Resampling and Data Augmentation for Short-Term PV Output Prediction Based on an Imbalanced Sky Images Dataset Using Convolutional Neural Networks

Yuhao Nie, Ahmed Zamzam, Adam Brandt

Research output: Contribution to journalArticlepeer-review

38 Scopus Citations

Abstract

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: nowcasting (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 nowcast 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 ~ 6 times over-sampling of cloudy images).

Original languageAmerican English
Pages (from-to)341-354
Number of pages14
JournalSolar Energy
Volume224
DOIs
StatePublished - Aug 2021

Bibliographical note

Publisher Copyright:
© 2021

NREL Publication Number

  • NREL/JA-5D00-80184

Keywords

  • Convolutional neural network
  • Data augmentation
  • Imbalanced dataset
  • PV output prediction
  • Resampling
  • Sky images

Fingerprint

Dive into the research topics of 'Resampling and Data Augmentation for Short-Term PV Output Prediction Based on an Imbalanced Sky Images Dataset Using Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this