Bowen Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bowen Zheng has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Chang Liu
China Electric Power Research Institute, Beijing, China
3 shared publicationsMingming Pan
China Electric Power Research Institute, Beijing, China
3 shared publications- Feixiang Gong
Beijing Key Laboratory of Demand Side Multi-Energy Complementary Optimization and Supply-Demand Interaction Technology, China Electric Power Research Institute Co., Ltd., Beijing 100035, China
2 shared publications Jianfeng Li
China Electric Power Research Institute, Beijing, China
2 shared publicationsJie Tong
China Electric Power Research Institute, Beijing, China
2 shared publicationsJing Zhang
China Electric Power Research Institute, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 15 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A deep surrogate modeling approach for distributed control of aggregated air-conditioning loads
With the increasing penetration of intermittent renewable energy sources, harnessing the flexibility of aggregated air conditioning (AC) loads has become critical for maintaining grid stability. However, existing control strategies often face a trade-off between protecting user privacy and providing a standardized, model-free interface for grid dispatch. This paper proposes a deep surrogate modeling approach that addresses this challenge. We introduce a three-layer “Aggregator-Edge-End user” architecture leveraging a data-driven workflow. At the core of this framework is a hybrid deep learning model combining a Temporal Convolutional Network (TCN) and a Bidirectional Long Short-Term Memory (BiLSTM) network. This model integrates grid regulation signals and a user-willingness factor, enabling it to generate a reliable power-response mapping without requiring sensitive physical parameters. For real-time power allocation, we propose an Improved Distributed Particle Swarm Optimization (IDPSO) algorithm that embeds a LightGBM model to predict thermal dynamics, thereby reducing reliance on traditional thermodynamic models. Large-scale simulations demonstrate that the proposed approach achieves a low power tracking (mean relative error < 0.2%) and robustness to user disturbances. By effectively decoupling control from physical models, this work presents a scalable and market-compatible framework for demand response that reduces direct exposure of user-level data through edge-side aggregation.
- 15 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA deep surrogate modeling approach for distributed control of aggregated air-conditioning loads
With the increasing penetration of intermittent renewable energy sources, harnessing the flexibility of aggregated air conditioning (AC) loads has become critical for maintaining grid stability. However, existing control strategies often face a trade-off between protecting user privacy and providing a standardized, model-free interface for grid dispatch. This paper proposes a deep surrogate modeling approach that addresses this challenge. We introduce a three-layer “Aggregator-Edge-End user” architecture leveraging a data-driven workflow. At the core of this framework is a hybrid deep learning model combining a Temporal Convolutional Network (TCN) and a Bidirectional Long Short-Term Memory (BiLSTM) network. This model integrates grid regulation signals and a user-willingness factor, enabling it to generate a reliable power-response mapping without requiring sensitive physical parameters. For real-time power allocation, we propose an Improved Distributed Particle Swarm Optimization (IDPSO) algorithm that embeds a LightGBM model to predict thermal dynamics, thereby reducing reliance on traditional thermodynamic models. Large-scale simulations demonstrate that the proposed approach achieves a low power tracking (mean relative error < 0.2%) and robustness to user disturbances. By effectively decoupling control from physical models, this work presents a scalable and market-compatible framework for demand response that reduces direct exposure of user-level data through edge-side aggregation.
- Open Access
- 20 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Coordinated Temporal Convolutional Network and Transformer for enhanced carbon emission prediction in energy intensive industries
This research presents a systematic framework for high-precision carbon emission forecasting in energy-intensive industries, integrating emission accounting methodologies with a Temporal Convolutional Network (TCN)-Transformer hybrid architecture. Motivated by the need for more robust short-term emission prediction, the study first establishes a theoretical foundation by comprehensively reviewing and categorizing prevalent carbon accounting approaches—including direct and indirect emission estimation based on the Intergovernmental Panel on Climate Change (IPCC) emission factor method—applied to representative enterprises in the steel, concrete, and electrolytic aluminum sectors. Building on this, a novel hybrid model is developed that combines the TCN’s ability to extract multi-scale temporal features using dilated convolutions with the Transformer’s capability to capture long-range dependencies through multi-head self-attention. Empirical validation on real-world datasets demonstrates that the proposed model significantly outperforms standalone Transformer architectures, yielding a 35% improvement in prediction accuracy and reducing the Mean Absolute Percentage Error (MAPE) to 3.21%. These results highlight the framework’s effectiveness in modeling complex emission dynamics, offering a scalable and data-driven tool to support proactive carbon management strategies in high-emission industrial contexts.
