期刊
SOLAR ENERGY
卷 224, 期 -, 页码 341-354出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.solener.2021.05.095
关键词
PV output prediction; Sky images; Convolutional neural network; Imbalanced dataset; Resampling; Data augmentation
资金
- Dubai Electricity and Water Authority (DEWA)
- U.S. Department of Energy (DOE) [DE-AC36-08GO28308]
- Laboratory Directed Research and Development (LDRD) Program at NREL
The study aims to address the imbalance in sky image datasets for PV output prediction, showing that resampling and data augmentation can effectively enhance model performance for now-casting tasks but have limited impact on forecasting tasks.
Integrating photovoltaics (PV) into electricity grids is challenged by potentially large fluctuations in power generation. In recent years, sky image-based PV output prediction using convolutional neural networks (CNNs) has emerged as a promising approach to forecasting fluctuations. A key challenge is imbalanced sky image datasets: because of the geography of solar PV system installations, sky image datasets are often rich in sunny condition data but deficient in cloudy condition data. This imbalance contrasts with the fact that model errors are dominated by cloudy condition performance. In this study, we attempt to remedy this by exploring the enrichment and augmentation of an imbalanced sky images dataset for two PV output prediction tasks: now-casting (predicting concurrent PV output) and forecasting (predicting 15-minute-ahead future PV output). We empirically examine the efficacy of using different resampling and data augmentation approaches to create a rebalanced dataset for model development. A three-stage greedy search is used to determine the optimal resampling approach, data augmentation techniques and over-sampling rate. The results show that for the now-cast problem, resampling and data augmentation can effectively enhance the model performance, reducing overall root mean squared error (RMSE) by an average of 4%, or a 15 std. (standard deviation) of improvement compared to the variability of the baseline model. In contrast, the treatment RMSE for the forecast problem nearly always overlaps the baseline performance at the +/- 2 std. level. The optimal resampling approach expands on the original dataset by over-sampling the minority cloudy data, with the best results from large over-sampling rate (e.g., 4 similar to 6 times over-sampling of cloudy images).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据