Zhengzhong Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhengzhong Gao has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Baokang Peng
College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
1 shared publication Chen Feng
1 shared publication- Fengqi Zang
Jining Coal Mine Safety Production Testing and Monitoring Center, Jining 272000, China
1 shared publication Haiyang Jiang
1 shared publication- Hua Duan
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China
1 shared publication Jian Zhao
University of Science and Technology Liaoning, China, China
1 shared publication
Latest Publications
- Open Access
A Short-Term Photovoltaic Power Forecasting Method Based on Multiscale Decomposition and Adaptive Optimization
Existing studies still have limitations in characterizing the complex temporal patterns of photovoltaic time series. In particular, current forecasting models often struggle to capture local abrupt fluctuations and nonlinear relationships among variables, while hyperparameter optimization remains challenging. To overcome these limitations, this paper proposes a CNN-iTransformer short-term photovoltaic power forecasting method based on multiscale decomposition and adaptive optimization. First, the original photovoltaic power time series is decomposed into trend, seasonal, and residual components using seasonal-trend decomposition based on Loess (STL). The residual component is then further decomposed through variational mode decomposition (VMD) to fully extract the latent multiscale temporal information embedded in the sequence. Second, a convolutional neural network (CNN) is employed to extract local fluctuation features, while the iTransformer is utilized to model the nonlinear relationships and long-term temporal dependencies between multiple meteorological variables and photovoltaic power. Finally, the Phototropic Growth Algorithm (PGA) is introduced to optimize key hyperparameters of the forecasting model, thereby improving its generalization capability and forecasting accuracy under multi-seasonal scenarios. Simulation experiments are conducted using real-world data from a photovoltaic power station in Alice Springs, Australia. The experimental results show that, under the same PGA optimization conditions, the proposed model reduces the root mean square error (RMSE) and mean absolute error (MAE) by approximately 19.12% and 17.43%, respectively, compared with the baseline iTransformer. Meanwhile, its performance is better than that of several mainstream deep learning models, which verifies the generalization ability and forecasting accuracy of the proposed method under complex seasonal variations.
Open AccessA Short-Term Photovoltaic Power Forecasting Method Based on Multiscale Decomposition and Adaptive Optimization
Existing studies still have limitations in characterizing the complex temporal patterns of photovoltaic time series. In particular, current forecasting models often struggle to capture local abrupt fluctuations and nonlinear relationships among variables, while hyperparameter optimization remains challenging. To overcome these limitations, this paper proposes a CNN-iTransformer short-term photovoltaic power forecasting method based on multiscale decomposition and adaptive optimization. First, the original photovoltaic power time series is decomposed into trend, seasonal, and residual components using seasonal-trend decomposition based on Loess (STL). The residual component is then further decomposed through variational mode decomposition (VMD) to fully extract the latent multiscale temporal information embedded in the sequence. Second, a convolutional neural network (CNN) is employed to extract local fluctuation features, while the iTransformer is utilized to model the nonlinear relationships and long-term temporal dependencies between multiple meteorological variables and photovoltaic power. Finally, the Phototropic Growth Algorithm (PGA) is introduced to optimize key hyperparameters of the forecasting model, thereby improving its generalization capability and forecasting accuracy under multi-seasonal scenarios. Simulation experiments are conducted using real-world data from a photovoltaic power station in Alice Springs, Australia. The experimental results show that, under the same PGA optimization conditions, the proposed model reduces the root mean square error (RMSE) and mean absolute error (MAE) by approximately 19.12% and 17.43%, respectively, compared with the baseline iTransformer. Meanwhile, its performance is better than that of several mainstream deep learning models, which verifies the generalization ability and forecasting accuracy of the proposed method under complex seasonal variations.
- Open Access
- 8 January 2024
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 11, 1296037
An ultra-short-term forecasting method for multivariate loads of user-level integrated energy systems in a microscopic perspective: based on multi-energy spatio-temporal coupling and dual-attention mechanism
An ultra-short-term multivariate load forecasting method under a microscopic perspective is proposed to address the characteristics of user-level integrated energy systems (UIES), which are small in scale and have large load fluctuations. Firstly, the spatio-temporal correlation of users’ energy use behavior within the UIES is analyzed, and a multivariate load input feature set in the form of a class image is constructed based on the various types of load units. Secondly, in order to maintain the feature independence and temporal integrity of each load during the feature extraction process, a deep neural network architecture with spatio-temporal coupling characteristics is designed. Among them, the multi-channel parallel convolutional neural network (MCNN) performs independent spatial feature extraction of the 2D load component pixel images at each moment in time, and feature fusion of various types of load features in high dimensional space. A bidirectional long short-term memory network (BiLSTM) is used as a feature sharing layer to perform temporal feature extraction on the fused load sequences. In addition, a spatial attention layer and a temporal attention layer are designed in this paper for the original input load pixel images and the fused load sequences, respectively, so that the model can better capture the important information. Finally, a multi-task learning approach based on the hard sharing mechanism achieves joint prediction of each load. The measured load data of a UIES is analyzed as an example to verify the superiority of the method proposed in this paper.
