Wangbin Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wangbin Cao has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Xiaolin Liang
Hebei University
7 shared publications - Huawei Mei
North China Electric Power University 2 Department of Computer Baoding, 071003
3 shared publications Xiaolin Liang
3 shared publicationsZhengwei Hu
College of Electrical and Electronic Engineering North China Electric Power University Baoding China
3 shared publicationsFei Guo
2 shared publicationsGuangxing Wang
2 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 60220-60234
Joint Optimization of Task Offloading and Digital Twin Synchronization in SAGIVNs: A Personalized Federated Deep Reinforcement Learning Approach
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 60220-60234
Joint Optimization of Task Offloading and Digital Twin Synchronization in SAGIVNs: A Personalized Federated Deep Reinforcement Learning Approach
- Open Access
- 13 September 2026
- Published by Elsevier in SSRN Electronic Journal
A WM-STSM model for photovoltaic power forecasting with trend-seasonal enhancement
Accurate photovoltaic (PV) power forecasting is essential for the reliable operation of power systems. To enhance forecasting accuracy, this study proposes a Weather-Modulated State Tributary Space Model (WM-STSM) with a trend-seasonal enhancement strategy in a dual-branch forecasting framework. Specifically, WM-STSM differentiates the feedback contributions of historical states using content relevance and a local decay prior, while recursive state aggregation enables multi-hop, multi-path propagation, thereby improving the modeling of historical dependencies across time steps. A weather condition representation further modulates state feedback and readout, allowing the effective contribution of historical information to adapt to changing weather conditions. For trend-seasonal enhancement, first- and second-order differences with temporal downsampling are applied to the trend component, while depthwise one-dimensional convolution is applied to the seasonal component while preserving the original temporal resolution. This strategy strengthens the variation information of the trend component and the local fluctuations of the seasonal component, thereby improving the representation of their complementary temporal information. Comparative experiments on three public PV datasets against eight representative models demonstrate the superior overall performance of WM-STSM, including Transformer, Mamba, and Sessa. The proposed method achieves R2 values of 0.9983, 0.9944, and 0.9670 on the three datasets, respectively, indicating accurate and consistent forecasting performance.
- 13 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA WM-STSM model for photovoltaic power forecasting with trend-seasonal enhancement
Accurate photovoltaic (PV) power forecasting is essential for the reliable operation of power systems. To enhance forecasting accuracy, this study proposes a Weather-Modulated State Tributary Space Model (WM-STSM) with a trend-seasonal enhancement strategy in a dual-branch forecasting framework. Specifically, WM-STSM differentiates the feedback contributions of historical states using content relevance and a local decay prior, while recursive state aggregation enables multi-hop, multi-path propagation, thereby improving the modeling of historical dependencies across time steps. A weather condition representation further modulates state feedback and readout, allowing the effective contribution of historical information to adapt to changing weather conditions. For trend-seasonal enhancement, first- and second-order differences with temporal downsampling are applied to the trend component, while depthwise one-dimensional convolution is applied to the seasonal component while preserving the original temporal resolution. This strategy strengthens the variation information of the trend component and the local fluctuations of the seasonal component, thereby improving the representation of their complementary temporal information. Comparative experiments on three public PV datasets against eight representative models demonstrate the superior overall performance of WM-STSM, including Transformer, Mamba, and Sessa. The proposed method achieves R2 values of 0.9983, 0.9944, and 0.9670 on the three datasets, respectively, indicating accurate and consistent forecasting performance.
- Open Access
- 23 February 2026
- Published by Elsevier in SSRN Electronic Journal
Deep Learning Enhancement for Wind Power Prediction Using Pattern Memory Bank and Multi-scale Feature Perceptive Modulation
Accurate wind power prediction is essential for secure and economical grid operation. However, conventional deep learning models for wind power prediction struggle to capture long-term dependencies and adapt to the rapid shifts in feature importance caused by varying weather conditions. To addresses these limitations, this paper proposes an enhanced wind power prediction model by constructing the Pattern Memory Bank (PMB) and Multi-scale Feature Perceptive Modulation (MFPM) and integrating them into conventional deep learning models as a closed-loop architecture. The PMB consists of a context encoder, a memory matrix, a triple importance tracking system and a gated read/write mechanism. As a differentiable external memory architecture, the PMB stores and updates key climatic patterns, enabling the model to capture extended temporal dependencies. The MFPM incorporates gating mechanisms and dilated convolutions to dynamically adjust feature weights across multiple time scales, thereby enhancing the model ability to represent complex relationships. The closed-loop optimization architecture is further to facilitate bidirectional interaction between PMB and MFPM, which ensures that feature selection reinforces memory retrieval, while memory optimization guides feature enhancement, ultimately improving the prediction performance. Experiments are conducted based on real-world wind farm datasets and the results are compared with the widely used conventional deep learning models. It shows that the proposed model achieves reductions in mean squared error and mean absolute error of 51.59% and 35.90%, respectively. These results demonstrate that the proposed enhanced wind power prediction model using PMB and MFPM significantly improves the accuracy and reliability of wind power prediction.
