Shuang Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shuang Han has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Yongqian Liu
School of New Energy, North China Electric Power University, Beijing 102206, China
6 shared publications Fu-Rong Luo
1 shared publicationHang Meng
State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University No.2 Beinong Road, Changping District Beijing People's Republic of China
1 shared publication- Hang Meng
State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
1 shared publication Hao Zhao
State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University No.2 Beinong Road, Changping District Beijing People's Republic of China
1 shared publicationJialin Han
North China Electric Power University
1 shared publication
Latest Publications
- Open Access
Weather-Transition-Aware Dynamic Mixture-of-Experts for Day-Ahead Probabilistic Wind Power Forecasting
Wind power forecasting under transitional weather conditions is crucial for the secure operation and dispatch of power systems. However, existing methods have limited ability to perceive and adapt to the rapid, nonstationary changes in the weather–power mapping caused by transitional weather, resulting in substantially increased forecasting errors and uncertainty. To address this issue, this paper proposes a day-ahead probabilistic wind power forecasting method based on a weather-transition-aware mixture-of-experts network. First, based on numerical weather prediction (NWP) sequences of wind speed and temperature, a progressive analysis of trends and abrupt changes and a turning-point localization mechanism based on symmetric-ratio minimization are introduced to identify potential transitional periods and generate a weather-transition mask. The binary transition indicator is then concatenated with the NWP features at each time step, and cross-attention is employed to fuse meteorological forecasts with historical power information. Finally, a gated mixture-of-experts (MoE) network dynamically fuses conventional-weather and transitional-weather experts according to the daily transition fraction. Quantile regression is subsequently used to generate prediction intervals at multiple coverage levels. A case study of a wind farm shows that the proposed method achieves a normalized mean absolute error (NMAE) of 5.79%, a coefficient of determination () of 0.88, and a 21.36% reduction in the normalized average width of the 95% prediction interval relative to the baseline with the lowest mean normalized average interval width.Open AccessWeather-Transition-Aware Dynamic Mixture-of-Experts for Day-Ahead Probabilistic Wind Power Forecasting
Wind power forecasting under transitional weather conditions is crucial for the secure operation and dispatch of power systems. However, existing methods have limited ability to perceive and adapt to the rapid, nonstationary changes in the weather–power mapping caused by transitional weather, resulting in substantially increased forecasting errors and uncertainty. To address this issue, this paper proposes a day-ahead probabilistic wind power forecasting method based on a weather-transition-aware mixture-of-experts network. First, based on numerical weather prediction (NWP) sequences of wind speed and temperature, a progressive analysis of trends and abrupt changes and a turning-point localization mechanism based on symmetric-ratio minimization are introduced to identify potential transitional periods and generate a weather-transition mask. The binary transition indicator is then concatenated with the NWP features at each time step, and cross-attention is employed to fuse meteorological forecasts with historical power information. Finally, a gated mixture-of-experts (MoE) network dynamically fuses conventional-weather and transitional-weather experts according to the daily transition fraction. Quantile regression is subsequently used to generate prediction intervals at multiple coverage levels. A case study of a wind farm shows that the proposed method achieves a normalized mean absolute error (NMAE) of 5.79%, a coefficient of determination () of 0.88, and a 21.36% reduction in the normalized average width of the 95% prediction interval relative to the baseline with the lowest mean normalized average interval width. - Open Access
The Calculation Method of Time-Series Reduction Coefficients for Wind Power Generation in Ultra-High-Altitude Areas
In the preliminary design stage of wind farms, the theoretical energy output must be adjusted by multiple reduction factors to estimate the actual grid-connected power. As renewable energy becomes increasingly integrated into electricity markets, the conventional approach using static, averaged reduction coefficients for annual yield estimation can no longer meet the market’s demand for high-resolution power time series. Addressing this gap, the novelty of this paper lies in shifting the focus from total annual estimation to hourly-level dynamic allocation. This paper proposes a time-series reduction coefficient evaluation method based on the time-varying entropy weight method (TV-EWM). Under the assumption that the total annual reduction quantity adheres to standard design specifications, this method utilizes long-term wind measurement data, integrates unique ultra-high-altitude wind resource characteristics, and constructs a scenario-based indicator system. By quantifying the coupling relationships between key meteorological variables and incorporating a dynamic weighting mechanism, the proposed approach achieves hourly refined reduction estimation for theoretical power output. Comparative analysis was conducted against the traditional static average reduction method. Results indicate that, compared to the traditional average reduction method, the TV-EWM approach significantly enhances the model’s ability to capture seasonal variability, increasing the coefficient of determination (R2) by 4.19% to 0.7061. Furthermore, it demonstrates higher stability in error control, reducing the Normalized Root Mean Square Error (NRMSE) by 4.51% to 15.45%. The TV-EWM more accurately captures the temporal evolution and coupling effects between meteorological elements and curtailed generation under various reduction scenarios, retains full-load operational features, and enhances physical interpretability and time responsiveness, providing a new analytical framework for market-oriented power generation assessment.
