Cross-domain HVAC energy prediction is essential for scalable building energy management, particularly because collecting extensive labeled data for every new building is both costly and impractical. Yet, this task remains highly challenging due to the scarcity and heterogeneity of data across different buildings, climate zones, and seasonal patterns. In particular, buildings situated in distinct climatic regions introduce variability that often leads existing methods to overfit to spurious correlations, rely heavily on expert intervention, or compromise on data diversity. To address these limitations, we propose CaberNet, a causal and interpretable deep sequence model that learns invariant (Markov blanket) representations for robust cross-domain prediction. In a purely data-driven fashion and without requiring any prior knowledge, CaberNet integrates i) a global feature gate trained with a self-supervised Bernoulli regularization to distinguish superior causal features from inferior ones, and ii) a domain-wise training scheme that balances domain contributions, minimizes cross-domain loss variance, and promotes latent factor independence. We evaluate CaberNet on real-world datasets collected from three buildings located in three climatically diverse cities, and it consistently outperforms all baselines, achieving a 22.9% reduction in normalized mean squared error (NMSE) compared to the best benchmark. Our code is available at https://github.com/SusCom-Lab/CaberNet-CRL.

翻译：跨域HVAC（暖通空调）能耗预测对于可扩展的建筑能源管理至关重要，尤其是在为每栋新建建筑收集大量标注数据既昂贵又不切实际的情况下。然而，由于不同建筑、气候带和季节模式之间数据的稀缺性和异质性，这项任务仍然极具挑战性。具体而言，位于不同气候区域的建筑会引入变异性，这往往导致现有方法过拟合于虚假相关性、严重依赖专家干预或牺牲数据多样性。为应对这些局限性，我们提出了CaberNet——一种因果可解释的深度序列模型，能够学习不变（马尔可夫毯）表征以实现稳健的跨域预测。CaberNet以纯数据驱动的方式且无需任何先验知识，整合了以下两个核心组件：i）通过自监督伯努利正则化训练的全局特征门控机制，用于区分优质因果特征与劣质特征；ii）域平衡训练策略，该策略平衡各领域贡献、最小化跨域损失方差并促进潜在因子独立性。我们在从三个气候迥异城市的三栋建筑收集的真实数据集上评估CaberNet，其性能始终优于所有基线模型，与最佳基准相比实现了归一化均方误差（NMSE）降低22.9%。我们的代码公开于https://github.com/SusCom-Lab/CaberNet-CRL。