- 23 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDeep Learning Enhancement for Wind Power Prediction Using Pattern Memory Bank and Multi-scale Feature Perceptive Modulation
Accurate wind power prediction is essential for secure and economical grid operation. However, conventional deep learning models for wind power prediction struggle to capture long-term dependencies and adapt to the rapid shifts in feature importance caused by varying weather conditions. To addresses these limitations, this paper proposes an enhanced wind power prediction model by constructing the Pattern Memory Bank (PMB) and Multi-scale Feature Perceptive Modulation (MFPM) and integrating them into conventional deep learning models as a closed-loop architecture. The PMB consists of a context encoder, a memory matrix, a triple importance tracking system and a gated read/write mechanism. As a differentiable external memory architecture, the PMB stores and updates key climatic patterns, enabling the model to capture extended temporal dependencies. The MFPM incorporates gating mechanisms and dilated convolutions to dynamically adjust feature weights across multiple time scales, thereby enhancing the model ability to represent complex relationships. The closed-loop optimization architecture is further to facilitate bidirectional interaction between PMB and MFPM, which ensures that feature selection reinforces memory retrieval, while memory optimization guides feature enhancement, ultimately improving the prediction performance. Experiments are conducted based on real-world wind farm datasets and the results are compared with the widely used conventional deep learning models. It shows that the proposed model achieves reductions in mean squared error and mean absolute error of 51.59% and 35.90%, respectively. These results demonstrate that the proposed enhanced wind power prediction model using PMB and MFPM significantly improves the accuracy and reliability of wind power prediction.
- Open Access
- 6 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 20 (1)
YOLO‐EPDS: A Small Object Detection Algorithm for Power Transmission Line Nut Spacing Looseness
To address the challenges of feature loss, inaccurate localization, and false or missed detections in small‐object detection of loosened and spaced nuts in power transmission lines, this study proposes an enhanced detection model, you only look once‐EPDS (YOLO‐EPDS), built upon an improved YOLOv9 framework. A RepNCSPELAN4_EMA module is integrated into the backbone network to incorporate a multi‐scale attention mechanism, enhancing the extraction of subtle nut texture features via cross‐space interactions and parallel multi‐branch feature recalibration. SPD‐Conv modules replace conventional downsampling layers in the backbone, effectively preserving spatial details in feature maps. Additionally, a RepNCSPELAN4_DCNv4 module employs dynamic deformable convolutions (DCNv4) to improve adaptability to geometrically deformed objects. The shape‐IoU loss function is utilized to optimize bounding box regression for small objects. Experimental results indicate that the proposed model achieves a mAP@50 of 79.7% on a self‐constructed transmission line nut dataset, outperforming the baseline by 4.3%. These enhancements synergistically increase confidence scores while reducing false‐positive and false‐negative rates, demonstrating superior capability in extracting defective features of loosened nuts and substantially improving the reliability of transmission line inspection.
- 6 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 20 (1)
Open AccessYOLO‐EPDS: A Small Object Detection Algorithm for Power Transmission Line Nut Spacing Looseness
To address the challenges of feature loss, inaccurate localization, and false or missed detections in small‐object detection of loosened and spaced nuts in power transmission lines, this study proposes an enhanced detection model, you only look once‐EPDS (YOLO‐EPDS), built upon an improved YOLOv9 framework. A RepNCSPELAN4_EMA module is integrated into the backbone network to incorporate a multi‐scale attention mechanism, enhancing the extraction of subtle nut texture features via cross‐space interactions and parallel multi‐branch feature recalibration. SPD‐Conv modules replace conventional downsampling layers in the backbone, effectively preserving spatial details in feature maps. Additionally, a RepNCSPELAN4_DCNv4 module employs dynamic deformable convolutions (DCNv4) to improve adaptability to geometrically deformed objects. The shape‐IoU loss function is utilized to optimize bounding box regression for small objects. Experimental results indicate that the proposed model achieves a mAP@50 of 79.7% on a self‐constructed transmission line nut dataset, outperforming the baseline by 4.3%. These enhancements synergistically increase confidence scores while reducing false‐positive and false‐negative rates, demonstrating superior capability in extracting defective features of loosened nuts and substantially improving the reliability of transmission line inspection.
