025 in Electronics
Verified
Journal Article
Open access
PDF file
SWShuaibo Wang
Shuaibo Wang
WLWenhao Luo
Wenhao Luo
SYSixing Yin
Sixing Yin
JZJie Zhang
Jie Zhang
ZLZhuohang Liang
Zhuohang Liang
SLShufang Li
Shufang Li
Power system state estimation is a critical task for ensuring stable grid operation and serves as the foundation of grid control and analysis. Conventional approaches largely involve field measurements, network topology, and manual anomaly detection, which present significant limitations, particularly while dealing with dynamic and complex power systems. In recent years, deep learning techniques have been progressively applied in this field to overcome the shortcomings of conventional approaches, which are based on mathematical models and static analysis. However, existing deep learning techniques primarily focus on power system security analysis and computational resource management. In spite of the powerful capabilities in supervised learning tasks, the lack of interpretability still makes deep learning models less convincing, and thus might hinder their practical applications. In response to this issue, we apply a computational model for power system state estimation based on the Kolmogorov–Arnold network (KAN) model with learnable activation functions, visualization capabilities, and pruning features. From the perspective of feature interpretability, we find the influence of bus features on the model output, such as bus voltage magnitude. Moreover, through analysis of the internal structure of the model, we uncover a possibility of potential mechanisms of power system state estimation. Experimental results show that our study not only enhances the interpretability of power system state estimation but also effectively ensures grid security and stability through state estimation.

3 August 2025 in Information
Verified
Journal Article
Open access
PDF file
MCMin Cheng
Min Cheng
JYJiawei Yu
Jiawei Yu
MWMingkang Wu
Mingkang Wu
YZYihua Zhu
Yihua Zhu
YZYayao Zhang
Yayao Zhang
YZYuanfu Zhu
Yuanfu Zhu
With the increasing uncertainty introduced by the large-scale integration of renewable energy sources, traditional power dispatching methods face significant challenges, including severe frequency fluctuations, substantial forecasting deviations, and the difficulty of balancing economic efficiency with system stability. To address these issues, a deep learning-based dispatching framework is proposed, which integrates spatiotemporal feature extraction with a stability-aware mechanism. A joint forecasting model is constructed using Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to handle multi-source inputs, while a reinforcement learning-based stability-aware scheduler is developed to manage dynamic system responses. In addition, an uncertainty modeling mechanism combining Dropout and Bayesian networks is incorporated to enhance dispatch robustness. Experiments conducted on real-world power grid and renewable generation datasets demonstrate that the proposed forecasting module achieves approximately a 2.1% improvement in accuracy compared with Autoformer and reduces Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) by 18.1% and 14.1%, respectively, compared with traditional LSTM models. The achieved Mean Absolute Percentage Error (MAPE) of 5.82% outperforms all baseline models. In terms of scheduling performance, the proposed method reduces the total operating cost by 5.8% relative to Autoformer, decreases the frequency deviation from 0.158 Hz to 0.129 Hz, and increases the Critical Clearing Time (CCT) to 2.74 s, significantly enhancing dynamic system stability. Ablation studies reveal that removing the uncertainty modeling module increases the frequency deviation to 0.153 Hz and raises operational costs by approximately 6.9%, confirming the critical role of this module in maintaining robustness. Furthermore, under diverse load profiles and meteorological disturbances, the proposed method maintains stable forecasting accuracy and scheduling policy outputs, demonstrating strong generalization capabilities. Overall, the proposed approach achieves a well-balanced performance in terms of forecasting precision, system stability, and economic efficiency in power grids with high renewable energy penetration, indicating substantial potential for practical deployment and further research.

