A comprehensive dataset integrating household energy consumption and weather conditions in a north-eastern Mexican urban city

Abstract

The prediction of domestic electricity consumption is relevant because it helps to plan energy production, among many other benefits. In this work a dataset was collected from one house in an urban city of north-east of Mexico. An ad-hoc acquisition system was implemented to collect the data using a smart meter and the open weather API. The data was collected every minute over a period of 14 months since November 5, 2022, to January 5, 2024. The dataset contains 605,260 samples of 19 variables related with energy consumption and weather data. This dataset is specifically tailored for predicting domestic energy consumption and understanding consumption behaviours, filling a void in the existing literature where such datasets for Mexico are scarce. Moreover, the multivariate nature of the dataset allows researchers to investigate and propose new techniques for forecasting or pattern classification using multivariate data collected in a real scenario.

Keywords

• Empirical data collection
• Machine learning
• Forecast
• Artificial intelligence
• Electricity consumption behaviour
• Smart plug