HEAPO -- An Open Dataset for Heat Pump Optimization with Smart Electricity Meter Data and On-Site Inspection Protocols

TL;DR

HEAPO delivers an open, real-world dataset for heat pump optimization by integrating 1,408 households’ 15-minute and daily smart-meter data, weather from 8 MeteoSwiss stations, building metadata, and 410 on-site inspection protocols across 2018–2024. It provides a Python-based dataloader to streamline data ingestion, supports treatment-control analyses around professional optimizations, and validates data quality with near-perfect alignment between 15-minute and daily measurements ($R^2 = 0.99$, $MAE = 0.48\ \text{kWh}$, $SMAPE = 2.46\%$). The dataset enables research on predictive maintenance, energy efficiency, demand-side management, and load disaggregation, while documenting common real-world issues identified during audits. Although Swiss-focused, HEAPO offers a scalable basis for developing data-driven services to improve hp performance and grid interactions in residential settings.

Abstract

Heat pumps are essential for decarbonizing residential heating but consume substantial electrical energy, impacting operational costs and grid demand. Many systems run inefficiently due to planning flaws, operational faults, or misconfigurations. While optimizing performance requires skilled professionals, labor shortages hinder large-scale interventions. However, digital tools and improved data availability create new service opportunities for energy efficiency, predictive maintenance, and demand-side management. To support research and practical solutions, we present an open-source dataset of electricity consumption from 1,408 households with heat pumps and smart electricity meters in the canton of Zurich, Switzerland, recorded at 15-minute and daily resolutions between 2018-11-03 and 2024-03-21. The dataset includes household metadata, weather data from 8 stations, and ground truth data from 410 field visit protocols collected by energy consultants during system optimizations. Additionally, the dataset includes a Python-based data loader to facilitate seamless data processing and exploration.

Figures (5)

• Figure 1: Overview of available data sources.
• Figure 2: Example of 15-minute resolution smd for a single household (Household_ID: 461158) visualized as a heat map. The graph shows total active electrical energy consumption (in kWh) using colored pixels, with the date on the x-axis and the time of day on the y-axis. A shift in consumption patterns is noticeable after the energy consultant's visit, where the night setback was deactivated as part of the hp optimization.
• Figure 3: Example of Python code demonstrating the use of the dataloader and its data visualization features. This code snippet produces the graph shown in Figure \ref{['fig:heatmap_example']}.
• Figure 4: Daily household energy intensity (kWh per square meter of living area) as a function of outdoor temperature for households in the dataset.
• Figure 6: File and folder structure of the HEAPO dataset.