@article{chou_nisar_haldar_queiroz_2025, title={Day-ahead Solar Power Forecasting in a Large-scale System Using Statistical and Neural Network Models}, DOI={10.1109/pesgm52009.2025.11225770}, author={Chou, Yen-Hsi and Nisar, Shubh and Haldar, Arundhuti and Queiroz, Anderson Rodrigo}, year={2025}, month={Jul} }
 @article{haldar_nisar_chou_queiroz_2025, title={Load Forecasting Using Recurrent and Transformer Neural Networks: A Comprehensive Analysis Across Multi-Time Scales}, DOI={10.1109/pesgm52009.2025.11225674}, author={Haldar, Arundhuti and Nisar, Shubh and Chou, Yen-Hsi and Queiroz, Anderson Rodrigo}, year={2025}, month={Jul} }
 @article{haldar_chou_nisar_queiroz_2025, title={Transfer Learning Based Load Forecasting using Recurrent and Transformer Neural Networks}, DOI={10.1109/naps66256.2025.11272430}, abstractNote={Accurate load forecasting is crucial for grid reliability, operational effectiveness, and energy planning as electricity demand becomes more dependent on weather volatility and integration of distributed energy resources. The scarcity of high-quality historical data is detrimental to accurate forecasting capabilities. This paper presents a transfer learning based approach that enhances load forecasting capabilities in a data-constrained zone by training on data-rich regions using advanced neural network structures like Long Short-Term Memory, Gated Recurrent Units, Bidirectional Recurrent Neural Networks, and Transformer Neural Networks. By pretraining the models on high-resolution data from California, Texas, and New York and fine-tuning on sparse data from New Mexico, the results demonstrate that transfer learning significantly improves prediction accuracy while reducing training requirements. The Transformer model outperforms other neural network architectures, and it remains accurate even with coarse-grained input data. Furthermore, simple and weighted averaging over the forecasted values also elevate the prediction accuracy. These results form the basis for combining transfer learning and deep learning for scalable and precise load forecasting in heterogeneous and data-constrained power grids.}, author={Haldar, Arundhuti and Chou, Yen-Hsi and Nisar, Shubh and Queiroz, Anderson Rodrigo}, year={2025}, month={Oct} }
 @article{chou_faria_queiroz_2025, title={Transfer Learning and Convolutional Neural Networks for Solar Photovoltaic Systems Detection in Distributed Power Grids}, DOI={10.2139/ssrn.5174461}, journal={SSRN Electronic Journal}, author={Chou, Yen-Hsi and Faria, Victor and Queiroz, Anderson Rodrigo}, year={2025}, month={Jan} }