Lee Da-Sheng, Lai Chih-Wei, Fu Shih-Kai
National Taipei University of Technology Energy and Refrigerating Air-conditioning Engineering, Room 610, College of Mechanical & Electrical Engineering, Integrated Technology Complex, No.1, Sec. 3, Zhongxiao E. Rd., Da'an Dist., Taipei City 10608, Taiwan.
Heliyon. 2024 Mar 12;10(6):e27752. doi: 10.1016/j.heliyon.2024.e27752. eCollection 2024 Mar 30.
This study worked with Chunghwa Telecom to collect data from 17 rooftop solar photovoltaic plants installed on top of office buildings, warehouses, and computer rooms in northern, central and southern Taiwan from January 2021 to June 2023. A data pre-processing method combining linear regression and K Nearest Neighbor (k-NN) was proposed to estimate missing values for weather and power generation data. Outliers were processed using historical data and parameters highly correlated with power generation volumes were used to train an artificial intelligence (AI) model. To verify the reliability of this data pre-processing method, this study developed multilayer perceptron (MLP) and long short-term memory (LSTM) models to make short-term and medium-term power generation forecasts for the 17 solar photovoltaic plants. Study results showed that the proposed data pre-processing method reduced normalized root mean square error (nRMSE) for short- and medium-term forecasts in the MLP model by 17.47% and 11.06%, respectively, and also reduced the nRMSE for short- and medium-term forecasts in the LSTM model by 20.20% and 8.03%, respectively.
本研究与中华电信合作，于2021年1月至2023年6月期间，从台湾北部、中部和南部安装在办公楼、仓库和计算机房顶部的17座屋顶太阳能光伏电站收集数据。提出了一种结合线性回归和K近邻（k-NN）的数据预处理方法，以估计天气和发电数据的缺失值。利用历史数据处理异常值，并使用与发电量高度相关的参数训练人工智能（AI）模型。为了验证这种数据预处理方法的可靠性，本研究开发了多层感知器（MLP）和长短期记忆（LSTM）模型，对这17座太阳能光伏电站进行短期和中期发电量预测。研究结果表明，所提出的数据预处理方法使MLP模型短期和中期预测的归一化均方根误差（nRMSE）分别降低了17.47%和11.06%，同时也使LSTM模型短期和中期预测的nRMSE分别降低了20.20%和8.03%。
