A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine-learning-based multi-step heat demand forecasting in a district heating system
Graphical abstract Display Omitted
Highlights Methodology for 48-hour multi-step heat demand forecasting in a DH system. Gaussian process regression outperforms considered machine learning methods. Accurate temperature forecasts are important, solar irradiation forecasts are not. Forecasting errors for 48 h ahead below 3% of the max. heating power. Proposed forecasting solution can be fitted to different DH systems.
Abstract Short-term heat demand forecasting in district heating (DH) systems is essential for a sufficient heat supply and optimal operation of the DH. In this study, a machine learning based multi-step short-term heat demand forecasting approach using the data of the largest Slovenian DH system is considered. The proposed approach involved feature extraction and comparative analysis of different representative machine learning based forecasting models. Nonlinear models performed better than linear models, and the best forecasting results were obtained by Gaussian process regression (GPR), where the mean absolute normalized error was 2.94% of the maximum heating power of the DH system. The analysis confirmed the importance of accurate temperature forecasts but did not confirm the relevance of using future solar irradiation forecasts. The optimal length of training data is shown to be 3 years, and past data of up to 4 days can be used as input to increase the forecasting accuracy. The forecasting model (GPR) proposed in this study can be fitted to different DH systems. In the presented case study, it was selected to implement the online forecasting solution for the DH of Ljubljana and has been generating forecasts with a mean absolute normalized error of 2.70% since November 2019.
Machine-learning-based multi-step heat demand forecasting in a district heating system
Graphical abstract Display Omitted
Highlights Methodology for 48-hour multi-step heat demand forecasting in a DH system. Gaussian process regression outperforms considered machine learning methods. Accurate temperature forecasts are important, solar irradiation forecasts are not. Forecasting errors for 48 h ahead below 3% of the max. heating power. Proposed forecasting solution can be fitted to different DH systems.
Abstract Short-term heat demand forecasting in district heating (DH) systems is essential for a sufficient heat supply and optimal operation of the DH. In this study, a machine learning based multi-step short-term heat demand forecasting approach using the data of the largest Slovenian DH system is considered. The proposed approach involved feature extraction and comparative analysis of different representative machine learning based forecasting models. Nonlinear models performed better than linear models, and the best forecasting results were obtained by Gaussian process regression (GPR), where the mean absolute normalized error was 2.94% of the maximum heating power of the DH system. The analysis confirmed the importance of accurate temperature forecasts but did not confirm the relevance of using future solar irradiation forecasts. The optimal length of training data is shown to be 3 years, and past data of up to 4 days can be used as input to increase the forecasting accuracy. The forecasting model (GPR) proposed in this study can be fitted to different DH systems. In the presented case study, it was selected to implement the online forecasting solution for the DH of Ljubljana and has been generating forecasts with a mean absolute normalized error of 2.70% since November 2019.
Machine-learning-based multi-step heat demand forecasting in a district heating system
Potočnik, Primož (author) / Škerl, Primož (author) / Govekar, Edvard (author)
Energy and Buildings ; 233
2020-12-16
Article (Journal)
Electronic Resource
English
AI , artificial intelligence , ALADIN , Aire Limitee Adaptation dynamique Development International , ANN , artificial neural network , ARMA , autoregressive moving average models , ARSO , Slovenian environmental agency , CET , central European time , CHP , combined heat and power , CNN , convolutional neural network , CPU , central processing unit , CV , cross validation , DH , district heating , ECMWF , European Centre for Medium-Range Weather Forecasts , ELM , extreme learning machines , GP , Gaussian process , GPR , Gaussian process regression , INCA , integrated nowcasting through comprehensive analysis , LM , Levenberg–Marquardt training algorithm , LM–BR , LM algorithm with Bayesian regularization , LR , linear regression , LRord , ordinary linear regression , LRrob , robust regression , LRstep , stepwise regression , LSTM , long short-term memory , MAPE , mean absolute percentage error , MANE , mean absolute normalized error , ML , machine learning , NN , neural network , RVFL , random vector functional link , SVM , support vector machines , SVMlin , linear support vector machine , SVMquad , quadratic support vector machine , TE-TOL , cogeneration heating plant Ljubljana , TOS , heating plant Ljubljana-Šiška , UTC , universal time coordinated , District heating , Heat demand , Short-term forecasting , Machine learning
Applied machine learning: Forecasting heat load in district heating system
| Online Contents | 2016
Forecasting Heat Load for Smart District Heating Systems : A Machine Learning Approach
| BASE | 2014