Predicting hourly heating load in a district heating system based on a hybrid CNN-LSTM model

Abstract Heat loads change dynamically with meteorological conditions and user demand, and the related accurate prediction algorithms are conducive to the realization of optimized automatic control and green heating. However, a traditional load forecasting algorithm exhibits low accuracy and is sensitive to data noise. Hence, it is difficult to satisfy the requirements of industrial applications via forecasting algorithms. The progress in big data technology leads to the construction of a smart district heating system (SDHS) with the next generation technology wherein artificial intelligence algorithms play the role of a chemical catalyst. The operation monitoring of heat exchange stations installed with various Internet of Things (IoT) sensors provides abundant data resources for heating load forecasting based on machine learning algorithms. A novel estimation model based on spatiotemporal hybrid convolution neural network long–short term memory (CNN–LSTM) is presented to predict the heating load more reasonably for the SDHS. This hybrid model deeply integrates the excellent feature extraction ability of CNN and LSTM in spatiotemporal two-dimensional feature space. Furthermore, CNN can extract the heating load's spatial characteristics and influencing factors, and LSTM can extract the heating load's temporal characteristics. Therefore, the CNN–LSTM algorithm can describe the complex change trend of the heating load and lead to a more accurate dynamic model of heating load with high nonlinearity and considerable thermal inertia delay. A detailed performance comparison was conducted between the CNN–LSTM and support vector machine (SVM) and ensemble learning algorithms, such as extra tree regression (ETR), random forest regression (RFR), gradient boosting regression (GBR), multiple layer perception (MLP). The experimental results showed the evident accuracy advantages of prediction performance based on the proposed CNN–LSTM algorithm. The MAPE evaluation indexes of the four heat exchange stations are distributed between 3.1% and 4.1%. Besides, this algorithm exhibits good adaptability for heating load data with different numerical ranges, which can satisfy the field engineering applications' requirements in a more enhanced manner.

[1]  Mary Ann Piette,et al.  Building thermal load prediction through shallow machine learning and deep learning , 2020, Applied Energy.

[2]  Shahaboddin Shamshirband,et al.  Forecasting of consumers heat load in district heating systems using the support vector machine with a discrete wavelet transform algorithm , 2015 .

[3]  Tanveer Ahmad,et al.  Short and medium-term forecasting of cooling and heating load demand in building environment with data-mining based approaches , 2018 .

[4]  Luigi Glielmo,et al.  Model Predictive Control-Based Optimal Operations of District Heating System With Thermal Energy Storage and Flexible Loads , 2017, IEEE Transactions on Automation Science and Engineering.

[5]  Long Chen,et al.  Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation , 2017 .

[6]  Peder Bacher,et al.  Online short-term forecast of greenhouse heat load using a weather forecast service , 2017 .

[7]  Fu Xiao,et al.  A short-term building cooling load prediction method using deep learning algorithms , 2017 .

[8]  Shi-Jie Cao,et al.  Investigation of temperature regulation effects on indoor thermal comfort, air quality, and energy savings toward green residential buildings , 2019, Science and Technology for the Built Environment.

[9]  Yixiong Feng,et al.  Big Data Analytics for System Stability Evaluation Strategy in the Energy Internet , 2017, IEEE Transactions on Industrial Informatics.

[10]  Yeong-Koo Yeo,et al.  Optimization of district heating systems based on the demand forecast in the capital region , 2009 .

[11]  Edvard Govekar,et al.  Linear and Neural Network-based Models for Short-Term Heat Load Forecasting , 2015 .

[12]  Shahaboddin Shamshirband,et al.  Prediction of heat load in district heating systems by Support Vector Machine with Firefly searching algorithm , 2016 .

[13]  Dragan Mitić,et al.  Appraisal of soft computing methods for short term consumers' heat load prediction in district heating systems , 2015 .

[14]  Yong Chen,et al.  Multifactor spatio-temporal correlation model based on a combination of convolutional neural network and long short-term memory neural network for wind speed forecasting , 2019, Energy Conversion and Management.

[15]  Risto Lahdelma,et al.  Evaluation of a multiple linear regression model and SARIMA model in forecasting heat demand for district heating system , 2016 .

[16]  Zhe Tian,et al.  Development of the heating load prediction model for the residential building of district heating based on model calibration , 2020 .

[17]  Gorm Bruun Andresen,et al.  Improving Short-Term Heat Load Forecasts with Calendar and Holiday Data , 2018, Energies.

[18]  T Ivan Ciric,et al.  Heat load prediction of small district heating system using artificial neural networks , 2016 .

[19]  Imran A. Zualkernan,et al.  A smart home energy management system using IoT and big data analytics approach , 2017, IEEE Transactions on Consumer Electronics.

[20]  Wei Li,et al.  Indoor thermal environment optimal control for thermal comfort and energy saving based on online monitoring of thermal sensation , 2019, Energy and Buildings.

[21]  Davide Anguita,et al.  Dynamic Delay Predictions for Large-Scale Railway Networks: Deep and Shallow Extreme Learning Machines Tuned via Thresholdout , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[22]  Udayraj,et al.  A study of thermal comfort enhancement using three energy-efficient personalized heating strategies at two low indoor temperatures , 2018, Building and Environment.

[23]  Tanveer Ahmad,et al.  A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: A review , 2018 .

[24]  Yeong-Koo Yeo,et al.  Heat consumption forecasting using partial least squares, artificial neural network and support vector regression techniques in district heating systems , 2010 .

[25]  İsmail Yabanova,et al.  Development of ANN model for geothermal district heating system and a novel PID-based control strategy , 2013 .

[26]  Jianqiang Yi,et al.  Building Energy Consumption Prediction: An Extreme Deep Learning Approach , 2017 .

[27]  Asifullah Khan,et al.  Wind power prediction using deep neural network based meta regression and transfer learning , 2017, Appl. Soft Comput..

[28]  Jinfu Chen,et al.  Wind Speed Prediction with Spatio–Temporal Correlation: A Deep Learning Approach , 2018 .

[29]  Qinghua Hu,et al.  Transfer learning for short-term wind speed prediction with deep neural networks , 2016 .

[30]  Zhenyu Zhou,et al.  Game-Theoretical Energy Management for Energy Internet With Big Data-Based Renewable Power Forecasting , 2017, IEEE Access.

[31]  Honglu Zhu,et al.  Hybrid Power Forecasting Model for Photovoltaic Plants Based on Neural Network with Air Quality Index , 2017 .

[32]  DalipiFisnik,et al.  Data-Driven Machine-Learning Model in District Heating System for Heat Load Prediction , 2016 .

[33]  Sven Werner,et al.  Daily Heat Load Variation in Swedish District Heating Systems , 2013 .

[34]  Magnus Dahl,et al.  Using ensemble weather predictions in district heating operation and load forecasting , 2017 .

[35]  Qie Sun,et al.  Statistical analysis of energy consumption patterns on the heat demand of buildings in district heating systems , 2014 .