Yanyu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yanyu Zhang has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Yi Zhou
Henan University
16 shared publications - Xibeng Zhang
School of Artificial Intelligence, Henan University, Zhengzhou, China
14 shared publications - Feixiang Jiao
School of Artificial Intelligence, Henan University, Zhengzhou, China
13 shared publications - Abhisek Ukil
The University of Auckland
9 shared publications - Benfei Wang
Sun Yat-Sen University, Guangzhou, China
5 shared publications - Darong Huang
Anhui University
5 shared publications
Latest Publications
- 26 June 2026
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 47
Physically consistent sequence generative adversarial networks for wind power scenario generation
- 26 June 2026
- Published by Elsevier in Sustainable Energy, Grids and Networks
- Vol. 47
Physically consistent sequence generative adversarial networks for wind power scenario generation
- 3 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. PP (02780046) , 1-13
Dynamic Fractional-Order Model Predictive Control of Integrated PEM Electrolyzer and DC–DC Converter Based on Equivalent Circuits
Proton exchange membrane electrolyzer (PEMELE) water electrolysis has garnered considerable interest for its high efficiency, particularly in microgrid applications. However, the diffusion processes within PEMELE introduce significant nonlinearity in the voltage-current relationship and exacerbate current ripple during operation. Excessive current ripple not only compromises hydrogen production efficiency and system performance but also accelerates device degradation. To mitigate these issues, this article introduces a fractional-order equivalent circuit model that accurately captures the dynamics of PEMELE. Based on this model, a dynamic fractional-order model predictive control (DFOMPC) strategy is developed, utilizing both real-time and historical current data to predict voltage-current behavior. By explicitly accounting for the nonlinear and memory-dependent characteristics of PEMELE, the proposed approach achieves superior control performance. Simulations and hardware experiments demonstrate that, compared to conventional MPC, the proposed method reduces current ripple by 39.7% to 42.4% and voltage ripple by 18.5%–27.6%.
- 3 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. PP (02780046) , 1-13
Dynamic Fractional-Order Model Predictive Control of Integrated PEM Electrolyzer and DC–DC Converter Based on Equivalent Circuits
Proton exchange membrane electrolyzer (PEMELE) water electrolysis has garnered considerable interest for its high efficiency, particularly in microgrid applications. However, the diffusion processes within PEMELE introduce significant nonlinearity in the voltage-current relationship and exacerbate current ripple during operation. Excessive current ripple not only compromises hydrogen production efficiency and system performance but also accelerates device degradation. To mitigate these issues, this article introduces a fractional-order equivalent circuit model that accurately captures the dynamics of PEMELE. Based on this model, a dynamic fractional-order model predictive control (DFOMPC) strategy is developed, utilizing both real-time and historical current data to predict voltage-current behavior. By explicitly accounting for the nonlinear and memory-dependent characteristics of PEMELE, the proposed approach achieves superior control performance. Simulations and hardware experiments demonstrate that, compared to conventional MPC, the proposed method reduces current ripple by 39.7% to 42.4% and voltage ripple by 18.5%–27.6%.
- 13 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 41 (8) , 13674-13686
A Synergistic ESO-MPC Framework for Robust Current Tracking in PEM Electrolyzers Under Nonlinear Voltage Disturbances
Proton Exchange Membrane (PEM) electrolyzers offer significant advantages for microgrid-integrated energy storage systems, including high hydrogen production efficiency and operational flexibility under variable renewable energy inputs. However, their highly nonlinear V-I characteristics introduce substantial current and voltage ripple when interfaced through power electronic converters, degrading power quality and accelerating electrolyzer degradation. To address this challenge, this paper proposes a synergistic extended state observer (ESO)-model predictive control (MPC) framework for power converters connected to PEM electrolyzers. In this framework, an ultra-local model is decomposed into a nominal linear component and a nonlinear disturbance term, where the nonlinear dynamics are estimated and predicted by an ESO. These estimated states dynamically update the MPC prediction model, compensating for nonlinearity-induced model uncertainties. Hardware validation using a physical PEM electrolyzer under real-world electrolysis conditions demonstrates that the proposed method achieves a 50.33% reduction in current ripple compared to conventional MPC approaches.
