Global horizontal irradiance forecasting code and data
收藏资源简介：
For reproducibility purposes, this dataset contains the data and code described in "A deep learning model for intra-day forecasting of solar irradiance using satellite-based estimations in the vicinity of a PV power plant" (https://doi.org/10.1016/j.solener.2021.02.033) There are four main folders in the project: code, data, models and logdir. Data This folder contains all the data used from the studied location: Loc.1 (latitude=40.4º, longitude=6.0º). Sorted by year, month and day, there are three kinds of data: • The files named as just a number are 151x151 irradiance estimates matrices centered in the same location obtained from http://msgcpp.knmi.nl. The spatial resolution is 0.03º for both latitude and longitude. • The files named Real_ are the irradiance measurements at the location • The files named CopernicusClear_ are the clear sky estimates from the CAMS McClear model Each file contains the 96 15-minute samples for the same day in Matlab format and UTC time. Code All the python scripts used to train the neural networks and perform the forecasts. The main files are: • tf1.yml: List of the modules and versions used. A clean Anaconda environment created from this file can run all the code in the project. • learnRadiation.py: The script to train a new model. Changing the “paper_model_name” variable selects the kind of model to fit. • predictOnly.py: Loads a trained model and performs the forecast. Notice that the model must match the one used to train the model stored in the “training_path” folder Models This folder contains all the trained models and their forecasting results. There is also a training folder to contain the last trained model. Logdir This folder stores Tensorboard files during training How to train and test a model A new model can be trained using “learnRadiation.py”. This script has two parameters • paper_model_name: This sets the inputs to match the ones used in the models from the article. • training_path: The folder to save the trained model Then the “predictOnly.py” script allows performing the forecasts. It is important to set the same parameters as in the “learnRadiation.py” script. This program will generate the predictions and save them in the model folder. It also plots some days, which can be modified at the bottom of the script. For instance, in order to train the TOA & all real model we would run: "python learnRadiation.py TOAallreal training" This will train the neural network and save the results in the folder models/training. After this, we would generate the results and plot some days using: “python predictOnly.py TOAallreal training” This will save the forecasts and real values in the training folder and show figures with 1 to 6 hour forecasts The models used for the article can also be evaluated by using predictOnly.py and targeting their folders. For instance, to evaluate the TOA & all real model used in the article, this command must be used: “python predictOnly.py TOAallreal RtoaAllReal”
为保证研究可复现，本数据集包含论文《基于光伏电站（photovoltaic power plant，简称PV）周边卫星反演数据的日内太阳辐照度深度学习预测模型》（https://doi.org/10.1016/j.solener.2021.02.033）中提及的全部数据与代码。本项目共包含四个核心文件夹：code、data、models与logdir。 数据文件夹：该文件夹存储研究地点Loc.1（纬度40.4°，经度6.0°）的所有实验数据，按年、月、日分级整理，共包含三类数据： 1. 仅以纯数字命名的文件：为从http://msgcpp.knmi.nl获取的、以该研究地点为中心的151×151辐照度反演矩阵，经纬度方向的空间分辨率均为0.03°。 2. 以Real_开头命名的文件：为该研究地点的实测辐照度数据。 3. 以CopernicusClear_开头命名的文件：为CAMS McClear模型生成的晴空辐照度反演结果。 所有文件均采用MATLAB格式，以UTC时间为基准，存储当日共96组15分钟采样的辐照度数据。 代码文件夹：该文件夹包含用于训练神经网络并执行预测的全部Python脚本，核心文件如下： - tf1.yml：项目依赖的Python模块及其版本列表，通过该文件可创建干净的Anaconda环境以运行本项目所有代码。 - learnRadiation.py：用于训练新模型的主脚本，修改paper_model_name变量即可选择待拟合的模型类型。 - predictOnly.py：加载已训练模型并执行预测的脚本，需保证加载的模型与training_path文件夹中存储的训练模型匹配。 模型文件夹：该文件夹存储所有已训练的模型及其预测结果，同时包含一个training子文件夹，用于存放最新训练的模型。 日志文件夹：该文件夹用于存储模型训练过程中的Tensorboard（Tensorboard）日志文件。 模型训练与测试流程：可通过learnRadiation.py脚本训练新模型，该脚本包含两个必填参数： - paper_model_name：用于设置模型输入参数，使其与论文中所用模型的输入保持一致。 - training_path：用于保存已训练模型的文件夹路径。 训练完成后，可通过predictOnly.py脚本执行预测任务，需保证该脚本的参数与learnRadiation.py保持完全一致。该程序将生成预测结果并保存至对应模型文件夹，同时绘制部分日期的预测效果图，绘图的日期范围可在脚本底部自行修改。 示例操作：若需训练TOA & all real模型，可执行以下命令：python learnRadiation.py TOAallreal training，该命令将完成神经网络的训练，并将训练结果保存至models/training文件夹。训练完成后，可通过以下命令生成预测结果并绘制对应日期的效果图：python predictOnly.py TOAallreal training，该命令将把预测结果与实测值保存至training文件夹，并展示1至6小时的预测对比效果图。 论文中使用的模型也可通过predictOnly.py调用其对应文件夹进行评估。例如，若需评估论文中使用的TOA & all real模型，需执行以下命令：python predictOnly.py TOAallreal RtoaAllReal。
