A Novel Forecasting Model for Solar Power Generation by a Deep Learning Framework with Data Preprocessing and Postprocessing
A Novel Forecasting Model for Solar Power Generation by a Deep Learning Framework with Data Preprocessing and Postprocessing
复制标题
基于深度学习框架的数据预处理和后处理的新型太阳能发电预测模型
DOI：
10.1109/icps54075.2022.9773862
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Hsin
中科院分区：
文献类型：
--
作者：
Quoc;Yuan;Q. Phan;Hsin
由于环境因素，光伏发电已成为最受欢迎的能源之一。然而，太阳能发电给电力系统运行带来了许多挑战。为了优化电力系统的安全性和降低运行成本，准确可靠的太阳能发电预测模型具有重要意义。该研究提出了一种深度学习方法来提高短期太阳能发电预测的性能，包括数据预处理，特征工程，核主成分分析，基于时间分类的门控递归单元网络训练模式，以及带有误差校正的后处理。在这项工作中，历史太阳能，太阳辐照度和数值天气预报（NWP）数据，如温度，辐照度，降雨量，风速，气压，湿度，被认为是输入数据集。作为一个案例研究，从十个太阳能站点在台湾的测量太阳能数据预测第二天的光伏发电输出与一个小时的分辨率。选用标准化均方根误差（NRMSE）、标准化平均绝对误差百分比（NMAPE）等误差指标来评价预测模型的性能。与其他基准模型（包括ANN，LSTM，XGBoost和单个GRU）相比，所提出的预测模型的实验结果显示了其高性能。此外，该模型还证明了基于误差校正的数据预处理和后处理的重要性。
Photovoltaic power has become one of the most popular energy due to environmental factors. However, solar power generation has brought many challenges for power system operations. To optimize safety and reduce costs of power system operations, an accurate and reliable solar power forecasting model is significance. This study proposes a deep learning method to improve the performance of short-term solar power forecasting, which includes data preprocessing, feature engineering, Kernel Principal Component Analysis, Gated Recurrent Unit Network training mode based on time of the day classification, and post processing with error correction. Both historical solar power, solar irradiance, and Numerical Weather Prediction (NWP) data, such as temperature, irradiance, rainfall, wind speed, air pressure, humidity, are considered as input dataset in this work. As a case study, the measured solar power data from ten solar sites in Taiwan are forecasted for the next day PV power outputs with one-hour resolution. The error index such as Normalized Root Mean Squared Error (NRMSE), Normalized Mean Absolute Percent Error (NMAPE) are chosen to evaluate the performance of forecasting models. Compared with other benchmark models including ANN, LSTM, XGBoost, and single GRU, the experimental results by the proposed forecasting model show its high performance. Furthermore, the proposed model also demonstrates the importance of data preprocessing and post processing based on error correction.