Aodong Shen

Dr. Aodong Shen

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
12 September 2024 in IEEE Access
Verified
Journal Article
Open access
LSLiangliang Song
Liangliang Song
XHXiang Huang
Xiang Huang
SZShuyi Zhuang
Shuyi Zhuang
ASAodong Shen
Aodong Shen
PXPeidong Xu
Peidong Xu
Table Structure Recognition (TSR) is pivotal in document analysis, especially in end-toend automated identification, which profoundly impacts decision-making and efficiency spanning diverse fields such as power industry, education, healthcare, and scientific papers. However, accurately identifying table structures remains challenging due to complex layouts and irregular distortions. Considering the complex structure of tables in power relay protection systems, this study proposes a novel end-to-end TSR model, leveraging deep learning and innovative modules to address these challenges. Specifically, the new model TSR-Net replaces YOLOv8's backbone with our proposed DSConv-Variants, improving accuracy and reducing parameters. Additionally, a Multi-Scale Attention Module (MAM) captures semantic features efficiently, while a Dynamic Calibration Module (DCM) enhances cross-layer fusion. Experimental results demonstrate the superior performance of our approach on public benchmarks, showcasing its utility for TSR.

23 December 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
ASAodong Shen
Aodong Shen
XWXingyue Wang
Xingyue Wang
HXHonghua Xu
Honghua Xu
JZJichao Zhan
Jichao Zhan
SZSuyang Zhou
Suyang Zhou
YKYouyong Kong
Youyong Kong
Load forecasting plays a vital role in key areas such as energy forecasting and resource management. Traditional forecasting methods are often limited in dealing with shifts in statistical distribution and dynamic changes in periodic parameters of load data, making it difficult to capture complex temporal dependencies and periodic change patterns. To address this challenge, we transform load data into the frequency domain and use a fine-tuned large language model for forecasting. Specifically, we propose the Frequency-Based Spatial–Temporal Mixture Learning Model (FSTML), which uses (1) a Frequency-domain Global Learning Module (FGLM), (2) Temporal-Dimension Learning Module (TDLM), and (3) Spatial-Dimension Learning Module (SDLM) to process load data and extract comprehensive temporal patterns. FGLM transfers load data to the frequency domain and provides the model with a frequency-domain global feature representation of load data. The TDLM and SDLM fine tune the pre-trained large language model in the time dimension and space dimension, respectively, extracting the temporal dependency and spatial dependency of load data, respectively, thereby extracting the spatial–temporal pattern of load data. FSTML achieves the best performance in the forecasting task on two public load datasets, and the forecasting accuracy is significantly improved. The high-precision load forecasting model proposed in this study can significantly improve the operational efficiency of power systems and the integration capacity of renewable energy sources, thereby supporting the sustainable development of the power industry in three dimensions: energy optimization, emission reduction, and economic operation.

28 December 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ZXZhihao Xu
Zhihao Xu
YKYouyong Kong
Youyong Kong
ASAodong Shen
Aodong Shen
Wind power forecasting is critical to renewable energy generation, as accurate predictions are essential for the efficient and reliable operation of power systems. However, wind power output is inherently unstable and is strongly affected by meteorological factors such as wind speed, wind direction, and atmospheric pressure. Weather conditions and wind power data are recorded by sensors installed in wind turbines, which may be damaged or malfunction during extreme or sudden weather events. Such failures can lead to inaccurate, incomplete, or missing data, thereby degrading data quality and, consequently, forecasting performance. To address these challenges, we propose a method that integrates a pre-trained large-scale language model (LLM) with the spatiotemporal characteristics of wind power networks, aiming to capture both meteorological variability and the complexity of wind farm terrain. Specifically, we design a spatiotemporal graph neural network based on multi-view maps as an encoder. The resulting embedded spatiotemporal map sequences are aligned with textual representations, concatenated with prompt embeddings, and then fed into a frozen LLM to predict future wind turbine power generation sequences. In addition, to mitigate anomalies and missing values caused by sensor malfunctions, we introduce a novel frequency-domain learning-based interpolation method that enhances data correlations and effectively reconstructs missing observations. Experiments conducted on real-world wind power datasets demonstrate that the proposed approach outperforms state-of-the-art methods, achieving root mean square errors of 17.776 kW and 50.029 kW for 24-h and 48-h forecasts, respectively. These results indicate substantial improvements in both accuracy and robustness, highlighting the strong practical potential of the proposed method for wind power forecasting in the renewable energy industry.

1 July 2026 in Electronics
Verified
Journal Article
Open access
PDF file
ASAodong Shen
Aodong Shen
ZLZesheng Lai
Zesheng Lai
TWTianwei Wang
Tianwei Wang
Time series forecasting plays a fundamental role across diverse domains including energy systems, transportation, healthcare, etc. Despite significant advancements in forecasting models, their practical application often encounters challenges due to distribution shifts, where the statistical properties of testing data deviate from those of training data. Such shifts can severely degrade model performance, necessitating frequent retraining with the latest data to maintain performance. To address this limitation, we introduce FreqMoE, a framework designed for out-of-distribution (OOD) scenarios. Our proposed method applies random masking as a regularization strategy and utilizes a Mixture of Experts (MoE) network to encourage robust frequency-domain representations. Each expert focuses on modeling specific frequency characteristics and the MoE dynamically selects experts based on spectrum embedding, capturing frequency-domain patterns by modeling sequences in the frequency domain. Experimental results on diverse real-world datasets demonstrate that FreqMoE achieves competitive or leading performance compared to existing approaches in both prediction accuracy and robustness under OOD scenarios, demonstrating improved robustness under naturalistic temporal distribution shifts.