@article{li_song_hu_lee_wu_rehm_lu_2024, title={Load Profile Inpainting for Missing Load Data Restoration and Baseline Estimation}, volume={15}, ISSN={["1949-3061"]}, url={https://doi.org/10.1109/TSG.2023.3293188}, DOI={10.1109/TSG.2023.3293188}, abstractNote={This paper introduces a Generative Adversarial Nets (GAN) based, Load Profile Inpainting Network (Load-PIN) for restoring missing load data segments and estimating the baseline for a demand response event. The inputs are time series load data before and after the inpainting period together with explanatory variables (e.g., weather data). We propose a Generator structure consisting of a coarse network and a fine-tuning network. The coarse network provides an initial estimation of the data segment in the inpainting period. The fine-tuning network consists of self-attention blocks and gated convolution layers for adjusting the initial estimations. Loss functions are specially designed for the fine-tuning and the discriminator networks to enhance both the point-to-point accuracy and realisticness of the results. We test the Load-PIN on three real-world data sets for two applications: patching missing data and deriving baselines of conservation voltage reduction (CVR) events. We benchmark the performance of Load-PIN with five existing deep-learning methods. Our simulation results show that, compared with the state-of-the-art methods, Load-PIN can handle varying-length missing data events and achieve 15%-30% accuracy improvement.}, number={2}, journal={IEEE TRANSACTIONS ON SMART GRID}, author={Li, Yiyan and Song, Lidong and Hu, Yi and Lee, Hanpyo and Wu, Di and Rehm, P. J. and Lu, Ning}, year={2024}, month={Mar}, pages={2251–2260} }
 @article{hu_li_song_lee_rehm_makdad_miller_lu_2024, title={MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations}, volume={15}, ISSN={["1949-3061"]}, url={https://doi.org/10.1109/TSG.2023.3302192}, DOI={10.1109/TSG.2023.3302192}, abstractNote={This paper presents a deep-learning framework, Multi-load Generative Adversarial Network (MultiLoad-GAN), for generating a group of synthetic load profiles (SLPs) simultaneously. The main contribution of MultiLoad-GAN is the capture of spatial-temporal correlations among a group of loads that are served by the same distribution transformer. This enables the generation of a large amount of correlated SLPs required for microgrid and distribution system studies. The novelty and uniqueness of the MultiLoad-GAN framework are three-fold. First, to the best of our knowledge, this is the first method for generating a group of load profiles bearing realistic spatial-temporal correlations simultaneously. Second, two complementary realisticness metrics for evaluating generated load profiles are developed: computing statistics based on domain knowledge and comparing high-level features via a deep-learning classifier. Third, to tackle data scarcity, a novel iterative data augmentation mechanism is developed to generate training samples for enhancing the training of both the classifier and the MultiLoad-GAN model. Simulation results show that MultiLoad-GAN can generate more realistic load profiles than existing approaches, especially in group level characteristics. With little finetuning, MultiLoad-GAN can be readily extended to generate a group of load or PV profiles for a feeder or a service area.}, number={2}, journal={IEEE TRANSACTIONS ON SMART GRID}, author={Hu, Yi and Li, Yiyan and Song, Lidong and Lee, Han Pyo and Rehm, P. J. and Makdad, Matthew and Miller, Edmond and Lu, Ning}, year={2024}, month={Mar}, pages={2309–2320} }
 @article{ye_kim_hu_lu_wu_rehm_2023, title={A Modified Sequence-to-point HVAC Load Disaggregation Algorithm}, ISSN={["1944-9925"]}, DOI={10.1109/PESGM52003.2023.10252553}, abstractNote={This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses load profiles as inputs. We propose three modifications. First, the input convolution layer is changed from 1D to 2D so that normalized temperature profiles are also used as inputs to the S2P model. Second, a drop-out layer is added to improve adaptability and generalizability so that the model trained in one area can be transferred to other geographical areas without labelled HVAC data. Third, a fine-tuning process is proposed for areas with a small amount of labelled HVAC data so that the pre-trained S2P model can be fine-tuned to achieve higher disaggregation accuracy (i.e., better transferability) in other areas. The model is first trained and tested using smart meter and sub-metered HVAC data collected in Austin, Texas. Then, the trained model is tested on two other areas: Boulder, Colorado and San Diego, California. Simulation results show that the proposed modified S2P algorithm outperforms the original S2P model and the support-vector machine based approach in accuracy, adaptability, and transferability.}, journal={2023 IEEE POWER & ENERGY SOCIETY GENERAL MEETING, PESGM}, author={Ye, Kai and Kim, Hyeonjin and Hu, Yi and Lu, Ning and Wu, Di and Rehm, P. J.}, year={2023} }