- 20 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessCoordinated Temporal Convolutional Network and Transformer for enhanced carbon emission prediction in energy intensive industries
This research presents a systematic framework for high-precision carbon emission forecasting in energy-intensive industries, integrating emission accounting methodologies with a Temporal Convolutional Network (TCN)-Transformer hybrid architecture. Motivated by the need for more robust short-term emission prediction, the study first establishes a theoretical foundation by comprehensively reviewing and categorizing prevalent carbon accounting approaches—including direct and indirect emission estimation based on the Intergovernmental Panel on Climate Change (IPCC) emission factor method—applied to representative enterprises in the steel, concrete, and electrolytic aluminum sectors. Building on this, a novel hybrid model is developed that combines the TCN’s ability to extract multi-scale temporal features using dilated convolutions with the Transformer’s capability to capture long-range dependencies through multi-head self-attention. Empirical validation on real-world datasets demonstrates that the proposed model significantly outperforms standalone Transformer architectures, yielding a 35% improvement in prediction accuracy and reducing the Mean Absolute Percentage Error (MAPE) to 3.21%. These results highlight the framework’s effectiveness in modeling complex emission dynamics, offering a scalable and data-driven tool to support proactive carbon management strategies in high-emission industrial contexts.
- Open Access
- 17 June 2025
- Published by Springer Nature in Research Square
Carbon Emission Prediction for Energy-Intensive Industries Based on a TCN-Transformer Hybrid Model
This research presents a systematic framework for high-precision carbon emission forecasting in energy-intensive industries, integrating emission accounting methodologies with a Temporal Convolutional Network (TCN)-Transformer hybrid architecture. First, direct and indirect emissions from representative enterprises in the steel, concrete, and electrolytic aluminum sectors were rigorously quantified using the Intergovernmental Panel on Climate Change (IPCC)emission factor approach. Subsequently, a TCN-Transformer model was developed to capture temporal patterns in annual emission data, where the TCN module leverages dilated convolutions and residual connections to extract multi-scale features, while the Transformer component employs multi-head self-attention to model long-range dependencies. Empirical results demonstrate that the proposed hybrid model outperforms standalone Transformer architectures by 35% in prediction accuracy, achieving a Mean Absolute Percentage Error (MAPE) of 3.21%. This significant improvement underscores the model's efficacy in capturing complex emission dynamics, providing a robust tool for proactive carbon management strategies.
- 17 June 2025
- Published by Springer Nature in Research Square
Open AccessCarbon Emission Prediction for Energy-Intensive Industries Based on a TCN-Transformer Hybrid Model
This research presents a systematic framework for high-precision carbon emission forecasting in energy-intensive industries, integrating emission accounting methodologies with a Temporal Convolutional Network (TCN)-Transformer hybrid architecture. First, direct and indirect emissions from representative enterprises in the steel, concrete, and electrolytic aluminum sectors were rigorously quantified using the Intergovernmental Panel on Climate Change (IPCC)emission factor approach. Subsequently, a TCN-Transformer model was developed to capture temporal patterns in annual emission data, where the TCN module leverages dilated convolutions and residual connections to extract multi-scale features, while the Transformer component employs multi-head self-attention to model long-range dependencies. Empirical results demonstrate that the proposed hybrid model outperforms standalone Transformer architectures by 35% in prediction accuracy, achieving a Mean Absolute Percentage Error (MAPE) of 3.21%. This significant improvement underscores the model's efficacy in capturing complex emission dynamics, providing a robust tool for proactive carbon management strategies.
