Di 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
Di Zhang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Jizhong Zhu
South China University of Technology
5 shared publications - Le Zhang
School of Electric Power Engineering, South China University of Technology, Guangzhou, China
4 shared publications - Shenglin Li
School of Electric Power Engineering, South China University of Technology, Guangzhou, China
2 shared publications - Alberto Borghetti
University of Bologna
1 shared publication - Chaohui Zhao
School of Electrical Engineering, Shanghai Dianji University, Shanghai, China
1 shared publication Feng Xiang
Shanghai Dianji University
1 shared publication
Latest Publications
- 14 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 62 (3) , 4307-4321
Electricity-Carbon Coordinated Optimal Dispatch for Multiple Industrial Parks Considering Life Cycle Carbon Emissions on the Power Generation Side
Current electricity-carbon markets commonly assume that renewable energy generation provides zero-carbon electricity. However, from a lifecycle perspective, carbon emissions persist during the construction, maintenance, and decommissioning phases of renewable energy systems. To address this gap, by incorporating lifecycle carbon emissions from renewable energy systems and thermal power units, a Lifecycle-Internalized Carbon Offset Mechanism is proposed to enforce renewable energy systems to internalize their lifecycle carbon responsibilities. Furthermore, based on carbon emission flow theory, a bi-level optimal dispatch framework is developed for electricity-carbon coordination across multiple industrial parks. The upper-level model formulates a distribution network dispatch strategy incorporating the proposed mechanism and computes dynamic nodal carbon intensity. The lower-level model performs low-carbon economic dispatch for industrial parks, aiming to minimize operational and carbon emission costs based on the upper-level-derived carbon intensity values. The optimal production and electricity-carbon trading strategies are derived through iterative coordination between the two levels, and a dichotomy-based heuristic method is employed to mitigate solution oscillations. Case study results demonstrate that the proposed method effectively reduces carbon emissions from industrial park operations while maintaining economic efficiency.
- 14 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 62 (3) , 4307-4321
Electricity-Carbon Coordinated Optimal Dispatch for Multiple Industrial Parks Considering Life Cycle Carbon Emissions on the Power Generation Side
Current electricity-carbon markets commonly assume that renewable energy generation provides zero-carbon electricity. However, from a lifecycle perspective, carbon emissions persist during the construction, maintenance, and decommissioning phases of renewable energy systems. To address this gap, by incorporating lifecycle carbon emissions from renewable energy systems and thermal power units, a Lifecycle-Internalized Carbon Offset Mechanism is proposed to enforce renewable energy systems to internalize their lifecycle carbon responsibilities. Furthermore, based on carbon emission flow theory, a bi-level optimal dispatch framework is developed for electricity-carbon coordination across multiple industrial parks. The upper-level model formulates a distribution network dispatch strategy incorporating the proposed mechanism and computes dynamic nodal carbon intensity. The lower-level model performs low-carbon economic dispatch for industrial parks, aiming to minimize operational and carbon emission costs based on the upper-level-derived carbon intensity values. The optimal production and electricity-carbon trading strategies are derived through iterative coordination between the two levels, and a dichotomy-based heuristic method is employed to mitigate solution oscillations. Case study results demonstrate that the proposed method effectively reduces carbon emissions from industrial park operations while maintaining economic efficiency.
- Open Access
- 18 November 2024
- Published by MDPI AG in Electronics
- Vol. 13 (22) , 4513
Dynamic Gust Detection and Conditional Sequence Modeling for Ultra-Short-Term Wind Speed Prediction
As the foundation for optimizing wind turbine operations and ensuring energy stability, wind speed forecasting directly impacts the safe operation of the power grid, the rationality of grid planning, and the balance of supply and demand. Furthermore, gust events, characterized by sudden and rapid wind speed fluctuations, pose significant challenges for ultra-short-term wind speed forecasting, making the data more complex and thus harder to predict accurately. To address this issue, this paper proposes a novel hybrid model that combines dynamic gust detection with Conditional Long Short-Term Memory (Conditional LSTM) and incorporates dynamic window adjustment and wind speed difference threshold screening methods. The model dynamically adjusts the window size to accurately detect gust events and uses a conditional LSTM model to adjust predictions based on gust and non-gust conditions. Experimental results show that the proposed model exhibits higher prediction accuracy across various wind speed scenarios, particularly during gust events. Through detailed experiments using data from a single actual wind farm, the effectiveness and practicality of the proposed hybrid model are demonstrated. The experimental results indicate that the proposed model outperforms contrast models, especially in handling gust events, significantly enhancing the robustness of ultra-short-term wind speed predictions.
