Tianqiao Zhao
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
Tianqiao Zhao has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Jianhui Wang
Southern Methodist University
17 shared publications - Meng Yue
Brookhaven National Laboratory, Upton, NY, USA
16 shared publications - Ding Lin
Department of Electrical and Computer Engineering, Southern Methodist University, Dallas, TX, USA
3 shared publications - Xiaonan Lu
Purdue University, West Lafayette, IN, USA
3 shared publications Alessandra Parisio
2 shared publications- Amirthagunaraj Yogarathinam
Interdisciplinary Science Department, Brookhaven National Laboratory, Upton, USA
2 shared publications
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17  (5) , 4186-4202
Nodal Frequency Nadir Chance-Constrained Economic Dispatch Considering Contingency Frequency Service From Hydrogen Electrolysis
Providing contingency frequency services (CFSs) through grid-forming (GFM) converter-interfaced resources (CIRs) is a technically effective method for bolstering the frequency stability of low-inertia power systems. However, this approach often causes significant power curtailment or high capital investment. Moreover, the heterogeneous dynamic characteristics of CIRs and increasing uncertainty of renewable energy sources (RESs) renders system-level frequency metrics under deterministic conditions insufficient, necessitating the incorporation of uncertain nodal frequency nadir (NFN) to ensure comprehensive frequency stability. To address these gaps, this paper proposes a novel NFN chance-constrained economic dispatch framework, which leverages hydrogen electrolysis systems (HESs) as cost-effective sources of CFSs. The framework first establishes a synergistic operation strategy for integrated grid-following RESs and GFM HESs to enable efficient delivery of CFSs under stochastic contingencies. System-level power dispatch decisions and device-level CIR settings (i.e., control mode) are then co-optimized to minimize operation costs while ensuring both the system-level and node-level frequency stability. Finally, to overcome the computational burden of the nonlinear NFN chance constraints, a computationally tractable solution methodology is developed that leverages input convex neural networks with analytical sensitivity analysis and Benders decomposition methods. The effectiveness and scalability of the proposed approach are validated through numerical simulations on two test systems.
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17  (5) , 4186-4202
Nodal Frequency Nadir Chance-Constrained Economic Dispatch Considering Contingency Frequency Service From Hydrogen Electrolysis
Providing contingency frequency services (CFSs) through grid-forming (GFM) converter-interfaced resources (CIRs) is a technically effective method for bolstering the frequency stability of low-inertia power systems. However, this approach often causes significant power curtailment or high capital investment. Moreover, the heterogeneous dynamic characteristics of CIRs and increasing uncertainty of renewable energy sources (RESs) renders system-level frequency metrics under deterministic conditions insufficient, necessitating the incorporation of uncertain nodal frequency nadir (NFN) to ensure comprehensive frequency stability. To address these gaps, this paper proposes a novel NFN chance-constrained economic dispatch framework, which leverages hydrogen electrolysis systems (HESs) as cost-effective sources of CFSs. The framework first establishes a synergistic operation strategy for integrated grid-following RESs and GFM HESs to enable efficient delivery of CFSs under stochastic contingencies. System-level power dispatch decisions and device-level CIR settings (i.e., control mode) are then co-optimized to minimize operation costs while ensuring both the system-level and node-level frequency stability. Finally, to overcome the computational burden of the nonlinear NFN chance constraints, a computationally tractable solution methodology is developed that leverages input convex neural networks with analytical sensitivity analysis and Benders decomposition methods. The effectiveness and scalability of the proposed approach are validated through numerical simulations on two test systems.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17  (4) , 3207-3220
Quantum Policy Learning for Energy Storage Arbitrage
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17  (4) , 3207-3220
Quantum Policy Learning for Energy Storage Arbitrage
- Open Access
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Access Journal of Power and Energy
- Vol. 13, 250-261
Reinforcement Learning-Based Symbolic Regression for Load Modeling
With the growing demand variability and evolving grid control strategies, accurate and efficient load modeling has become a critical yet challenging task. Traditional methods, such as fixed-form parametric models and data-driven approaches, often struggle to balance accuracy, computational efficiency, and interpretability. This paper introduces a novel symbolic regression algorithm based on the Actor-Critic reinforcement learning framework, specifically tailored for dynamic load modeling. The algorithm employs a trainable expression tree with controlled depth and a predefined set of operators to generate compact and interpretable mathematical expressions. The Actor network probabilistically selects operators for the symbolic expression, while the Critic evaluates the resulting expression tree through a loss function. To further enhance performance, a candidate pool mechanism is implemented to store high-performing expressions, which are subsequently fine-tuned using gradient descent. By focusing on simplicity and precision, the proposed method significantly reduces computational complexity while preserving interpretability. Experimental results validate its superior performance compared to existing benchmarks, which offers a robust and scalable solution for dynamic load modeling and system analysis in modern power systems.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Access Journal of Power and Energy
- Vol. 13, 250-261
Open AccessReinforcement Learning-Based Symbolic Regression for Load Modeling
With the growing demand variability and evolving grid control strategies, accurate and efficient load modeling has become a critical yet challenging task. Traditional methods, such as fixed-form parametric models and data-driven approaches, often struggle to balance accuracy, computational efficiency, and interpretability. This paper introduces a novel symbolic regression algorithm based on the Actor-Critic reinforcement learning framework, specifically tailored for dynamic load modeling. The algorithm employs a trainable expression tree with controlled depth and a predefined set of operators to generate compact and interpretable mathematical expressions. The Actor network probabilistically selects operators for the symbolic expression, while the Critic evaluates the resulting expression tree through a loss function. To further enhance performance, a candidate pool mechanism is implemented to store high-performing expressions, which are subsequently fine-tuned using gradient descent. By focusing on simplicity and precision, the proposed method significantly reduces computational complexity while preserving interpretability. Experimental results validate its superior performance compared to existing benchmarks, which offers a robust and scalable solution for dynamic load modeling and system analysis in modern power systems.
