NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling
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.
Ting-Yu Dai, Takuya Kurihana, Wing-Yee Au et al.
· 0 citations