当前位置:
X-MOL 学术
›
Energy Build.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Transfer learning in building dynamics prediction
Energy and Buildings ( IF 6.6 ) Pub Date : 2025-01-25 , DOI: 10.1016/j.enbuild.2025.115384
Gaurav Chaudhary, Hicham Johra, Laurent Georges, Bjørn Austbø
Energy and Buildings ( IF 6.6 ) Pub Date : 2025-01-25 , DOI: 10.1016/j.enbuild.2025.115384
Gaurav Chaudhary, Hicham Johra, Laurent Georges, Bjørn Austbø
Buildings account for approximately 40% of global energy use, largely due to heating, ventilation, and air conditioning (HVAC) systems. Advanced control strategies, such as model predictive control (MPC), are crucial for optimizing energy usage in smart buildings. For effective MPC, high-fidelity models are necessary to reliably predict thermal responses under varying conditions. Low development costs, scalability and ability to process high-dimensional data and capture non-linear relationships make deep neural networks (DNNs) apt for predicting complex building dynamics. However, developing DNNs for new buildings is challenging due to their extensive data requirements. This paper investigates the use of transfer learning to address this issue, based on studies of different building models in different Norwegian climates. By pre-training control-oriented deep neural network models on synthetic building operation datasets, developed using EnergyPlus, from a similar source building in a similar climate, these models can be fine-tuned for new target buildings with minimal data. The study makes three key contributions. First, it introduces and evaluates six fine-tuning strategies for pre-trained DNNs, offering empirical insights into optimal approaches for adapting complex encoder-decoder architectures. Second, it employs two custom key performance indicators to quantify the effectiveness of transfer learning strategies, providing a standardized framework for assessing transfer learning in building dynamics prediction. Third, the study demonstrates the importance of fine-tuning specific model components, such as decoder layers, and the benefits of adding dense layers or gated recurrent units, especially in cold climates, where introducing colder weather data significantly improves predictive accuracy. Key findings include better results from fine-tuning decoder layers, especially early ones, and the importance of adding new layers before fine-tuning specific ones. Target buildings in mild climates and with similar physical properties (U-values) showed more stable and faster improvement from transfer learning. For the cold-climate case studies, introducing colder weather in the fine-tuning datasets significantly improved prediction accuracy.
中文翻译:
建筑动力学预测中的迁移学习
建筑物约占全球能源使用量的 40%,这主要是由于供暖、通风和空调 (HVAC) 系统造成的。先进的控制策略,如模型预测控制 (MPC),对于优化智能建筑中的能源使用至关重要。为了实现有效的 MPC,需要高保真模型来可靠地预测不同条件下的热响应。深度神经网络 (DNN) 开发成本低、可扩展性强,能够处理高维数据和捕获非线性关系,因此非常适合预测复杂的建筑动力学。然而,由于新建筑物的数据要求广泛,因此为新建筑物开发 DNN 具有挑战性。本文基于对挪威不同气候下不同建筑模型的研究,调查了使用迁移学习来解决这个问题。通过使用 EnergyPlus 开发的合成建筑运营数据集上预训练面向控制的深度神经网络模型,这些模型可以在类似气候下的类似来源建筑中进行微调,以最少的数据针对新的目标建筑进行微调。该研究做出了三个主要贡献。首先,它介绍并评估了预训练 DNN 的六种微调策略,为适应复杂编码器-解码器架构的最佳方法提供了实证见解。其次,它采用两个自定义的关键绩效指标来量化迁移学习策略的有效性,为评估建筑动力学预测中的迁移学习提供了一个标准化框架。 第三,该研究证明了微调特定模型组件(如解码器层)的重要性,以及添加密集层或门控循环单元的好处,尤其是在寒冷气候中,引入较冷的天气数据会显著提高预测准确性。主要发现包括微调解码器层(尤其是早期解码器层)的更好结果,以及在微调特定层之前添加新层的重要性。气候温和且具有相似物理特性 (U 值) 的目标建筑物通过迁移学习显示出更稳定、更快速的改进。对于寒冷气候案例研究,在微调数据集中引入较冷的天气显著提高了预测准确性。
更新日期:2025-01-25
中文翻译:

建筑动力学预测中的迁移学习
建筑物约占全球能源使用量的 40%,这主要是由于供暖、通风和空调 (HVAC) 系统造成的。先进的控制策略,如模型预测控制 (MPC),对于优化智能建筑中的能源使用至关重要。为了实现有效的 MPC,需要高保真模型来可靠地预测不同条件下的热响应。深度神经网络 (DNN) 开发成本低、可扩展性强,能够处理高维数据和捕获非线性关系,因此非常适合预测复杂的建筑动力学。然而,由于新建筑物的数据要求广泛,因此为新建筑物开发 DNN 具有挑战性。本文基于对挪威不同气候下不同建筑模型的研究,调查了使用迁移学习来解决这个问题。通过使用 EnergyPlus 开发的合成建筑运营数据集上预训练面向控制的深度神经网络模型,这些模型可以在类似气候下的类似来源建筑中进行微调,以最少的数据针对新的目标建筑进行微调。该研究做出了三个主要贡献。首先,它介绍并评估了预训练 DNN 的六种微调策略,为适应复杂编码器-解码器架构的最佳方法提供了实证见解。其次,它采用两个自定义的关键绩效指标来量化迁移学习策略的有效性,为评估建筑动力学预测中的迁移学习提供了一个标准化框架。 第三,该研究证明了微调特定模型组件(如解码器层)的重要性,以及添加密集层或门控循环单元的好处,尤其是在寒冷气候中,引入较冷的天气数据会显著提高预测准确性。主要发现包括微调解码器层(尤其是早期解码器层)的更好结果,以及在微调特定层之前添加新层的重要性。气候温和且具有相似物理特性 (U 值) 的目标建筑物通过迁移学习显示出更稳定、更快速的改进。对于寒冷气候案例研究,在微调数据集中引入较冷的天气显著提高了预测准确性。