SinoGreenTech Academic Portal
SC
Verified CAS / Academic Author2 Decoded Studies

Prof. SHAO Chen

Key Laboratory of Distributed Energy Storage and Microgrid of Hebei Province (North China Electric Power University), Baoding 071003, China

Research Publications & English Decoded Briefs

Showing 2 publications
Acta Energiae Solaris Sinica2026DOI: 10.19912/j.0254-0096.tynxb.202608_9692

Regional Spatiotemporal Joint Rolling Load Forecasting Based on Stacking Ensemble Learning

Short-term load forecasting faces significant challenges due to the spatiotemporal heterogeneity of modern power systems with high renewable penetration. This study proposes a Stacking ensemble learning model that integrates spatiotemporal joint rolling sampling to enhance forecasting accuracy. The sampling scheme utilizes recent load data from other load zones to predict the target zone, maximizing the use of time-sensitive information. Heterogeneous base learners include eXtreme Gradient Boosting (XGBoost), Huber regression, Elastic Net (EN), Back Propagation Neural Network (BPNN), and Elman neural network. Hyperparameters are optimized via Bayesian optimization with Hyperband (BOHB) and cross-validation. A meta-learner based on a convolutional neural network-bidirectional long short-term memory-multi-head attention (CNN-BiLSTM-MultiHeadAttention) architecture performs deep feature fusion. Validation on a real-world load dataset from southern China demonstrates that the proposed model outperforms conventional sampling methods and common models, particularly in handling step loads and non-stationary fluctuations. The results confirm the feasibility and superiority of the integrated approach, achieving significant improvements in prediction accuracy and robustness.

SCIENCE CHINA Materials2025DOI: 10.1007/s40843-025-3284-x

Naphtho[2,3-b]thiophene diimide-terminated acceptor triads for improved n-type organic semiconductors

The development of high-performance n-type organic semiconductors is critical for advancing organic field-effect transistors (OFETs) and p-n complementary logic circuits. This study reports two novel n-type triple-acceptor triads, NTI-BTT and NTI-BT, based on naphtho[2,3-b]thiophene diimide (NTI), a monothiophene-extended naphthalene diimide (NDI). The influence of thiophene fusion versus spacer insertion on physicochemical and charge transport properties is systematically investigated. NTI-terminated triads exhibit enhanced electron-withdrawing capabilities, deeper energy levels, and more planar backbones compared to NDI-based counterparts. However, NTI-BT-based OFETs suffer a substantial drop in electron mobility to 0.004 cm2 V−1 s−1 due to polycrystalline structure with multiple grain boundaries that increase trap state density. In contrast, introducing thiophene spacers between NTI and benzothiadiazole units in NTI-BTT effectively enhances n-type charge transport by improving π-π interactions and reducing intermolecular distances, achieving a short π-π stacking distance of 3.45 Å. Consequently, NTI-BTT exhibits a significantly improved electron mobility of 0.13 cm2 V−1 s−1, four times higher than the NDI-based counterpart. These findings provide valuable insights into molecular design principles for high-performance n-type organic semiconductors, highlighting the impact of molecular structure and intermolecular interactions on charge transport.