RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting

2026-06-01

AI Summary

This work addresses the limitations of short-term forecasting of residential energy loads and indoor temperatures under data heterogeneity and scarcity, and the absence of a benchmark enabling structured cross-domain evaluation. We introduce RESCAST-100K, a large-scale residential forecasting benchmark comprising simulations of approximately 100,000 U.S. households generated with EnergyPlus and ResStock, featuring 15-minute resolution data on total load, HVAC load, and indoor temperature, alongside five real-world datasets. RESCAST-100K uniquely supports configurable source and target domains along interpretable dimensions—such as geography, climate zone, building envelope, and heating equipment—enabling controlled studies of domain shift, transfer learning, and zero-shot generalization. Experiments demonstrate that cross-attention and MLP-Mixer architectures significantly outperform RNN and Transformer baselines under domain shifts, missing inputs, and multitask settings, establishing a new benchmark for residential-to-grid-scale energy forecasting.

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 evaluation. We introduce RESCAST-100K, a large-scale residential forecasting benchmark for studying cross-domain generalization. It provides a configuration-driven interface that instantiates source and target domains along interpretable axes, including geography, climate zone, wall construction, and heating equipment, enabling systematic evaluation of transfer learning, domain adaptation, and zero-shot generalization under controlled domain shifts. The benchmark covers approximately 100,000 EnergyPlus-simulated U.S. homes derived from ResStock, with 15-minute time series for three coupled targets per home: total load, HVAC load, and indoor temperature. These are paired with weather channels, HVAC setpoints, and over 40 static building covariates. RESCAST-100K also integrates five real-world residential datasets under a unified schema, supporting sim-to-real evaluation on the same tasks. We benchmark recurrent, attention-based, and MLP-mixer architectures for zero-shot performance across domains, missing-input conditions, and forecasting tasks. Cross-attention and MLP-mixer models consistently outperform recurrent and classical transformer baselines under domain shift. RESCAST-100K is intended to aid the machine learning and building analytics communities advance cross-domain residential forecasting at home, community, and grid scale.

Problem

• residential load forecasting
• indoor temperature forecasting
• cross-domain generalization
• domain adaptation
• dataset benchmark

Innovation

• cross-domain forecasting
• residential load prediction
• domain adaptation
• sim-to-real evaluation
• RESCAST-100K