- 16 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 41  (3) , 2174-2186
A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching
Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.
- 16 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 41  (3) , 2174-2186
A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching
Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.
- Open Access
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Access Journal of Power and Energy
- Vol. 12, 833-844
Quantum Reinforcement Learning for Volt-VAR Control in Power Distribution Systems
Volt-VAR control (VVC) is crucial in active distribution networks for optimizing voltage profiles and minimizing network losses. While traditional deep reinforcement learning (DRL) algorithms exhibit promise for VVC, they often require extensive computational resources to handle such a high-dimensional problem. As a potential solution, quantum reinforcement learning (QRL) algorithms integrate the computational capabilities of quantum computing into the DRL framework. However, existing QRL algorithms struggle with complex VVC problems due to the limitations of current quantum hardware. To bridge this gap, this paper proposes an innovative QRL algorithm featuring an end-to-end architecture that integrates a classical autoencoder, variational quantum circuits (VQCs), and classical post-processing layers. This design efficiently compresses high-dimensional grid states, enabling VQCs to leverage quantum advantages while producing multiple control device outputs, specifically tailored for VVC tasks. Numerical studies on three representative distribution systems verify the effectiveness and scalability of the proposed QRL algorithm, and demonstrate its enhanced performance over classical approaches with only approximately 1% of the parameters. Additionally, the robustness of our developed algorithm is validated through noisy quantum environments.
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Access Journal of Power and Energy
- Vol. 12, 833-844
Open AccessQuantum Reinforcement Learning for Volt-VAR Control in Power Distribution Systems
Volt-VAR control (VVC) is crucial in active distribution networks for optimizing voltage profiles and minimizing network losses. While traditional deep reinforcement learning (DRL) algorithms exhibit promise for VVC, they often require extensive computational resources to handle such a high-dimensional problem. As a potential solution, quantum reinforcement learning (QRL) algorithms integrate the computational capabilities of quantum computing into the DRL framework. However, existing QRL algorithms struggle with complex VVC problems due to the limitations of current quantum hardware. To bridge this gap, this paper proposes an innovative QRL algorithm featuring an end-to-end architecture that integrates a classical autoencoder, variational quantum circuits (VQCs), and classical post-processing layers. This design efficiently compresses high-dimensional grid states, enabling VQCs to leverage quantum advantages while producing multiple control device outputs, specifically tailored for VVC tasks. Numerical studies on three representative distribution systems verify the effectiveness and scalability of the proposed QRL algorithm, and demonstrate its enhanced performance over classical approaches with only approximately 1% of the parameters. Additionally, the robustness of our developed algorithm is validated through noisy quantum environments.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21  (10) , 8133-8143
An End-to-End Learning Framework for Real-Time Decomposition and Classification of Aggregate Measurements at Substations
Understanding the composition of measured demand at the substation level is essential for understanding and modeling the highly complicated behaviors of numerous loads, which is very challenging due to their dynamic nature. This article presents a flexible, real-time decomposition framework that separates individual load sources from aggregate substation measurements while providing interpretability through load-type classification. Our approach employs an enhanced dual-path neural network to adaptively decompose load signals, supported by an encoder–decoder-based source-counting mechanism that estimates the number of load sources dynamically. To accommodate varying load counts, we include a multilayer convolutional module for flexible separation mask application. Extensive case studies with aggregate measurements containing different numbers of load sources demonstrate our model’s adaptability, achieving a mean-squared error reduction of up to 15% and a signal-to-distortion ratio improvement of 10% over baseline methods, with computational times suitable for real-time implementation. Comparative studies further show that our solution achieves consistent load-type classification accuracy of over 95%, enabling reliable insights for operational decisions in grid management.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21  (10) , 8133-8143
An End-to-End Learning Framework for Real-Time Decomposition and Classification of Aggregate Measurements at Substations
Understanding the composition of measured demand at the substation level is essential for understanding and modeling the highly complicated behaviors of numerous loads, which is very challenging due to their dynamic nature. This article presents a flexible, real-time decomposition framework that separates individual load sources from aggregate substation measurements while providing interpretability through load-type classification. Our approach employs an enhanced dual-path neural network to adaptively decompose load signals, supported by an encoder–decoder-based source-counting mechanism that estimates the number of load sources dynamically. To accommodate varying load counts, we include a multilayer convolutional module for flexible separation mask application. Extensive case studies with aggregate measurements containing different numbers of load sources demonstrate our model’s adaptability, achieving a mean-squared error reduction of up to 15% and a signal-to-distortion ratio improvement of 10% over baseline methods, with computational times suitable for real-time implementation. Comparative studies further show that our solution achieves consistent load-type classification accuracy of over 95%, enabling reliable insights for operational decisions in grid management.
