RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting
arXiv:2606.02852v1 Announce Type: new Abstract: Accurate short-term forecasting of residential energy load and indoor temperature is essential for home energy management systems, grid-level demand response, and community energy efficiency efforts. Domain adaptation and transfer learning have shown promise for improving forecasting accuracy under data heterogeneity and scarcity commonly seen in residential settings. However, progress is limited by the lack of comprehensive residential datasets: existing benchmarks are narrow in target coverage and rarely support structured cross-domain evaluati
The increasing focus on energy efficiency and grid stability, coupled with advancements in AI and data collection, makes comprehensive datasets like RESCAST-100K critical for current research and development.
This dataset addresses a critical gap in residential energy forecasting, enabling more accurate predictions for home energy management, demand response, and community-level energy efficiency.
The availability of a comprehensive, cross-domain dataset will accelerate research and development in energy forecasting, leading to more robust AI models and practical applications for energy management.
- · Smart home technology developers
- · Energy grid operators
- · AI researchers in energy
- · Energy efficiency consulting firms
- · Legacy energy management systems
- · Energy utilities with inefficient demand response
Improved forecasting leads to more efficient energy consumption and grid management.
Better energy management can reduce peak load electricity demand and lower consumer energy bills.
Widespread adoption of advanced energy management systems could contribute to decarbonization efforts and reduce the need for new power generation capacity.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG