A clustering-based approach for “cross-scale” load prediction on building level in HVAC systems

Abstract

A new cross-scale load prediction model on the building level based on the k-means clustering method is proposed in this paper. An office building with 26 conditioned thermal zones is the research object. The data set comprises 5785 h cooling/heating load data by Energyplus simulation and real-world monitoring, besides, a kind of data considering the accumulative effect is also included. The proposed model aims at quantifying the intra-cluster relationships. The quantification tool consists of a well-trained LSTM model and a representative load time series input from the cluster centroid in one prediction cell. By composing the prediction cells of all included clusters, the cross-scale prediction model from zone scale to building scale is built. To investigate the association between each explanatory variable and cluster belongings, ANN logistic regression model is applied. Some explanatory physical variables (e.g., the ratio of temperature difference) calculated by the “non-equilibrium” thermal insulation method are first proposed and used in logistic regression. By applying the simulation and accumulative effect considered data to the proposed model, the result shows that there is a trade-off between the ratio of the sample size of the cluster and mean cross-scale prediction accuracy, and the optimal prediction period can be obtained. In logistic regression, the result shows the maximum demand, start and end time of HVAC system, the west to the south ratio of temperature difference, and the exterior window area together determine the belonging of the cluster. At last, the proposed model is validated by real-world data and showed it’s effectiveness, and the accumulative effect makes the cross-scale prediction accuracy better.