scholarly journals A Novel Hybrid Spatial-Temporal Attention-LSTM Model for Heat Load Prediction

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 159182-159195
Author(s):  
Tao Lin ◽  
Yu Pan ◽  
Guixiang Xue ◽  
Jiancai Song ◽  
Chengying Qi
2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Fisnik Dalipi ◽  
Sule Yildirim Yayilgan ◽  
Alemayehu Gebremedhin

We present our data-driven supervised machine-learning (ML) model to predict heat load for buildings in a district heating system (DHS). Even though ML has been used as an approach to heat load prediction in literature, it is hard to select an approach that will qualify as a solution for our case as existing solutions are quite problem specific. For that reason, we compared and evaluated three ML algorithms within a framework on operational data from a DH system in order to generate the required prediction model. The algorithms examined are Support Vector Regression (SVR), Partial Least Square (PLS), and random forest (RF). We use the data collected from buildings at several locations for a period of 29 weeks. Concerning the accuracy of predicting the heat load, we evaluate the performance of the proposed algorithms using mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient. In order to determine which algorithm had the best accuracy, we conducted performance comparison among these ML algorithms. The comparison of the algorithms indicates that, for DH heat load prediction, SVR method presented in this paper is the most efficient one out of the three also compared to other methods found in the literature.


IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 16726-16741 ◽  
Author(s):  
Jiancai Song ◽  
Guixiang Xue ◽  
Xuhua Pan ◽  
Yunpeng Ma ◽  
Han Li

2014 ◽  
Vol 918 ◽  
pp. 154-159
Author(s):  
Lan Bin Liu ◽  
Ai Juan Zou ◽  
Yu Fei Ma

According to the internal mechanism of the formation of heat load, the formation of heat load consists of two parts, the systemic heat load, which is determined by the building envelope and outdoor environmental parameters and random load caused by the users randomness of events and solar radiation etc. Toward systemic heat load, this paper considered the influence of environmental parameters before the prediction time and used the method of stepwise trials and MSE to obtain the optimal solution. Toward random load, it is considered that the day of the same type have the same variation pattern. On this basis, this paper introduced a correction coefficient to obtain random load eventually. This paper selected DeST, the widely used energy simulation software in China, to analysis the case. The result shows that the prediction method is feasible and 50% of the predicted loads have the relative error of less than 5%.


Energy ◽  
2018 ◽  
Vol 152 ◽  
pp. 709-718 ◽  
Author(s):  
Jihao Gu ◽  
Jin Wang ◽  
Chengying Qi ◽  
Chunhua Min ◽  
Bengt Sundén

Sign in / Sign up

Export Citation Format

Share Document