- Open Access
- 25 June 2023
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 11 (7) , 1288
Study on Mitigation of Wake Interference by Combined Control of Yaw Misalignment and Pitch
Yaw misalignment can make a wake steer, which is an effective method to increase the power of wind farms but it also increases the fatigue load of the turbines. In this paper, the combination of yaw offset and pitch control (CYMP) is studied to analyse the potential mitigation of wake, focusing on the wind velocity and turbulence of the wake distribution, power increment, and fatigue load reduction. The simulation case study shows that the method of CYMP can reduce the fatigue load by 10.29% and increase the total power by 1.7% compared with only wake steering in FAST.Fram. The Collaborative MPC (CoMPC) method based on CYMP is proposed to the real-time wake control in this research, which can increase power by more than 2% and reduce thrust by more than 4% than greedy control under 10 m/s turbulent wind.
- 25 June 2023
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 11 (7) , 1288
Open AccessStudy on Mitigation of Wake Interference by Combined Control of Yaw Misalignment and Pitch
Yaw misalignment can make a wake steer, which is an effective method to increase the power of wind farms but it also increases the fatigue load of the turbines. In this paper, the combination of yaw offset and pitch control (CYMP) is studied to analyse the potential mitigation of wake, focusing on the wind velocity and turbulence of the wake distribution, power increment, and fatigue load reduction. The simulation case study shows that the method of CYMP can reduce the fatigue load by 10.29% and increase the total power by 1.7% compared with only wake steering in FAST.Fram. The Collaborative MPC (CoMPC) method based on CYMP is proposed to the real-time wake control in this research, which can increase power by more than 2% and reduce thrust by more than 4% than greedy control under 10 m/s turbulent wind.
- Open Access
- 13 June 2023
- Published by MDPI AG in Preprints.org
Study on Mitigation of Wake Interference by Combined Control of Yaw Misalignment and Pitch
Yaw misalignment can make a wake steer, which is an effective method to increase the power of wind farms, but it also increases the fatigue load of the turbines. In this paper, the method of combining yaw misalignment and pitch control (CYMP) is proposed to investigate the potential to mitigate wake interference, the wind velocity distribution and turbulence distribution in the wake, as well as the power and load changes of the wind turbine are studied, focusing on power in-crement and fatigue damage reduction. Although some studies have found that the method of CYMP are beneficial to increase power generation and reduce fatigue loads, there are no papers that have made a detailed analysis of the effects of wake turbulence, wind speed distribution, power, especially fatigue damage under this control. Simulation tool FAST.Farm is used to model and analyze wind farms, obtain the variation details of wake and provide simulation data for calculating power and fatigue load. The pitch control brings bias to the CYMP optimization results was neglected, the case studies show that the method of CYMP can reduce the fatigue load by 10.29% and increase the total power by 1.7% compared with only wake steering. The Model Predictive Control collaborative method based on CYMP is proposed, which can increase power by more than 2% and reduce thrust by more than 4% under 10m/s turbulent wind.
- 13 June 2023
- Published by MDPI AG in Preprints.org
Open AccessStudy on Mitigation of Wake Interference by Combined Control of Yaw Misalignment and Pitch
Yaw misalignment can make a wake steer, which is an effective method to increase the power of wind farms, but it also increases the fatigue load of the turbines. In this paper, the method of combining yaw misalignment and pitch control (CYMP) is proposed to investigate the potential to mitigate wake interference, the wind velocity distribution and turbulence distribution in the wake, as well as the power and load changes of the wind turbine are studied, focusing on power in-crement and fatigue damage reduction. Although some studies have found that the method of CYMP are beneficial to increase power generation and reduce fatigue loads, there are no papers that have made a detailed analysis of the effects of wake turbulence, wind speed distribution, power, especially fatigue damage under this control. Simulation tool FAST.Farm is used to model and analyze wind farms, obtain the variation details of wake and provide simulation data for calculating power and fatigue load. The pitch control brings bias to the CYMP optimization results was neglected, the case studies show that the method of CYMP can reduce the fatigue load by 10.29% and increase the total power by 1.7% compared with only wake steering. The Model Predictive Control collaborative method based on CYMP is proposed, which can increase power by more than 2% and reduce thrust by more than 4% under 10m/s turbulent wind.