Performance Evaluation Method of Day-Ahead Load Prediction Models in a District Heating and Cooling System: A Case Study

Haiyan Meng, Yakai Lu (), Zhe Tian (), Xiangbei Jiang, Zhongqing Han and Jide Niu
Additional contact information
Haiyan Meng: School of Environmental Science and Engineering, Tianjin University, Tianjin 300072, China
Yakai Lu: School of Energy and Environmental Engineering, Hebei University of Technology, Tianjin 300401, China
Zhe Tian: School of Environmental Science and Engineering, Tianjin University, Tianjin 300072, China
Xiangbei Jiang: Cecep Wind Power Co., Ltd., Beijing 100082, China
Zhongqing Han: State Grid Jibei Power Co., Ltd., Beijing 100054, China
Jide Niu: School of Environmental Science and Engineering, Tianjin University, Tianjin 300072, China

Energies, 2023, vol. 16, issue 14, 1-19

Abstract: Many researchers are devoted to improving the prediction accuracy of daily load profiles, so as to optimize day-ahead operation strategies to achieve the most efficient operation of district heating and cooling (DHC) systems; however, studies on load prediction and operation strategy optimization are generally isolated, which leaves the following question: what day-head load prediction performance should be paid attention to in the operation optimization of DHC systems? In order to explain this issue, and taking an actual DHC system as a case study, this paper proposes an evaluation method for the prediction of daily cooling load profiles by considering the impact of inaccurate prediction on the operation of a DHC system. The evaluation results show the following: (1) When prediction models for daily load profiles are developed, the prediction accuracy of the daily mean load should be emphasized, and there is no need to painstakingly increase the accuracy of load profile shapes. (2) CV and RMSE are the most suitable deviation measures (compared to others, e.g., MAPE, MAE, etc.) for the evaluation of load prediction models. A prediction model with 27.8% deviation ( CV ) only causes a 3.74% deviation in operation costs; thus, the prediction performance is enough to meet the engineering requirements for the DHC system in this paper.

Keywords: load prediction model; prediction performance evaluation; operation optimization; district heating and cooling (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/16/14/5402/pdf (application/pdf)
https://www.mdpi.com/1996-1073/16/14/5402/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:16:y:2023:i:14:p:5402-:d:1194954

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().