- 17 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 304
A VE-CONV2D model for wind power prediction based on frequency feature reconstruction and time efficiency optimization
- 17 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 304
A VE-CONV2D model for wind power prediction based on frequency feature reconstruction and time efficiency optimization
- 19 June 2025
- Published by Elsevier in Measurement
- Vol. 256
A PGS-LSTM-attention model for imbalanced partial discharge detection based on SVM
- 19 June 2025
- Published by Elsevier in Measurement
- Vol. 256
A PGS-LSTM-attention model for imbalanced partial discharge detection based on SVM
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (14) , 27450-27460
AoI Minimization for RIS-Assisted V2V Relay System With Deep Reinforcement Learning
By leveraging the inherent ability of reconfigurable intelligence surface (RIS) to enhance wireless communication channels, the integration of RIS into simultaneous wireless information and power transfer (SWIPT)-enabled vehicle-to-vehicle (V2V) systems presents a promising solution to jointly enhance communication performance and energy harvesting efficiency. Building on this potential, an RIS-assisted V2V dual-hop relay system is constructed, which deploys RIS on the gate of relay vehicle user equipment (VUE), enabling efficient signal refraction from source to relay VUEs. To address the critical challenge of information freshness in such RIS-assisted systems, Age of Information (AoI) is adopted as the key metric. And the AoI optimization problem is formulated that jointly considers energy/data buffer capacity limitations, relay sustainability, and real-time packet freshness. To effectively resolve this optimization problem under dynamic vehicular conditions, a prioritized experience replay-dueling double deep Q network (PER-D3QN) scheme based on deep reinforcement learning (DRL) is proposed to make the optimal relay decision for AoI minimization. Numerical results demonstrate that the average AoI using the proposed PER-D3QN scheme is reduced by 20% compared with the existing schemes.
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (14) , 27450-27460
AoI Minimization for RIS-Assisted V2V Relay System With Deep Reinforcement Learning
By leveraging the inherent ability of reconfigurable intelligence surface (RIS) to enhance wireless communication channels, the integration of RIS into simultaneous wireless information and power transfer (SWIPT)-enabled vehicle-to-vehicle (V2V) systems presents a promising solution to jointly enhance communication performance and energy harvesting efficiency. Building on this potential, an RIS-assisted V2V dual-hop relay system is constructed, which deploys RIS on the gate of relay vehicle user equipment (VUE), enabling efficient signal refraction from source to relay VUEs. To address the critical challenge of information freshness in such RIS-assisted systems, Age of Information (AoI) is adopted as the key metric. And the AoI optimization problem is formulated that jointly considers energy/data buffer capacity limitations, relay sustainability, and real-time packet freshness. To effectively resolve this optimization problem under dynamic vehicular conditions, a prioritized experience replay-dueling double deep Q network (PER-D3QN) scheme based on deep reinforcement learning (DRL) is proposed to make the optimal relay decision for AoI minimization. Numerical results demonstrate that the average AoI using the proposed PER-D3QN scheme is reduced by 20% compared with the existing schemes.
- 3 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (15) , 29291-29301
Adaptive CR-NOMA/OMA Scheduling Scheme and AoI Minimization for Vehicular Communication Systems
The Age of Information (AoI) as a new metric in vehicular communication system has begun to attract public attention. This article considers a muti-user vehicular communication network, where the base station (BS) transmits with vehicle users by adaptively selecting orthogonal multiple access (OMA) or non-OMA (NOMA) schemes. The cognitive radio (CR) technology has been performed in NOMA system to improve the spectrum resources utilization. The adaptive CR-NOMA/OMA scheduling scheme is proposed based on user matching algorithm to reduce the user interference of intergroups and intragroup. And the scheduling schemes for primary user and secondary user of CR-NOMA system using the generate-at-will (GAW) and the generate-at-request (GAR) data generation models are proposed. Then the nonlinear average AoI of CR-NOMA and OMA systems are formulized. Based on GAW and GAR models, the minimizing average AoI are derived. The Quality of Service (QoS) as to average AoI and achievable rate with different vehicle speeds, signal to interference plus noise ratio (SINR), transmit power and outage probability are analyzed. The simulation results are compared with validated analysis and better performances of vehicular systems can be achieved.
