Hong Wang

Dr. Hong Wang


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 November 2022 in Applied Energy
Verified
Journal Article
Open access
LYLei Yan
Lei Yan
WTWei Tian
Wei Tian
HWHong Wang
Hong Wang
XHXing Hao
Xing Hao
ZLZuyi Li
Zuyi Li

22 September 2020 in IEEE Transactions on Smart Grid
Verified
Journal Article
Closed access
HWHong Wang
Hong Wang
LQLinhai Qi
Linhai Qi
LYLei Yan
Lei Yan
ZLZuyi Li
Zuyi Li
Load data is an essential input for power system analysis and management. However, traditional load analysis methods do not fit well with emerging deep learning models that may require image matrix as input, such as Convolutional Neural Network (CNN) and Generative Adversarial Nets (GAN). This paper proposes a novel analysis method “Load Photo” to create the required image matrix for various loads in power systems by using the HSV color space. A load photo is a 2-D pixel graphical representation of load, in which the x-axis represents sampling time points (e.g., hours) for every day from Sunday to Saturday, the y-axis represents weeks from the first week till the last week, and the pixel color demonstrates the normalized load. A load photo stores all essential load-related parameters such as start time, end time, and sampling period. A load photo can be used to characterize the energy consumption pattern of any load type, just like taking a photo for the load that clearly demonstrates the load’s behavior. Furthermore, a load photo could work before feature selection as an input to deep learning models. Accordingly, the latest advancement in deep learning models related to image processing can be easily applied to the analysis and data mining of load data.

20 March 2020 in Journal of Electrical Engineering & Technology
Verified
Journal Article
Closed access
PDF file
HWHong Wang
Hong Wang
LQLinhai Qi
Linhai Qi
YMYongshuo Ma
Yongshuo Ma
JJJiehui Jia
Jiehui Jia
ZZZhicong Zheng
Zhicong Zheng

14 August 2025 in Electronics
Verified
Journal Article
Open access
PDF file
PZPeng Zhang
Peng Zhang
LPLing Pan
Ling Pan
CXCien Xiao
Cien Xiao
WWWei Wu
Wei Wu
HWHong Wang
Hong Wang
Due to the challenges of low resolution and incomplete data in the process of power data collection and transmission and the lack of detail in the power data super-resolution algorithm, this paper proposes a generative adversarial network super-resolution perception model based on a linear attention mechanism. It uses the adversarial training mechanism of generator and discriminator to restore high-resolution power data from low-resolution power data. In the generator, the deep residual network structure is innovatively combined with the multi-scale linear attention mechanism, and the linear rectifier unit that can be dynamically learned is combined to improve the model’s ability to extract power data features. The discriminator employs a multi-scale architecture embedded with a dual-attention module, integrating both global and local features to enhance the model’s ability to capture fine details. Experiments were conducted on a dataset of multiple monitoring points in a city in East China. Experimental results indicate that the proposed Lmla-GAN delivers an overall average SSIM improvement of approximately 6.7% over the four baseline models-Bicubic, SRCNN, SubPixelCNN, and VDSR.

16 February 2023 in IEEJ Transactions on Electrical and Electronic Engineering
Verified
Journal Article
Closed access
HXHeju Xiao
Heju Xiao
HWHong Wang
Hong Wang
LQLinhai Qi
Linhai Qi

4 February 2026 in Energies
Verified
Journal Article
Open access
PDF file
PZPeng Zhang
Peng Zhang
LPLing Pan
Ling Pan
CXCien Xiao
Cien Xiao
RZRuiyun Zhao
Ruiyun Zhao
YJYan Jiangyu
Yan Jiangyu
HWHong Wang
Hong Wang
Nonlinear loads are widely applied, making the generation mechanism of grid harmonics increasingly intricate. However, high-precision monitoring devices suffer from high deployment costs and limited coverage. This poses a major challenge to directly acquiring harmonic voltages at some nodes. To solve this problem, this paper proposes a harmonic state estimation method based on a Dual-Stream Adaptive Fusion Generative Adversarial Network (DSAF-GAN), with an innovative design in its generator architecture. A dual-path generator is developed to extract multi-scale features through heterogeneous network branches collaboratively. The ResNet-GRU path integrates convolutional residual modules with Bidirectional Gated Recurrent Units (Bi-GRUs). It effectively captures local spatial patterns and temporal dynamic characteristics of time-series data. The multi-layer perceptron (MLP) path focuses on mining global nonlinear correlations, thereby enhancing the overall feature-expressing capability. An adaptive weight fusion module (Attention Weight Net) fuses the outputs of the two paths. It dynamically allocates contribution weights, improving the model’s flexibility and generalization performance. Experimental results show that the proposed DSAF-GAN can accurately reconstruct the harmonic voltage component content rate of missing nodes.