- 13 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 41 (8) , 13674-13686
A Synergistic ESO-MPC Framework for Robust Current Tracking in PEM Electrolyzers Under Nonlinear Voltage Disturbances
Proton Exchange Membrane (PEM) electrolyzers offer significant advantages for microgrid-integrated energy storage systems, including high hydrogen production efficiency and operational flexibility under variable renewable energy inputs. However, their highly nonlinear V-I characteristics introduce substantial current and voltage ripple when interfaced through power electronic converters, degrading power quality and accelerating electrolyzer degradation. To address this challenge, this paper proposes a synergistic extended state observer (ESO)-model predictive control (MPC) framework for power converters connected to PEM electrolyzers. In this framework, an ultra-local model is decomposed into a nominal linear component and a nonlinear disturbance term, where the nonlinear dynamics are estimated and predicted by an ESO. These estimated states dynamically update the MPC prediction model, compensating for nonlinearity-induced model uncertainties. Hardware validation using a physical PEM electrolyzer under real-world electrolysis conditions demonstrates that the proposed method achieves a 50.33% reduction in current ripple compared to conventional MPC approaches.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Emerging and Selected Topics in Power Electronics
- Vol. 14 (2) , 2329-2340
Iterative Learning-Based MPC for Parameter Uncertainty Decoupling and Compensation in DC Microgrids
The control performance of power converters in energy storage systems (ESSs) critically determines the power quality of DC microgrids. However, parameter mismatches during operation may lead to significant voltage and current fluctuations, particularly under pulse load integration. To address this challenge, this paper proposes the iterative learning decoupling model predictive control (ILD-MPC) method for DC-DC converters. The key innovation lies in decoupling and estimating uncertain parameters from periodic model prediction errors by simple equations. These errors are treated as tracking errors and leveraged to iteratively update the MPC prediction model, thereby refining subsequent control actions. Simulation and experimental results demonstrate that the proposed method achieves superior performance compared to conventional MPC, reducing the steady-state voltage ripple by 37.5%–73% and the settling time by 33.3%.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Emerging and Selected Topics in Power Electronics
- Vol. 14 (2) , 2329-2340
Iterative Learning-Based MPC for Parameter Uncertainty Decoupling and Compensation in DC Microgrids
The control performance of power converters in energy storage systems (ESSs) critically determines the power quality of DC microgrids. However, parameter mismatches during operation may lead to significant voltage and current fluctuations, particularly under pulse load integration. To address this challenge, this paper proposes the iterative learning decoupling model predictive control (ILD-MPC) method for DC-DC converters. The key innovation lies in decoupling and estimating uncertain parameters from periodic model prediction errors by simple equations. These errors are treated as tracking errors and leveraged to iteratively update the MPC prediction model, thereby refining subsequent control actions. Simulation and experimental results demonstrate that the proposed method achieves superior performance compared to conventional MPC, reducing the steady-state voltage ripple by 37.5%–73% and the settling time by 33.3%.
- 2 March 2026
- Published by Elsevier in Solar Energy
- Vol. 310
Short term photovoltaic power prediction using multi-scale time and frequency features
- 2 March 2026
- Published by Elsevier in Solar Energy
- Vol. 310
Short term photovoltaic power prediction using multi-scale time and frequency features
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 5402-5413
Hybrid Digitized-Counterdiabatic Quantum–Classical Benders Decomposition for EV Charging Navigation in Coupled Transportation and Distribution Network
With the increasing integration of transportation network (TN) and distribution network (DN), the growing prevalence of electric vehicles (EVs) has posed significant challenges to both TN and DN operations, such as congestion at charging stations (CSs) and overload in the DN. To address these challenges, this article proposes a bi-layer coupled model that integrates EV route navigation and CS power scheduling. The upper layer of the model optimizes the lowest-cost routes for multiple EVs to reach the CS, while the lower layer optimizes the energy-efficient scheduling of the CS to meet EV charging demands. For solving the model in the form of mixed-integer linear programming (MILP), quantum computing (QC) has demonstrated significant potential. Therefore, a hybrid quantum–classical algorithm combining the digitized-counterdiabatic quantum approximate optimization algorithm (DC-QAOA) with Benders decomposition (DC-Q-BD) is developed. This algorithm leverages the parallelism of QC and the rapid convergence of digitized-counterdiabatic evolution. It also employs collaborative processing between a classical CPU and a quantum processing unit (QPU) to handle continuous and discrete variables, respectively. Results from practical case studies demonstrate that the proposed algorithm significantly enhances solution efficiency and quality. It provides cost-effective charging routes for EVs and notably reduces the adverse impacts of EV charging on the CS. This work provides a quantum-based approach for addressing the EV charging navigation problem in coupled TN and DN.