- 3 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (15) , 29291-29301
Adaptive CR-NOMA/OMA Scheduling Scheme and AoI Minimization for Vehicular Communication Systems
The Age of Information (AoI) as a new metric in vehicular communication system has begun to attract public attention. This article considers a muti-user vehicular communication network, where the base station (BS) transmits with vehicle users by adaptively selecting orthogonal multiple access (OMA) or non-OMA (NOMA) schemes. The cognitive radio (CR) technology has been performed in NOMA system to improve the spectrum resources utilization. The adaptive CR-NOMA/OMA scheduling scheme is proposed based on user matching algorithm to reduce the user interference of intergroups and intragroup. And the scheduling schemes for primary user and secondary user of CR-NOMA system using the generate-at-will (GAW) and the generate-at-request (GAR) data generation models are proposed. Then the nonlinear average AoI of CR-NOMA and OMA systems are formulized. Based on GAW and GAR models, the minimizing average AoI are derived. The Quality of Service (QoS) as to average AoI and achievable rate with different vehicle speeds, signal to interference plus noise ratio (SINR), transmit power and outage probability are analyzed. The simulation results are compared with validated analysis and better performances of vehicular systems can be achieved.
- Open Access
- 24 October 2024
- Published by Institution of Engineering and Technology (IET) in IET Power Electronics
- Vol. 17 (15) , 2380-2392
A novel vehicle power line communication method based on switching ripple modulation
Power converters can perform power conversion and data transmission simultaneously. With the aim of mitigating the hardware requirements of vehicle power line communication (VPLC), a novel VPLC scheme based on switching ripple modulation (SRM) is proposed to eliminate the need for coupling circuits and specialized communication chips. By embedding data modulation techniques into traditional pulse width modulation systems, power/data multiplexing transmission is achieved by demodulating the voltage ripple on the DC bus. First, the theoretical foundation of the SRM is introduced, and power/data single carrier modulation using 2FSK and data demodulation based on the sliding discrete Fourier transform are provided. Subsequently, comprehensive analyses of the mutual influence between power conversion and communication in the buck converter are conducted. The impact of power conversion on communication primarily depends on the control loop compensation and perturbation depth. Moreover, the designs of the ripple conditioning circuit and communication frame are presented. Finally, an experimental prototype is constructed with two buck converters in parallel. The experimental results demonstrate a data transmission rate of 12.5 kbps within 3 m under steady‐state, transient input and output voltage, and transient load conditions, validating the correctness of the proposed methodology.
- 24 October 2024
- Published by Institution of Engineering and Technology (IET) in IET Power Electronics
- Vol. 17 (15) , 2380-2392
Open AccessA novel vehicle power line communication method based on switching ripple modulation
Power converters can perform power conversion and data transmission simultaneously. With the aim of mitigating the hardware requirements of vehicle power line communication (VPLC), a novel VPLC scheme based on switching ripple modulation (SRM) is proposed to eliminate the need for coupling circuits and specialized communication chips. By embedding data modulation techniques into traditional pulse width modulation systems, power/data multiplexing transmission is achieved by demodulating the voltage ripple on the DC bus. First, the theoretical foundation of the SRM is introduced, and power/data single carrier modulation using 2FSK and data demodulation based on the sliding discrete Fourier transform are provided. Subsequently, comprehensive analyses of the mutual influence between power conversion and communication in the buck converter are conducted. The impact of power conversion on communication primarily depends on the control loop compensation and perturbation depth. Moreover, the designs of the ripple conditioning circuit and communication frame are presented. Finally, an experimental prototype is constructed with two buck converters in parallel. The experimental results demonstrate a data transmission rate of 12.5 kbps within 3 m under steady‐state, transient input and output voltage, and transient load conditions, validating the correctness of the proposed methodology.