- 8 January 2024
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 11, 1296037
Open AccessAn ultra-short-term forecasting method for multivariate loads of user-level integrated energy systems in a microscopic perspective: based on multi-energy spatio-temporal coupling and dual-attention mechanism
An ultra-short-term multivariate load forecasting method under a microscopic perspective is proposed to address the characteristics of user-level integrated energy systems (UIES), which are small in scale and have large load fluctuations. Firstly, the spatio-temporal correlation of users’ energy use behavior within the UIES is analyzed, and a multivariate load input feature set in the form of a class image is constructed based on the various types of load units. Secondly, in order to maintain the feature independence and temporal integrity of each load during the feature extraction process, a deep neural network architecture with spatio-temporal coupling characteristics is designed. Among them, the multi-channel parallel convolutional neural network (MCNN) performs independent spatial feature extraction of the 2D load component pixel images at each moment in time, and feature fusion of various types of load features in high dimensional space. A bidirectional long short-term memory network (BiLSTM) is used as a feature sharing layer to perform temporal feature extraction on the fused load sequences. In addition, a spatial attention layer and a temporal attention layer are designed in this paper for the original input load pixel images and the fused load sequences, respectively, so that the model can better capture the important information. Finally, a multi-task learning approach based on the hard sharing mechanism achieves joint prediction of each load. The measured load data of a UIES is analyzed as an example to verify the superiority of the method proposed in this paper.
- Open Access
- 24 October 2023
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 11, 1291552
A novel distributing–collecting on-line insulation monitoring system and line selection technology for the DC supply system
At present, the power supply system of 5G base stations is a micro smart grid, it generally uses 240 V DC power supply with multiple branches, and leakage accidents will threaten personal and property safety, so it is vital to identify the fault line accurately and remove the faults rapidly. In this paper, the leakage phenomenon of transmission lines in the HVDC power supply system of a 5G communication base station is studied. To address the issue of multi-branch line leakage diagnosis and line selection in the 240 V DC system, a new distributed DC insulation monitoring and fault line selection technology and system are proposed. The distributed DC insulation monitoring line selection technology is used to collect the leakage current of each branch by setting a unique single-core DC leakage transformer and process the signal primarily. In addition, a high-resistance bridge switchgear is added to the bus bar. According to different leakage currents caused by the imbalance of the bridge before and after the switch, the insulation resistance of electrodes to the ground is calculated accurately, which solves the problem that the current technology cannot judge the fault of the positive and negative electrodes to the ground at the same time. Through both simulation and prototype experiments, the feasibility of this technology and system device in line insulation monitoring and line selection of the HVDC communication base station power supply system is verified.
- 24 October 2023
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 11, 1291552
Open AccessA novel distributing–collecting on-line insulation monitoring system and line selection technology for the DC supply system
At present, the power supply system of 5G base stations is a micro smart grid, it generally uses 240 V DC power supply with multiple branches, and leakage accidents will threaten personal and property safety, so it is vital to identify the fault line accurately and remove the faults rapidly. In this paper, the leakage phenomenon of transmission lines in the HVDC power supply system of a 5G communication base station is studied. To address the issue of multi-branch line leakage diagnosis and line selection in the 240 V DC system, a new distributed DC insulation monitoring and fault line selection technology and system are proposed. The distributed DC insulation monitoring line selection technology is used to collect the leakage current of each branch by setting a unique single-core DC leakage transformer and process the signal primarily. In addition, a high-resistance bridge switchgear is added to the bus bar. According to different leakage currents caused by the imbalance of the bridge before and after the switch, the insulation resistance of electrodes to the ground is calculated accurately, which solves the problem that the current technology cannot judge the fault of the positive and negative electrodes to the ground at the same time. Through both simulation and prototype experiments, the feasibility of this technology and system device in line insulation monitoring and line selection of the HVDC communication base station power supply system is verified.
- 25 March 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 50 (9) , 2779-2799
Comprehensive learning cuckoo search with chaos-lambda method for solving economic dispatch problems
- 25 March 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 50 (9) , 2779-2799
Comprehensive learning cuckoo search with chaos-lambda method for solving economic dispatch problems