Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks.
Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks.
复制标题
通过自动编码器贝叶斯深度神经网络进行风险感知最佳通风的概率占用预测。
DOI：
10.1016/j.buildenv.2022.109207
复制
发表时间：
2022-07-01
影响因子：
7.4
通讯作者：
Mavrogianni, Anna
中科院分区：
文献类型：
--
作者：
Zhuang, Chaoqun;Choudhary, Ruchi;Mavrogianni, Anna
通风在维持健康、舒适和节能的室内环境以及减轻气溶胶传播和疾病感染的风险方面发挥着值得注意的作用（例如，SARS-COV-2）。在大多数商业和办公建筑中，需求控制通风（DCV）系统被广泛用于基于占用率来节省能源。然而，由于占用者的存在通常固有地是随机的，准确的占用预测是具有挑战性的。因此，本研究提出了一种用于概率占用预测的自动编码器贝叶斯长短期记忆神经网络（LSTM）模型，考虑了模型误指定，认知不确定性和任意不确定性。在英国剑桥大学的一栋教学楼中，使用真实的数据对所提出的模型的性能进行了评估。在一个开放式空间的数据上训练的模型用于预测同一建筑物中其他空间（具有类似布局和功能）的占用人数。然后使用概率性居住者简档来估计两种情况的最佳通风率（即，用于节能的正常DCV模式和用于防止病毒传播的抗感染模式）。结果表明，在测试期间，对于1小时的提前预测，该模型比传统的LSTM模型具有更好的性能，平均绝对误差百分比降低高达5.8%。所提出的风险感知决策方案可为真实的运行条件下不同目的的通风方案提供更灵活的选择。这项研究的结果提供了新的占用预测解决方案，并探讨了建筑通风优化的概率决策的潜力。
Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization.
登录
查看更多内容
影响因子：
5.8
作者：
Gupta, Jitendra K.;Lin, Chao-Hsin;Chen, Qingyan
通讯作者：
Chen, Qingyan
影响因子：
6.7
作者：
Deng, Zhipeng;Chen, Qingyan
通讯作者：
Chen, Qingyan
影响因子：
2.5
作者：
Dong, Bing;Lam, Khee Poh
通讯作者：
Lam, Khee Poh
影响因子：
6.7
作者：
Kim, Yang-Seon;Srebric, Jelena
通讯作者：
Srebric, Jelena
影响因子：
6.7
作者：
Candanedo, Luis M.;Feldheim, Veronique;Deramaix, Dominique
通讯作者：
Deramaix, Dominique