- Open Access
A Deep Reinforcement Learning Method for Multi-objective Transmission Switching
Transmission switching is a well-established approach primarily applied to minimize operational costs through strategic network reconfiguration. However, exclusive focus on cost reduction can compromise system reliability. While multi-objective transmission switching can balance cost savings with reliability improvements, feasible solutions become exceedingly difficult to obtain as system scale grows, due to the inherent nonlinearity and high computational demands involved. This paper proposes a deep reinforcement learning (DRL) method for multi-objective transmission switching. The method incorporates a dueling-based actor-critic framework to evaluate the relative impact of each line switching decision within the action space, which improves decision quality and enhances both system reliability and cost efficiency. Numerical studies on the IEEE 118-bus system verify the effectiveness and efficiency of the proposed approach compared to two benchmark DRL algorithms.
Open AccessA Deep Reinforcement Learning Method for Multi-objective Transmission Switching
Transmission switching is a well-established approach primarily applied to minimize operational costs through strategic network reconfiguration. However, exclusive focus on cost reduction can compromise system reliability. While multi-objective transmission switching can balance cost savings with reliability improvements, feasible solutions become exceedingly difficult to obtain as system scale grows, due to the inherent nonlinearity and high computational demands involved. This paper proposes a deep reinforcement learning (DRL) method for multi-objective transmission switching. The method incorporates a dueling-based actor-critic framework to evaluate the relative impact of each line switching decision within the action space, which improves decision quality and enhances both system reliability and cost efficiency. Numerical studies on the IEEE 118-bus system verify the effectiveness and efficiency of the proposed approach compared to two benchmark DRL algorithms.
- Open Access
- 20 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 65403-65419
Reduced-Order Decomposition and Coordination Approach for Markov-Based Stochastic Unit Commitment With Distributed Wind Farms
States in the US increasingly integrate renewable energies to facilitate the transition to carbon neutrality. However, there are still many operational challenges to their efficient integration. This paper presents an innovative approach to solve the day-ahead Markov-based stochastic unit commitment (MSUC) problem with distributed wind generation. The MSUC utilizes a Markovian uncertainty set to represent the uncertainties in wind and other distributed intermittent renewable energies. While the Markovian uncertainty set intricately captures the stochasticity via states and state transitions, the set grows exponentially under the multi-dimensional uncertainties of distributed intermittent resources, thus rendering the MSUC intractable for systems with five or more such resources. In order to reduce the MSUC’s complexity, the problem is decomposed into approximate area problems (AAP), where each AAP utilizes a reduced, area-centric uncertainty set created using principal component analysis. Furthermore, the AAPs consider the binary commitment variables of only the local units, thus rendering much reduced complexity than the original MSUC. The AAPs are iteratively solved, and their solutions are coordinated in a novel Surrogate Absolute-Value Lagrangian Relaxation-based framework. Numerical testing is performed on test cases based on the IEEE 118-bus system with up to ten distributed wind farms, and solutions are validated via Monte Carlo simulations with typical and extreme wind generation scenarios. The simulation results demonstrate the ability of our method to obtain robust and cost-effective solutions to the MSUC in a constrained time frame.
- 20 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 65403-65419
Open AccessReduced-Order Decomposition and Coordination Approach for Markov-Based Stochastic Unit Commitment With Distributed Wind Farms
States in the US increasingly integrate renewable energies to facilitate the transition to carbon neutrality. However, there are still many operational challenges to their efficient integration. This paper presents an innovative approach to solve the day-ahead Markov-based stochastic unit commitment (MSUC) problem with distributed wind generation. The MSUC utilizes a Markovian uncertainty set to represent the uncertainties in wind and other distributed intermittent renewable energies. While the Markovian uncertainty set intricately captures the stochasticity via states and state transitions, the set grows exponentially under the multi-dimensional uncertainties of distributed intermittent resources, thus rendering the MSUC intractable for systems with five or more such resources. In order to reduce the MSUC’s complexity, the problem is decomposed into approximate area problems (AAP), where each AAP utilizes a reduced, area-centric uncertainty set created using principal component analysis. Furthermore, the AAPs consider the binary commitment variables of only the local units, thus rendering much reduced complexity than the original MSUC. The AAPs are iteratively solved, and their solutions are coordinated in a novel Surrogate Absolute-Value Lagrangian Relaxation-based framework. Numerical testing is performed on test cases based on the IEEE 118-bus system with up to ten distributed wind farms, and solutions are validated via Monte Carlo simulations with typical and extreme wind generation scenarios. The simulation results demonstrate the ability of our method to obtain robust and cost-effective solutions to the MSUC in a constrained time frame.