Leveraging Sustainable Household Energy and Environment Resources Management with Time-Series

Area of Science:

• Environmental Science
• Energy Systems Engineering
• Data Science

Background:

• Understanding residential energy consumption and solar production is crucial for sustainable energy transitions.
• Existing datasets often lack integrated, granular data linking energy use, cost, solar generation, and environmental factors.
• Achieving Sustainable Development Goals (SDG) 7, 9, 11, and 13 requires robust data for informed decision-making.

Purpose of the Study:

• To introduce the novel Solar, Household Energy, and Environmental Research Metrics (SHEERM) dataset.
• To provide a comprehensive, cross-sectional dataset linking electrical load, energy cost, solar production, solar irradiation, and weather parameters.
• To facilitate research in renewable energy forecasting, grid management, and energy policy formulation.

Main Methods:

• Collected nearly three years of data from 13 households.
• Integrated electrical load, energy cost, on-premises solar energy production, solar irradiation, and weather parameters.
• Validated the dataset using established machine learning models.

Main Results:

• The SHEERM dataset offers a unique combination of residential energy and environmental data.
• Machine learning models were successfully applied to validate the data and demonstrate its utility.
• The dataset enables multifaceted analysis for optimizing energy utilization and forecasting.

Conclusions:

• The SHEERM dataset is a valuable resource for advancing renewable energy research and implementation.
• It supports the design of new energy systems to enhance sustainable energy strategies.
• The dataset can accelerate the transition towards carbon neutrality and improved energy efficiency.