Abstract
Successful operation of a district heating system requires optimal scheduling of heating resources to satisfy heating demands. The optimal operation, therefore, requires accurate short-term forecasts of future heat load. In this paper, short-term forecasting of heat load in a district heating system of Ljubljana is presented. Heat load data and weather-related influential variables for five subsequent winter seasons of district heating operation are applied in this study. Various linear models and nonlinear neural network-based forecasting models are developed to forecast the future daily heat load with the forecasting horizon one day ahead. The models are evaluated based on generalization error, obtained on an independent test data set. Results demonstrate the importance of outdoor temperature as the most important influential variable. Other influential inputs include solar radiation and extracted features denoting population activities (such as day of the week). Comparison of forecasting models reveals good forecasting performance of a linear stepwise regression model (SR) that utilizes only a subset of the most relevant input variables. The operation of the SR model was improved by using neural network (NN) models, and also NN models with a direct linear link (NNLL). The latter showed the overall best forecasting performance, which suggests that NN or the proposed NNLL structures should be considered as forecasting solutions for applied forecasting in district heating markets.
Highlights
Energy efficiency is specified by the European Union (EU) as a key driver of the transition toward a lowcarbon society [1]; recent studies show that new district heating systems can reduce heating and cooling costs by 15 %, which represents €100 billion per year [2]
For the evaluation of forecasting models, we introduce the so-called mean absolute range normalized error (MARNE), which is a relative measure depending on the size of the district heating system and can be interpreted in technical or economical terms
For all applied models both training and testing errors (MARNE) are presented, only the testing error that is considered an estimator of the generalization ability of the model is evaluated as a final model performance measure
Summary
Energy efficiency is specified by the European Union (EU) as a key driver of the transition toward a lowcarbon society [1]; recent studies show that new district heating systems can reduce heating and cooling costs by 15 %, which represents €100 billion per year [2]. The successful operation of a district heating system requires optimal scheduling of heating resources to satisfy the heating demands. The scheduling operation requires accurate short-term forecasts of future heat load to optimally assign heating resources. Short-term energy demand forecasting has been studied predominantly in the field of electricity load forecasting and natural gas consumption forecasting [4], and less so in district heating forecasting, similar statistical models can be applied [5]. The sources of heat load variations in district heating systems are both seasonal and daily and are mainly a consequence of variations in outdoor temperature and the social behaviour of customers [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Strojniški vestnik – Journal of Mechanical Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