Open AccessThe Calculation Method of Time-Series Reduction Coefficients for Wind Power Generation in Ultra-High-Altitude Areas
In the preliminary design stage of wind farms, the theoretical energy output must be adjusted by multiple reduction factors to estimate the actual grid-connected power. As renewable energy becomes increasingly integrated into electricity markets, the conventional approach using static, averaged reduction coefficients for annual yield estimation can no longer meet the market’s demand for high-resolution power time series. Addressing this gap, the novelty of this paper lies in shifting the focus from total annual estimation to hourly-level dynamic allocation. This paper proposes a time-series reduction coefficient evaluation method based on the time-varying entropy weight method (TV-EWM). Under the assumption that the total annual reduction quantity adheres to standard design specifications, this method utilizes long-term wind measurement data, integrates unique ultra-high-altitude wind resource characteristics, and constructs a scenario-based indicator system. By quantifying the coupling relationships between key meteorological variables and incorporating a dynamic weighting mechanism, the proposed approach achieves hourly refined reduction estimation for theoretical power output. Comparative analysis was conducted against the traditional static average reduction method. Results indicate that, compared to the traditional average reduction method, the TV-EWM approach significantly enhances the model’s ability to capture seasonal variability, increasing the coefficient of determination (R2) by 4.19% to 0.7061. Furthermore, it demonstrates higher stability in error control, reducing the Normalized Root Mean Square Error (NRMSE) by 4.51% to 15.45%. The TV-EWM more accurately captures the temporal evolution and coupling effects between meteorological elements and curtailed generation under various reduction scenarios, retains full-load operational features, and enhances physical interpretability and time responsiveness, providing a new analytical framework for market-oriented power generation assessment.
- 2 January 2026
- Published by Springer Nature
- p. 461-470
Early Fault Detection for Wind Turbine Main Bearing Based on Neural Circuit Policies
- 2 January 2026
- Published by Springer Nature
- p. 461-470
Early Fault Detection for Wind Turbine Main Bearing Based on Neural Circuit Policies
- Open Access
Charging and Discharging Optimization of Vehicle Battery Efficiency for Minimizing Company Expenses Considering Regular User Travel Habits
With the increasing popularity and development of electric vehicles, the demand for electric vehicle charging is also constantly increasing. To meet the diverse charging needs of electric vehicle users and improve the efficiency of charging infrastructure, this study proposes an optimization strategy for electric vehicle charging and discharging. This method considers both the user’s travel mode and the operational efficiency of the charging pile. Firstly, a probability model based on travel spatiotemporal variables and Monte Carlo algorithm were used to simulate the travel trajectory of electric vehicles, providing a data foundation for optimizing the charging and discharging schemes of electric vehicles. Then, with the dual objective of minimizing the operating costs of charging piles and user charging costs, a linear programming model was constructed to optimize the charging and discharging strategies of electric vehicles. Finally, the model was validated using an apartment building as an example. The results indicate that, under the normal travel habits of users, with the goal of minimizing company expenses, the annual cost of the company reaches its minimum at a certain number of charging piles. When the cost of electric vehicle users dominates the objective function, they will pay more attention to battery degradation, significantly reducing their willingness to participate in discharge.