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 12 (3) , 5402-5413
Hybrid Digitized-Counterdiabatic Quantum–Classical Benders Decomposition for EV Charging Navigation in Coupled Transportation and Distribution Network
With the increasing integration of transportation network (TN) and distribution network (DN), the growing prevalence of electric vehicles (EVs) has posed significant challenges to both TN and DN operations, such as congestion at charging stations (CSs) and overload in the DN. To address these challenges, this article proposes a bi-layer coupled model that integrates EV route navigation and CS power scheduling. The upper layer of the model optimizes the lowest-cost routes for multiple EVs to reach the CS, while the lower layer optimizes the energy-efficient scheduling of the CS to meet EV charging demands. For solving the model in the form of mixed-integer linear programming (MILP), quantum computing (QC) has demonstrated significant potential. Therefore, a hybrid quantum–classical algorithm combining the digitized-counterdiabatic quantum approximate optimization algorithm (DC-QAOA) with Benders decomposition (DC-Q-BD) is developed. This algorithm leverages the parallelism of QC and the rapid convergence of digitized-counterdiabatic evolution. It also employs collaborative processing between a classical CPU and a quantum processing unit (QPU) to handle continuous and discrete variables, respectively. Results from practical case studies demonstrate that the proposed algorithm significantly enhances solution efficiency and quality. It provides cost-effective charging routes for EVs and notably reduces the adverse impacts of EV charging on the CS. This work provides a quantum-based approach for addressing the EV charging navigation problem in coupled TN and DN.
- 29 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 62 (2) , 3734-3745
Semi-Quantum Communication for Cyber Secure Microgrid Under Zero-Trust Architecture
The microgrid faces increasingly severe communication security challenges due to its open and highly interactive characteristics. However, the traditional trust architecture cannot cope with the dynamically changing identity authentication requirements, and data transmission based on classical encryption is vulnerable to attacks from quantum computers. Existing quantum-secure microgrid research typically requires both parties to possess full quantum capabilities, which limits its practicality in real-world deployments. To address these challenges, this paper proposes a semi-quantum secure communication framework for microgrids. Firstly, a semi-quantum authentication model based on zero-trust architecture is introduced to support dynamic and secure identity verification between the microgrid central controller (MGCC) and distributed energy resources (DERs). Secondly, a semi-quantum key distribution (SQKD) scheme is integrated, requiring only the MGCC to be fully quantum-capable, thereby reducing system complexity. Additionally, a dynamic key provisioning strategy is designed based on DERs' energy characteristics to improve resource efficiency and system security. Experimental results and analysis provide valuable insights for the design and deployment of semi-quantum-enabled microgrid communication.
- 29 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 62 (2) , 3734-3745
Semi-Quantum Communication for Cyber Secure Microgrid Under Zero-Trust Architecture
The microgrid faces increasingly severe communication security challenges due to its open and highly interactive characteristics. However, the traditional trust architecture cannot cope with the dynamically changing identity authentication requirements, and data transmission based on classical encryption is vulnerable to attacks from quantum computers. Existing quantum-secure microgrid research typically requires both parties to possess full quantum capabilities, which limits its practicality in real-world deployments. To address these challenges, this paper proposes a semi-quantum secure communication framework for microgrids. Firstly, a semi-quantum authentication model based on zero-trust architecture is introduced to support dynamic and secure identity verification between the microgrid central controller (MGCC) and distributed energy resources (DERs). Secondly, a semi-quantum key distribution (SQKD) scheme is integrated, requiring only the MGCC to be fully quantum-capable, thereby reducing system complexity. Additionally, a dynamic key provisioning strategy is designed based on DERs' energy characteristics to improve resource efficiency and system security. Experimental results and analysis provide valuable insights for the design and deployment of semi-quantum-enabled microgrid communication.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (2) , 2427-2439
Reinforcement Learning Based Active Model Variation Deadbeat Control for Energy Storage System in DC Microgrids With Constant Power Loads
