Medium-term heat load prediction for an existing residential building based on a wireless on-off control system

• Published in: Energy (Oxford) Vol. 152; pp. 709 - 718
• Main Authors: Gu, Jihao, Wang, Jin, Qi, Chengying, Min, Chunhua, Sundén, Bengt
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.06.2018; Elsevier BV
• Subjects: Algorithms; Back propagation; Back propagation networks; buildings; China; Control systems; District heating; District heating system; Energiteknik; Energy consumption; Energy efficiency; Energy Engineering; Energy storage; Engineering and Technology; Genetic algorithms; heat; Heat load; Heating; Heating systems; Learning algorithms; Maskinteknik; Mathematical models; Mechanical Engineering; Neural network; Neural networks; Prediction; Prediction models; Predictions; Residential areas; Residential buildings; Residential energy; residential housing; Support vector machine; Support vector machines; Teknik; Temperature; Temperature effects; wavelet; Wavelet analysis; China; District heating system; Support vector machine; Neural network; Heat load; Prediction
• ISSN: 0360-5442; 1873-6785; 1873-6785
• DOI: 10.1016/j.energy.2018.03.179

For district heating systems, prediction of the heat load is a very important topic for energy storage and optimized operation. For large and complex heating systems, most prediction models in previous publications only considered the influence of outdoor temperature, whereas the indoor temperature and thermal inertia of buildings were not included. For an energy-efficient residential building in Shijiazhuang (China), the heat load prediction is investigated using various prediction models, including a wavelet neural network (WNN), extreme learning machine (ELM), support vector machine (SVM) and back propagation neural network optimized by a genetic algorithm (GA-BP). In these models, the indoor temperature and historical loads are considered as influencing factors. It is found that the prediction accuracies of the ELM and GA-BP are slightly higher than that of WNN, so the ELM and GA-BP models provide feasible methods for the heat load prediction. The SVM shows smaller relative errors in the model prediction compared with three neural network algorithms. 1.Indoor temperature and building thermal inertia were included in prediction models;2.Modified models were used to predict a 7-day heat load;3.Neural network algorithms and support vector machine were both investigated;4.Daily-accumulated heat supply was proposed instead of instantaneous heat supply.