Open AccessCharging and Discharging Optimization of Vehicle Battery Efficiency for Minimizing Company Expenses Considering Regular User Travel Habits
With the increasing popularity and development of electric vehicles, the demand for electric vehicle charging is also constantly increasing. To meet the diverse charging needs of electric vehicle users and improve the efficiency of charging infrastructure, this study proposes an optimization strategy for electric vehicle charging and discharging. This method considers both the user’s travel mode and the operational efficiency of the charging pile. Firstly, a probability model based on travel spatiotemporal variables and Monte Carlo algorithm were used to simulate the travel trajectory of electric vehicles, providing a data foundation for optimizing the charging and discharging schemes of electric vehicles. Then, with the dual objective of minimizing the operating costs of charging piles and user charging costs, a linear programming model was constructed to optimize the charging and discharging strategies of electric vehicles. Finally, the model was validated using an apartment building as an example. The results indicate that, under the normal travel habits of users, with the goal of minimizing company expenses, the annual cost of the company reaches its minimum at a certain number of charging piles. When the cost of electric vehicle users dominates the objective function, they will pay more attention to battery degradation, significantly reducing their willingness to participate in discharge.
- Open Access
Wave Power Prediction Based on Seasonal and Trend Decomposition Using Locally Weighted Scatterplot Smoothing and Dual-Channel Seq2Seq Model
Wave energy has emerged as a focal point in marine renewable energy research. Accurate prediction of wave power plays a pivotal role in enhancing power supply reliability. This paper introduces an innovative wave power prediction method that combines seasonal–trend decomposition using LOESS (STL) with a dual-channel Seq2Seq model. The decomposition model addresses the issue of component redundancy in current input decomposition methods, thereby uncovering key components. The prediction model improves upon the limitations of current prediction models that directly concatenate multiple features, allowing for a more detailed consideration of both trend and periodic features. The proposed approach begins by decomposing the power sequence based on tidal periods and optimal correlation criteria, effectively extracting both trend and periodic features. Subsequently, a dual-channel Seq2Seq model is constructed. The first channel employs temporal pattern attention to capture the trend and stochastic fluctuation information, while the second channel utilizes multi-head self-attention to further enhance the extraction of periodic components. Model validation is performed using data from two ocean buoys, each with a five-year dataset. The proposed model achieves an average 2.45% reduction in RMSE compared to the state-of-the-art method. Both the decomposition and prediction components of the model contribute to this increase in accuracy.
Open AccessWave Power Prediction Based on Seasonal and Trend Decomposition Using Locally Weighted Scatterplot Smoothing and Dual-Channel Seq2Seq Model
Wave energy has emerged as a focal point in marine renewable energy research. Accurate prediction of wave power plays a pivotal role in enhancing power supply reliability. This paper introduces an innovative wave power prediction method that combines seasonal–trend decomposition using LOESS (STL) with a dual-channel Seq2Seq model. The decomposition model addresses the issue of component redundancy in current input decomposition methods, thereby uncovering key components. The prediction model improves upon the limitations of current prediction models that directly concatenate multiple features, allowing for a more detailed consideration of both trend and periodic features. The proposed approach begins by decomposing the power sequence based on tidal periods and optimal correlation criteria, effectively extracting both trend and periodic features. Subsequently, a dual-channel Seq2Seq model is constructed. The first channel employs temporal pattern attention to capture the trend and stochastic fluctuation information, while the second channel utilizes multi-head self-attention to further enhance the extraction of periodic components. Model validation is performed using data from two ocean buoys, each with a five-year dataset. The proposed model achieves an average 2.45% reduction in RMSE compared to the state-of-the-art method. Both the decomposition and prediction components of the model contribute to this increase in accuracy.