24 November 2020 in Energies
Verified
Journal Article
Open access
PDF file
CLChanggang Li
Changgang Li
Hang zhiHang zhi
Hang zhi
Hengxu ZhangHengxu Zhang
Hengxu Zhang
QGQi Guo
Qi Guo
YZYihua Zhu
Yihua Zhu
VTVladimir Terzija
Vladimir Terzija
Accompanying the continuous increase in wind power penetration, the power system inertia is reduced, and the system frequency regulation performance deteriorates. Wind turbine generators are required to participate in primary frequency regulation (PFR) to support system frequency. Here, the PFR capability of the widely-used doubly-fed induction generator (DFIG) is evaluated to estimate the participation of the DFIG in system frequency control. The frequency regulation model of the DFIG is established and briefly discussed. The equivalent PFR droop coefficient is then deduced from the model using a small signal increment method to evaluate the DFIG’s PFR capability. Key factors affecting the equivalent droop coefficient are studied, and the droop control is optimized to keep the equivalent droop coefficient in the desired range. The proposed method is verified utilizing a provincial power grid model of China.

19 February 2025 in Energies
Verified
Journal Article
Open access
PDF file
SWShuaibo Wang
Shuaibo Wang
JZJie Zeng
Jie Zeng
JZJie Zhang
Jie Zhang
ZLZhuohang Liang
Zhuohang Liang
YZYihua Zhu
Yihua Zhu
SLShufang Li
Shufang Li
This paper addresses the challenge of achieving fast and accurate transient stability analysis and emergency control in power systems, which are crucial for reliable grid operation under disturbances. To this end, we propose a spatio-temporal graph deep learning approach leveraging Diffusion Convolutional Gated Recurrent Units (DCGRUs) for transient stability assessment and coherent generator group prediction. Unlike traditional methods, our approach explicitly represents transient responses as spatio-temporal graph data, capturing both topological and dynamic dependencies. The DCGRU model effectively extracts these features, and the predicted coherent generator groups are incorporated into the single-machine infinite-bus equivalence method to design an emergency generator tripping scheme. Simulation analysis results on both benchmark and real-world power grids validate the proposed method’s feasibility and effectiveness in enhancing transient stability analysis and emergency control.

12 October 2024 in Energies
Verified
Journal Article
Open access
PDF file
XCXipeng Cai
Xipeng Cai
YLYixin Liu
Yixin Liu
YZYihua Zhu
Yihua Zhu
YZYanbing Zhou
Yanbing Zhou
CLChao Luo
Chao Luo
QLQihui Liu
Qihui Liu
This study offers a modular isolated grid-connected DC/DC medium-voltage DC aggregation converter to support offshore full DC wind farms’ need for lightweight and highly efficient power aggregation and transmission. The converter can simultaneously have a smaller transformer size and lower switching frequency during operation through the dual-voltage stabilization three-loop control strategy and phase-shift modulation strategy, which greatly reduces the space occupied by the converter and lowers the switching loss, Additionally, the use of a two-level structure at a lower switching frequency has lower loss, which effectively reduces the cost of the power device compared with the commonly used three-level converter. The input series output series connection between the converter sub-modules effectively lowers the voltage stress on each power switching device and facilitates expansion into a multi-module structure, expanding its application in high-voltage and large-capacity environments. This study analyzes the two working modes of the DC/DC converter and its control approach, in addition to providing a detailed introduction to the application scenarios of this converter. Ultimately, the efficacy and practicability of the suggested topology and control scheme are confirmed by simulations and experiments.

10 June 2025 in Energies
Verified
Journal Article
Open access
PDF file
MWMingkang Wu
Mingkang Wu
MCMin Cheng
Min Cheng
JYJiawei Yu
Jiawei Yu
YZYayao Zhang
Yayao Zhang
YZYuanfu Zhu
Yuanfu Zhu
YZYihua Zhu
Yihua Zhu
There is increasing penetration of photovoltaic (PV) systems into modern power grids; however, existing centralized communication architectures for PV stations often suffer from high latency and poor scalability, and the synchronization and coordinated control of multi-inverter clusters at millisecond timescales remain unresolved challenges. Hence, this paper proposes a distributed communication-based framework integrating multi-inverter synchronization and dynamic power allocation for rapid power regulation in PV stations. The architecture employs decentralized control logic to achieve the real-time synchronization of inverter clusters, eliminating reliance on centralized controllers. A dynamic power allocation algorithm, embedded with adaptive droop characteristics, optimizes active power distribution across inverters while minimizing transient overshoot. Experimental validation confirms the efficacy and operational advantages of the proposed communication architecture and power allocation strategy.