- 18 November 2024
- Published by MDPI AG in Electronics
- Vol. 13 (22) , 4513
Open AccessDynamic Gust Detection and Conditional Sequence Modeling for Ultra-Short-Term Wind Speed Prediction
As the foundation for optimizing wind turbine operations and ensuring energy stability, wind speed forecasting directly impacts the safe operation of the power grid, the rationality of grid planning, and the balance of supply and demand. Furthermore, gust events, characterized by sudden and rapid wind speed fluctuations, pose significant challenges for ultra-short-term wind speed forecasting, making the data more complex and thus harder to predict accurately. To address this issue, this paper proposes a novel hybrid model that combines dynamic gust detection with Conditional Long Short-Term Memory (Conditional LSTM) and incorporates dynamic window adjustment and wind speed difference threshold screening methods. The model dynamically adjusts the window size to accurately detect gust events and uses a conditional LSTM model to adjust predictions based on gust and non-gust conditions. Experimental results show that the proposed model exhibits higher prediction accuracy across various wind speed scenarios, particularly during gust events. Through detailed experiments using data from a single actual wind farm, the effectiveness and practicality of the proposed hybrid model are demonstrated. The experimental results indicate that the proposed model outperforms contrast models, especially in handling gust events, significantly enhancing the robustness of ultra-short-term wind speed predictions.
- 17 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 61 (1) , 1399-1409
Probabilistic Wind Power Prediction Using Incremental Bayesian Stochastic Configuration Network Under Concept Drift Environment
Standard data-driven probabilistic wind power prediction solutions typically assume a static exogenous environment, where historical data contains all information desired to predict the future. Unfortunately, the practical industrial data distribution is time-varying and unforeseen, known as concept drift (CD), violating the assumption. To address this challenge, an incremental Bayesian stochastic configuration network is proposed to enhance prediction accuracy under CD environments. Concretely, Stochastic Configuration Network (SCN), a lightweight and iteration-free random weight neural network, is explored to model latent relationships between variables and targets. Subsequently, Bayesian inference updates SCN's output layer parameters, approximating the parameter posterior distribution and generating the probabilistic prediction model BSCN. To manage CD, Maximum Mean Discrepancy and Continuous Ranked Probability Score are employed to detect virtual and real drifts. The real drift serves as a trigger for the incremental learning of the BSCN, with a specifically designed incremental update strategy to facilitate this process. Extensive experiments demonstrate that the proposed method can continuously learn new modes without forgetting and significantly improve probabilistic wind power prediction accuracy in dynamic CD environments.
- 17 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 61 (1) , 1399-1409
Probabilistic Wind Power Prediction Using Incremental Bayesian Stochastic Configuration Network Under Concept Drift Environment
Standard data-driven probabilistic wind power prediction solutions typically assume a static exogenous environment, where historical data contains all information desired to predict the future. Unfortunately, the practical industrial data distribution is time-varying and unforeseen, known as concept drift (CD), violating the assumption. To address this challenge, an incremental Bayesian stochastic configuration network is proposed to enhance prediction accuracy under CD environments. Concretely, Stochastic Configuration Network (SCN), a lightweight and iteration-free random weight neural network, is explored to model latent relationships between variables and targets. Subsequently, Bayesian inference updates SCN's output layer parameters, approximating the parameter posterior distribution and generating the probabilistic prediction model BSCN. To manage CD, Maximum Mean Discrepancy and Continuous Ranked Probability Score are employed to detect virtual and real drifts. The real drift serves as a trigger for the incremental learning of the BSCN, with a specifically designed incremental update strategy to facilitate this process. Extensive experiments demonstrate that the proposed method can continuously learn new modes without forgetting and significantly improve probabilistic wind power prediction accuracy in dynamic CD environments.
