arXiv：cs.LG· Ting-Yu Dai, Takuya Kurihana, Wing Yee Au, Hon Yung Wong·· 4 小时前AI 评分35
NeuralBES：一种可微分、控制感知的可扩展建筑能耗建模模拟器
NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling
AI 导读
NeuralBES 是一种可微分模拟器，用共享神经编码器将建筑元数据映射为物理有界的 RC 热模型参数，通过 log-space 并行扫描求解并保持全时域梯度流，从而兼顾物理可解释性与规模化。
正文
Abstract:Demand-side flexibility i.e. forecasting, shifting, and curtailing residential energy loads, depends on thermal models trusted across millions of heterogeneous buildings. Existing tools force a hard tradeoff: high-fidelity physics simulators such as EnergyPlus are accurate but sequential and require per-building calibration, while purely data-driven sequence models scale but abandon the physical structure that makes their predictions trustworthy.
We introduce NeuralBES (Building Energy Simulation), a differentiable emulator that resolves this tradeoff by parameterizing a resistance--capacitance (RC) based thermal model with a shared neural encoder: static building metadata such as floor area, vintage, and HVAC type is mapped to physically bounded capacitances, conductances, and equipment coefficients, which become the coefficients of a scalar linear recurrence solved via a log-space parallel scan, and a predictor--corrector loop closes the thermostat--temperature nonlinearity while preserving full-horizon gradient flow. Trained on the ResStock dataset across three climate zones, NeuralBES handles heterogeneous building archetypes, vintages, and climate zones within a single trained encoder, while black-box baselines produce statistically plausible but physically inconsistent trajectories. On the annual full-year rollout, NeuralBES is the only data-conditioned model that is simultaneously physics-valid and accurate to within 4 MAPE points of the strongest raw-error baseline, while operating at roughly an order of magnitude fewer parameters than the transformer and recurrent baselines; among physics-valid baselines at parameter parity it more than halves the MAPE of the grey-box RC alternative.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.10459 [cs.LG] |
| (or arXiv:2610.10459v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10459 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ting-Yu Dai [view email]
[v1]
Wed, 7 Oct 2026 17:27:20 UTC (1,305 KB)
来源：arXiv：cs.LG · arxiv.org