期刊
WATER
卷 13, 期 13, 页码 -出版社
MDPI
DOI: 10.3390/w13131773
关键词
3D CNN; feature engineering; global horizontal irradiance; machine learning algorithm; sky image
资金
- National Natural Science Foundation of China [62002016, U1836106]
- Beijing Natural Science Foundation [9204028]
- Guangdong Basic and Applied Basic Research Foundation [2019A1515111165, 2020A1515110431]
- Beijing Talents Plan [BJSQ2020008]
- Scientific and Technological Innovation Foundation of Shunde Graduate School of USTB [BK19BF006, BK20BF010]
- Interdisciplinary Research Project for Young Teachers of USTB (Fundamental Research Funds for the Central Universities) [FRF-IDRY-19-002]
A novel feature extracting method using a three-dimensional CNN is proposed for GHI forecasting, achieving a minimum average RMSE of 62 W/m2 with a 15.2% improvement in Skill score compared to the baseline method. Multiple machine learning algorithms are introduced to explore forecasting accuracy with different input features on a large dataset.
The instability and variability of solar irradiance induces great challenges for the management of photovoltaic water pumping systems. Accurate global horizontal irradiance (GHI) forecasting is a promising technique to solve this problem. To improve short-term GHI forecasting accuracy, ground-based sky image is valuable due to its correlation with solar generation. In previous studies, great efforts have been made to extract numerical features from sky image for data-driven solar irradiance forecasting methods, e.g., based on pixel-value color information, and based on the cloud motion detection method. In this work, we propose a novel feature extracting method for GHI forecasting that a three-dimensional (3D) convolutional neural network (CNN) is developed to extract features from sky images with efficient training strategies. Popular machine learning algorithms are introduced as GHI forecasting models and corresponding forecasting accuracy is fully explored with different input features on a large dataset. The numerical experiment illustrates that the minimum average root mean square error (RMSE) of 62 W/m2 is achieved by the proposed method with 15.2% improvement in Skill score against baseline forecasting method.
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