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 16 (1) , 801-815
Resilience Enhancement in Urban Power-Transportation System Considering Multiple Uncertainties Against Ice Storms
This paper proposes a resilience enhancement strategy for the urban power-transportation system (UPTS) against ice storms. To address the uncertain impact of ice storms on the UPTS, a Wasserstein distance-based ambiguity set is established to describe the probability distribution of failure probabilities of power lines and reduction of transportation capacities. The de-icing schedule, liquefied natural gas (LNG) pre-allocation, mobile emergency generators (MEGs) scheduling and Vehicle-to-grid (V2G) services are coordinated to minimize the load shedding and operating costs of the UPTS. A distributionally robust chance constraint (DRCC) model is established and reformulated by conditional value-at-risk (CVaR) approximation, where the Lagrangian relaxation method is applied to protect the privacy of the independent system and accelerate the solution process. Case studies demonstrate the effectiveness of the proposed strategy for the UPTS in terms of operating costs, power load shedding and robustness to multiple uncertainties.
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 16 (1) , 801-815
Resilience Enhancement in Urban Power-Transportation System Considering Multiple Uncertainties Against Ice Storms
This paper proposes a resilience enhancement strategy for the urban power-transportation system (UPTS) against ice storms. To address the uncertain impact of ice storms on the UPTS, a Wasserstein distance-based ambiguity set is established to describe the probability distribution of failure probabilities of power lines and reduction of transportation capacities. The de-icing schedule, liquefied natural gas (LNG) pre-allocation, mobile emergency generators (MEGs) scheduling and Vehicle-to-grid (V2G) services are coordinated to minimize the load shedding and operating costs of the UPTS. A distributionally robust chance constraint (DRCC) model is established and reformulated by conditional value-at-risk (CVaR) approximation, where the Lagrangian relaxation method is applied to protect the privacy of the independent system and accelerate the solution process. Case studies demonstrate the effectiveness of the proposed strategy for the UPTS in terms of operating costs, power load shedding and robustness to multiple uncertainties.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Online Fault Line Detection in Small-Sample and Streaming Data Environments
This paper focuses on medium and low voltage networks with neutral grounded through arc-suppression coils. Standard data-driven fault line detection (FLD) approaches assume that the training sample is sufficient, static, and reusable. In practical scenarios, such approaches may be infeasible due to the sporadic and temporary nature of single-phase-to-ground faults, which provide insufficient fault samples, and due to large-scale high-speed dynamic data streams associated with measurements. To tackle these issues, the paper proposes a novel FLD scheme based on personalized federated learning (PFL) and incremental stochastic configuration networks (SCN) for small-sample and streaming data environments. Concretely, the SCN, a concise non-iterative neural network, is exploited as the FLD classifier. To adapt effectively to dynamic and non-reusable environments, an incremental SCN is proposed that can learn fault features without experiencing forgetting when dealing with streaming data. The proposed FLD scheme based on PFL selectively aggregates fault features from multiple substations. This approach addresses the challenge of limited sample sizes while preserving the personalization of each local model. Extensive experiment results using real data show that the proposed method can significantly improve accuracy when dealing with small samples and continuously learn fault features in streaming data.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Online Fault Line Detection in Small-Sample and Streaming Data Environments
This paper focuses on medium and low voltage networks with neutral grounded through arc-suppression coils. Standard data-driven fault line detection (FLD) approaches assume that the training sample is sufficient, static, and reusable. In practical scenarios, such approaches may be infeasible due to the sporadic and temporary nature of single-phase-to-ground faults, which provide insufficient fault samples, and due to large-scale high-speed dynamic data streams associated with measurements. To tackle these issues, the paper proposes a novel FLD scheme based on personalized federated learning (PFL) and incremental stochastic configuration networks (SCN) for small-sample and streaming data environments. Concretely, the SCN, a concise non-iterative neural network, is exploited as the FLD classifier. To adapt effectively to dynamic and non-reusable environments, an incremental SCN is proposed that can learn fault features without experiencing forgetting when dealing with streaming data. The proposed FLD scheme based on PFL selectively aggregates fault features from multiple substations. This approach addresses the challenge of limited sample sizes while preserving the personalization of each local model. Extensive experiment results using real data show that the proposed method can significantly improve accuracy when dealing with small samples and continuously learn fault features in streaming data.
- 18 October 2016
- Published by Springer Nature
- p. 507-533
Energy Management of Smart Homes with Microgrid
- 18 October 2016
- Published by Springer Nature
- p. 507-533
Energy Management of Smart Homes with Microgrid
- 13 March 2012
- Published by Springer Nature
- p. 873-883
Analysis of Influence Factors of SRM Torque Ripple on Current Chopping Control Condition
- 13 March 2012
- Published by Springer Nature
- p. 873-883
Analysis of Influence Factors of SRM Torque Ripple on Current Chopping Control Condition