The issues of constant power load (CPL) and model mismatch lead to significant current ripples and voltage fluctuations in dc microgrids, presenting a substantial challenge for the control methods of energy storage systems. To address these issues, this article proposes a reinforcement learning based active model variation deadbeat control (RL-AMVDB), which adjusts a few control model parameters in the current control loop. The model variation factors and the states of closed-loop system are formulated as a Markov decision process, allowing the model variation factors to be optimized through RL. The performance of the proposed method is evaluated through both simulation and hardware experiments. Experimental results demonstrate that the proposed method reduces current ripple by 16.6% under model mismatch conditions. Additionally, under sudden CPL changes, the settling time, voltage fluctuations, and current ripple are reduced by 38.4%, 10.2%, and 12.5%–20%, respectively.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (2) , 2427-2439
Reinforcement Learning Based Active Model Variation Deadbeat Control for Energy Storage System in DC Microgrids With Constant Power Loads
The issues of constant power load (CPL) and model mismatch lead to significant current ripples and voltage fluctuations in dc microgrids, presenting a substantial challenge for the control methods of energy storage systems. To address these issues, this article proposes a reinforcement learning based active model variation deadbeat control (RL-AMVDB), which adjusts a few control model parameters in the current control loop. The model variation factors and the states of closed-loop system are formulated as a Markov decision process, allowing the model variation factors to be optimized through RL. The performance of the proposed method is evaluated through both simulation and hardware experiments. Experimental results demonstrate that the proposed method reduces current ripple by 16.6% under model mismatch conditions. Additionally, under sudden CPL changes, the settling time, voltage fluctuations, and current ripple are reduced by 38.4%, 10.2%, and 12.5%–20%, respectively.
- 7 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 62 (2) , 3699-3709
Privacy-Shielded Federated Quantum Learning Approach for Charging Load Forecasting
As data privacy increasingly becomes a critical societal concern, traditional centralized training for EV charging load prediction may lead to data leakage and missing information. In this paper, a federated quantum learning (FQL) framework for charging prediction is established, which can avoid sensitive privacy concerns by sharing model parameters rather than sharing private data to obtain accurate predictive models. Quantum long short-term memory neural network (QLSTM) is designed to predict the charging load. By integrating a variational quantum circuit into the neural network architecture as a replacement for the traditional weight matrix, QLSTM model significantly enhances its ability to learn complex nonlinear patterns inherent in electric vehicle charging load data, thereby achieving improved prediction accuracy. Comparative experiments based on MAE, MSE, MAPE, and R$^{2}$ metrics demonstrate that F-QLSTM consistently outperforms traditional models such as RNN, LSTM, GRU, and Transformer, achieving higher prediction accuracy with significantly fewer trainable parameters. Specifically, it achieves a 46.1% reduction in parameters compared to LSTM, while maintaining a high R$^{2}$ score, indicating its strong ability to capture complex temporal dependencies and nonlinear patterns. Moreover, experiments conducted across multiple datasets and qubit configurations validate the robustness and generalizability of the F-QLSTM framework.
- 7 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 62 (2) , 3699-3709
Privacy-Shielded Federated Quantum Learning Approach for Charging Load Forecasting
As data privacy increasingly becomes a critical societal concern, traditional centralized training for EV charging load prediction may lead to data leakage and missing information. In this paper, a federated quantum learning (FQL) framework for charging prediction is established, which can avoid sensitive privacy concerns by sharing model parameters rather than sharing private data to obtain accurate predictive models. Quantum long short-term memory neural network (QLSTM) is designed to predict the charging load. By integrating a variational quantum circuit into the neural network architecture as a replacement for the traditional weight matrix, QLSTM model significantly enhances its ability to learn complex nonlinear patterns inherent in electric vehicle charging load data, thereby achieving improved prediction accuracy. Comparative experiments based on MAE, MSE, MAPE, and R$^{2}$ metrics demonstrate that F-QLSTM consistently outperforms traditional models such as RNN, LSTM, GRU, and Transformer, achieving higher prediction accuracy with significantly fewer trainable parameters. Specifically, it achieves a 46.1% reduction in parameters compared to LSTM, while maintaining a high R$^{2}$ score, indicating its strong ability to capture complex temporal dependencies and nonlinear patterns. Moreover, experiments conducted across multiple datasets and qubit configurations validate the robustness and generalizability of the F-QLSTM framework.
- 6 August 2025
- Published by Elsevier in Computer Networks
- Vol. 271
Spatial–temporal Causal Fusion Graph Neural Networks for urban traffic prediction
- 6 August 2025
- Published by Elsevier in Computer Networks
- Vol. 271
Spatial–temporal Causal Fusion Graph Neural Networks for urban traffic prediction