Short-term electricity load forecasting (Panama case study)

This is a useful dataset to train and test Machine Learning forecasting algorithms and compare results with the official forecast from weekly pre-dispatch reports. The following considerations should be kept to compare forecasting results with the weekly pre-dispatch forecast: 1. Saturday is the first day of each weekly forecast; for instance, Friday is the last day. 2. A 72 hours gap of unseen records should be considered before the first day to forecast. In other words, next week forecast should be done with records until each Tuesday last hour. Data sources provide hourly records. The data composition is the following: 1. Historical electricity load, available on daily post-dispatch reports, from the grid operator (CND). 2. Historical weekly forecasts available on weekly pre-dispatch reports, both from CND. 3. Calendar information related to school periods, from Panama's Ministery of Education. 4. Calendar information related to holidays, from "When on Earth?" website. 5. Weather variables, such as temperature, relative humidity, precipitation, and wind speed, for three main cities in Panama, from Earthdata. The original data sources provide the post-dispatch electricity load in individual Excel files on a daily basis and weekly pre-dispatch electricity load forecast data in individual Excel files on a weekly basis, both with hourly granularity. Holidays and school periods data is sparse, along with websites and PDF files. Weather data is available on daily NetCDF files. For simplicity, the published datasets are already pre-processed by merging all data sources on the date-time index: 1. A CSV file containing all records in a single continuous dataset with all variables. 2. A CSV file containing the load forecast from weekly pre-dispatch reports. 3. Two Excel files containing suggested regressors and 14 training/testing datasets pairs as described in the PDF file.

本数据集适用于训练、测试机器学习预测算法，并可将模型预测结果与每周预调度报告中的官方预测结果进行对比。在将预测结果与每周预调度预测结果进行对标时，需遵循以下规则：1. 每周预测周期以周六为起始日，例如周五为该周期的最后一日。2. 需在预测起始日前预留72小时的未观测记录间隔，换言之，下周预测应使用截至当周周二最后一小时的全部历史记录开展训练。数据集提供每小时粒度的观测记录，其构成如下：1. 电网运营商（CND）发布的每日调度后报告中的历史电力负荷数据。2. 同样由CND发布的每周预调度报告中的历史周度预测数据。3. 巴拿马教育部提供的与学期时段相关的日历信息。4. 「When on Earth?」网站提供的节假日相关日历信息。5. 地球数据（Earthdata）平台提供的巴拿马三座主要城市的气象变量数据，涵盖气温、相对湿度、降水量与风速。原始数据源以日为单位提供单个Excel文件格式的调度后电力负荷数据，同时以周为单位提供单个Excel文件格式的每周预调度电力负荷预测数据，二者均采用每小时粒度。节假日与学期时段数据较为稀疏，存储于网页与PDF文件中。气象数据以日为单位存储于NetCDF文件中。为简化使用流程，本次发布的数据集已完成预处理，通过日期时间索引完成多源数据整合，具体包括：1. 包含全部变量的单条连续数据集的CSV文件。2. 包含每周预调度报告中电力负荷预测结果的CSV文件。3. 两个Excel文件，内含PDF文档中提及的候选回归变量与14组训练/测试数据集配对。

搜集汇总

背景与挑战

背景概述

该数据集用于短期电力负荷预测的机器学习训练和测试，特别针对巴拿马案例，可与官方周预调度预测进行比较。数据来源多样，包括历史负荷和预测、学校与节假日日历，以及巴拿马三个主要城市的天气变量，已预处理为CSV和Excel文件，便于直接使用。