- Open Access
- 15 April 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (4) , 544
Effects of the Parameter C4ε in the Extended k-ε Turbulence Model for Wind Farm Wake Simulation Using an Actuator Disc
The actuator disc model (ADM) incorporated into the k-ε turbulence model of EI Kasmi is able to simulate the wind farm wakes with high fidelity, which is essential for layout optimization and the evaluation of power production in modern wind farms. However, the effects of the parameter C4ε in the k-ε model of EI Kasmi on turbulent kinetic energy (TKE) in the superposition areas and the recovery of wind farm wake velocity have rarely been studied. To this end, the k-ε model of EI Kasmi is coupled with the advanced ADM in PHOENICS to investigate the influence of the parameter C4ε on the wake simulation of wind farms (e.g., two offshore wind farms, one onshore wind farm). It is concluded that a decreased parameter C4ε makes the generation range of TKE in the vicinity of the rotor smaller, but the TKE near the rotor becomes larger, and the wake recovery rate of the downstream turbine is less affected by the near wake. As the interwind turbine spacing increases, the influence area of TKE in the wake region of each downstream machine gradually reduces, and atmospheric turbulence plays a dominant role in wake recovery. A decreased parameter C4ε can effectively promote the inflow wind velocity and power output of downstream turbines. The power output simulated compares well with the measured power value when the parameter C4ε = 0.15.
- 15 April 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (4) , 544
Open AccessEffects of the Parameter C4ε in the Extended k-ε Turbulence Model for Wind Farm Wake Simulation Using an Actuator Disc
The actuator disc model (ADM) incorporated into the k-ε turbulence model of EI Kasmi is able to simulate the wind farm wakes with high fidelity, which is essential for layout optimization and the evaluation of power production in modern wind farms. However, the effects of the parameter C4ε in the k-ε model of EI Kasmi on turbulent kinetic energy (TKE) in the superposition areas and the recovery of wind farm wake velocity have rarely been studied. To this end, the k-ε model of EI Kasmi is coupled with the advanced ADM in PHOENICS to investigate the influence of the parameter C4ε on the wake simulation of wind farms (e.g., two offshore wind farms, one onshore wind farm). It is concluded that a decreased parameter C4ε makes the generation range of TKE in the vicinity of the rotor smaller, but the TKE near the rotor becomes larger, and the wake recovery rate of the downstream turbine is less affected by the near wake. As the interwind turbine spacing increases, the influence area of TKE in the wake region of each downstream machine gradually reduces, and atmospheric turbulence plays a dominant role in wake recovery. A decreased parameter C4ε can effectively promote the inflow wind velocity and power output of downstream turbines. The power output simulated compares well with the measured power value when the parameter C4ε = 0.15.
- Open Access
Power Generation Performance Indicators of Wind Farms Including the Influence of Wind Energy Resource Differences
The accurate evaluation and fair comparison of wind farms power generation performance is of great significance to the technical transformation and operation and maintenance management of wind farms. However, problems exist in the evaluation indicator systems such as confusion, coupling and broadness, and the influence of wind energy resource differences not being able to be effectively eliminated, which makes it difficult to achieve the fair comparison of power generation performance among different wind farms. Thus, the evaluation indicator system and comprehensive evaluation method of wind farm power generation performance, including the influence of wind energy resource differences, are proposed in this paper to address the problems above, to which some new concepts such as resource conditions, ideal performance, reachable performance, actual performance, and performance loss are introduced in the proposed indicator system; the combination of statistical and comparative indicators are adopted to realize the quantitative evaluation, indicator decoupling, fair comparison, and loss attribution of wind farm power generation performance. The proposed comprehensive evaluation method is based on improved CRITIC (Criteria Importance though Intercrieria Correlation) weighting method, in which the uneven situation of different evaluation indicators and the comprehensive comparison of power generation performance among different wind farms shall be overcome and realized. Several sets of data from Chinese wind farms in service are used to validate the effectiveness and applicability of the proposed method by taking the comprehensive evaluation models based on CRITIC weighting method and entropy weighting method as the benchmarks. The results demonstrated that the proposed evaluation indicator system works in the quantitative evaluation and fair comparison of wind farm design, operation, and maintenance and traces the source of power generation performance loss. In addition, the results of the proposed comprehensive evaluation model are more in line with the actual power generation performance of wind farms and can be applied to the comprehensive evaluation and comparison of power generation performance of different wind farms.
