Buildings' energy consumption forecasting is critical for energy saving and building maintenance. However, most studies only focus on centralized learning of one dataset, which ignores the data privacy and data shortage issue. Meanwhile, the difference in energy data distributions from many buildings causes difficulties in training a good machine learning model. Although these two challenges of data privacy and data heterogeneity could be resolved through personalized federated learning algorithms to some degree, there is still a lack of investigation into applying these algorithms to building energy data analytics. Besides using existing personalized federated learning algorithms, we design a new deep learning model through a mixture of experts to support personalization for heterogeneous data distribution. This new design is the first trial to tackle the data heterogeneity through ensemble architecture in federated load forecasting. Extensive experiments are conducted to evaluate the effectiveness of our proposed model with different training algorithms. The results show that our proposed method outperforms other state-of-the-art models in energy forecasting accuracies by 10% to 40% across the buildings' energy data from university campuses.

中文翻译：

---

建筑能耗预测的个性化联合学习


建筑物的能耗预测对于节能和建筑物维护至关重要。然而，大多数研究只关注一个数据集的集中学习，忽略了数据隐私和数据短缺问题。同时，许多建筑物的能源数据分布存在差异，导致训练良好的机器学习模型变得困难。尽管数据隐私和数据异构性这两个挑战可以在一定程度上通过个性化联邦学习算法得到解决，但仍缺乏将这些算法应用于构建能源数据分析的研究。除了使用现有的个性化联邦学习算法外，我们还通过专家的混合设计了一种新的深度学习模型，以支持异构数据分布的个性化。这种新设计是首次在联合负载预测中通过集成架构解决数据异构性的尝试。进行了大量的实验来评估我们提出的模型使用不同训练算法的有效性。结果表明，我们提出的方法在大学校园建筑物能源数据的能源预测精度方面优于其他最先进的模型 10% 到 40%。