Residential water and energy consumption prediction at hourly resolution based on a hybrid machine learning approach.
Residential water and energy consumption prediction at hourly resolution based on a hybrid machine learning approach.
复制标题
DOI：
10.1016/j.watres.2023.120733
复制
发表时间：
2023-10
期刊：
影响因子：
12.8
通讯作者：
Chunyan Wang;Zonghan Li;Xiaoyuan Ni;Wenlei Shi;Jia Zhang;Jiang Bian;Yi Liu
中科院分区：
文献类型：
--
作者：
Chunyan Wang;Zonghan Li;Xiaoyuan Ni;Wenlei Shi;Jia Zhang;Jiang Bian;Yi Liu
在短期范围内以高分辨率预测水和能源消耗对于水资源和能源管理至关重要。在家庭消费中，水和能源被证明是紧密相连的。然而，每小时的预测往往只基于被预测的资源的历史消费数据，活动或用具信息和家庭属性是额外的信息。很少有研究使用水和能源的总消耗量来预测。在此背景下，本研究提出了一种新的基于Prophet时间序列模型、门控递归单元网络和自适应权重的混合机器学习模型，称为Prophet-GRU模型，该模型可以联合包括历史用水量和用电量作为小时用水量或用电量预测的输入。利用2020年1月至3月北京6户家庭的小时用水量和用电量数据对PROPHET-GRU模型进行了训练和验证。对水电预测的拟合度(R2)和预测精度(均方误差和平均绝对误差)进行了评价。与水或电的单一输入相比，在两种资源数据的联合输入下，PROPHET-GRU模型对用水量和用电量的预测R2分别提高了29.2%和48.5%。我们的结果有助于更好地了解水-能源联系，并促进水和能源管理的协作实践。
Predicting water and energy consumption at high resolution over a short-term horizon is critical for water and energy resource management. Water and energy are shown to be closely interlinked in household consumption. However, hourly predictions are often based only on historical consumption data for the resource being predicted, with activity or appliance information and household attribution as additional information. Few studies have used aggregated water and energy consumption for predictions. Within this context, the current study proposed a novel hybrid machine learning model based on the Prophet time-series model, Gated Recurrent Unit network, and self-adaptive weights, called the Prophet-GRU model, which could jointly include historical water and electricity consumption as inputs for hourly water or electricity prediction. Data on hourly water and electricity consumption in six households in Beijing during January–March 2020 were used to train and validate the Prophet-GRU model. The goodness of fit indicator (R2) and prediction accuracy (mean squared error and mean absolute error) for the water and electricity predictions were evaluated. Compared with the single input of water or electricity, with the combined input of data of these two resources, the proposed Prophet-GRU model achieved improvements of 29.2 % and 48.5 % inR2, for water and electricity consumption prediction, respectively. Our results could help better understand water-energy linkages and promote collaborative water and energy management practices.