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

arXiv cs.LG Papers
dataset energy-forecasting transfer-learning domain-adaptation zero-shot-learning residential benchmark

Summary

Introduces RESCAST-100K, a large-scale benchmark dataset for cross-domain residential load and indoor temperature forecasting, featuring simulated and real data to evaluate transfer learning, domain adaptation, and zero-shot generalization.

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 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.
Original Article
View Cached Full Text

Cached at: 06/03/26, 09:40 AM 

# RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting
Source: [https://arxiv.org/abs/2606.02852](https://arxiv.org/abs/2606.02852)
[View PDF](https://arxiv.org/pdf/2606.02852)

> 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\.

## Submission history

From: Jainam Dhruva \[[view email](https://arxiv.org/show-email/552d5901/2606.02852)\] **\[v1\]**Mon, 1 Jun 2026 20:17:16 UTC \(693 KB\)

Similar Articles

A Benchmark for Electrical Load Forecasting Across Grid Levels: Time-Series Transformers Outperform Established Methods

arXiv cs.LG

This paper presents a comprehensive benchmark for electrical load forecasting across grid levels, evaluating ten methods and finding that Transformer-based approaches consistently outperform established methods, reducing forecast error by 6.6–10.7%. The standard Transformer achieves superior performance over a novel flexible architecture, and the foundation model Chronos-2 shows competitive zero-shot performance on some datasets.

Domain-Adaptive Climate Downscaling Under Temporal Distribution Shift

arXiv cs.LG

This paper investigates temporal out-of-distribution shift in deep-learning-based climate downscaling and proposes a domain-adaptive framework that combines supervised reconstruction with domain alignment to improve high-resolution climate projections under non-stationary conditions.