Open AccessPower Generation Performance Indicators of Wind Farms Including the Influence of Wind Energy Resource Differences
The accurate evaluation and fair comparison of wind farms power generation performance is of great significance to the technical transformation and operation and maintenance management of wind farms. However, problems exist in the evaluation indicator systems such as confusion, coupling and broadness, and the influence of wind energy resource differences not being able to be effectively eliminated, which makes it difficult to achieve the fair comparison of power generation performance among different wind farms. Thus, the evaluation indicator system and comprehensive evaluation method of wind farm power generation performance, including the influence of wind energy resource differences, are proposed in this paper to address the problems above, to which some new concepts such as resource conditions, ideal performance, reachable performance, actual performance, and performance loss are introduced in the proposed indicator system; the combination of statistical and comparative indicators are adopted to realize the quantitative evaluation, indicator decoupling, fair comparison, and loss attribution of wind farm power generation performance. The proposed comprehensive evaluation method is based on improved CRITIC (Criteria Importance though Intercrieria Correlation) weighting method, in which the uneven situation of different evaluation indicators and the comprehensive comparison of power generation performance among different wind farms shall be overcome and realized. Several sets of data from Chinese wind farms in service are used to validate the effectiveness and applicability of the proposed method by taking the comprehensive evaluation models based on CRITIC weighting method and entropy weighting method as the benchmarks. The results demonstrated that the proposed evaluation indicator system works in the quantitative evaluation and fair comparison of wind farm design, operation, and maintenance and traces the source of power generation performance loss. In addition, the results of the proposed comprehensive evaluation model are more in line with the actual power generation performance of wind farms and can be applied to the comprehensive evaluation and comparison of power generation performance of different wind farms.
- Open Access
- 1 December 2020
- Published by Institution of Engineering and Technology (IET) in IET Renewable Power Generation
- Vol. 14 (18) , 3834-3842
Numerical simulation of wind turbine wake based on extended k‐epsilon turbulence model coupling with actuator disc considering nacelle and tower
The Reynolds-averaged Navier–Stokes (RANS) method coupling with the actuator disc model (ADM) is considered as a promising numerical simulation technology of wind turbine wake, and it is widely utilised in the aerodynamics of wind turbines and optimal layout of wind farms. The turbulence model is widely adopted, among the RANS-based turbulence models. However, the turbulence model easily overestimates the turbulence viscosity in the wake, which results in fast recovery of wake velocity and failure in wake forecasting. In addition, ADM with the oversimplified geometrical structure ignores the effects of nacelle and tower on the wind turbine wake, which further lowers the accuracy of wake simulation. Therefore, the numerical simulation of wind turbine wake based on the extended turbulence model of EI Kasmi coupling with ADM considering nacelle and tower is proposed. Comparing the results of Marchwood Engineering Laboratories (MEL) ABL wind tunnel measurements and TNO wind tunnel experiments, it has been found that the proposed model improves the simulation effect for the near wake and has a certain contribution to the wake prediction accuracy overall.- 1 December 2020
- Published by Institution of Engineering and Technology (IET) in IET Renewable Power Generation
- Vol. 14 (18) , 3834-3842
Open AccessNumerical simulation of wind turbine wake based on extended k‐epsilon turbulence model coupling with actuator disc considering nacelle and tower
The Reynolds-averaged Navier–Stokes (RANS) method coupling with the actuator disc model (ADM) is considered as a promising numerical simulation technology of wind turbine wake, and it is widely utilised in the aerodynamics of wind turbines and optimal layout of wind farms. The turbulence model is widely adopted, among the RANS-based turbulence models. However, the turbulence model easily overestimates the turbulence viscosity in the wake, which results in fast recovery of wake velocity and failure in wake forecasting. In addition, ADM with the oversimplified geometrical structure ignores the effects of nacelle and tower on the wind turbine wake, which further lowers the accuracy of wake simulation. Therefore, the numerical simulation of wind turbine wake based on the extended turbulence model of EI Kasmi coupling with ADM considering nacelle and tower is proposed. Comparing the results of Marchwood Engineering Laboratories (MEL) ABL wind tunnel measurements and TNO wind tunnel experiments, it has been found that the proposed model improves the simulation effect for the near wake and has a certain contribution to the wake prediction accuracy overall. - 22 July 2009
- Published by China Science Publishing & Media Ltd. in Journal of Computer Applications
- Vol. 29 (6) , 1523-1526
Three-layer topology architecture and topology control algorithm
- 22 July 2009
- Published by China Science Publishing & Media Ltd. in Journal of Computer Applications
- Vol. 29 (6) , 1523-1526
Three-layer topology architecture and topology control algorithm