Heat Load Prediction Research Articles

Physics-guided LSTM model for heat load prediction of buildings

The thermal process of heating buildings is characterized by the multivariable, nonlinear, and large time lag. Accurately predicting building heat loads is crucial for regulating building heating systems. However, the current black-box method of heat load prediction has challenges such as extensive data usage and weak integration with the building's heat transfer process. To address these challenges, a physics-guided long short-term memory (LSTM) model for dynamic heat load prediction in the next seven days based on data-driven and mechanism analysis was proposed. The data for the model were collected from in-situ measurement and numerical simulation. Specifically, the thermal mechanism was introduced to the training loss function of LSTM and the selection of input variables. The influence of the adaptive data time step on prediction accuracy was investigated. The main conclusions obtained from the current data in this paper are drawn as follows. 1) Refining solar radiation intensity calculation for each orientation reduced mean absolute percentage error (MAPE) of heat load prediction results by 0.02%–1.8% compared to horizontal solar radiation intensity. 2) Improving the training loss function decreased MAPE of heat load prediction results by 0.04%–0.43% compared with the original loss function. 3) Adaptive data time step lowered the MAPE of heat load prediction results by 0.08%–1.8% compared with fixed time step. 4) Mean absolute errors corresponding to those three aspects decreased by 25 kJ–558 kJ, 6 kJ–157 kJ, and 41 kJ–1881 kJ. In the future, wider promotion and application of the prediction model will lead to better performance and be more beneficial to energy saving and carbon reduction of the heating system.

Toward explainable heat load patterns prediction for district heating

Heat networks play a vital role in the energy sector by offering thermal energy to residents in certain countries. Effective management and optimization of heat networks require a deep understanding of users' heat usage patterns. Irregular patterns, such as peak usage periods, can exceed the design capacities of the system. However, previous work has mostly neglected the analysis of heat usage profiles or performed on a small scale. To close the gap, this study proposes a data-driven approach to analyze and predict heat load in a district heating network. The study uses data from over eight heating seasons of a cogeneration DH plant in Cheongju, Korea, to build analysis and forecast models using supervised machine learning (ML) algorithms, including support vector regression (SVR), boosting algorithms, and multilayer perceptron (MLP). The models take weather data, holiday information, and historical hourly heat load as input variables. The performance of these algorithms is compared using different training sample sizes of the dataset. The results show that boosting algorithms, particularly XGBoost, are more suitable ML algorithms with lower prediction errors than SVR and MLP. Finally, different explainable artificial intelligence approaches are applied to provide an in-depth interpretation of the trained model and the importance of input variables.

Simplified Model of Heat Load Prediction and Its Application in Estimation of Building Envelope Thermal Performance

This study provides a reference for estimating the building envelope thermal performance at the initial stage of design for nearly zero-energy buildings in different climate zones. A simplified model of heat load prediction, which combines the quasi-steady-state thermal balance calculation procedure in ISO 52016 and the variable-base degree-days method, was proposed. Therefore, a building energy performance evaluation tool BPT V1.0 was developed. Subsequently, the simplified model was validated through comparative analysis with the Building Energy Simulation Test (BESTEST) standard procedure. To conduct a feasibility analysis of the development tool, case studies were performed on the performance evaluation of building envelopes of residential and office buildings in different climate zones in China. Compared to the simulation results from EnergyPlus, the deviation of heat load calculated by BPT V1.0 was within 10%, which further verifies the applicability of the tool under different climatic conditions. Annual heat load under different thermal performance building envelopes was calculated through BPT V1.0. The building energy efficiency improvement rates were found to range from 30 to 60% in nearly zero-energy buildings in different climate zones in China. The study results can provide a reference for energy managers and a basis for estimating the building energy efficiency performance with different envelope thermal properties in the region.

Modeling and validation of a novel load model considering uncertain thermal disturbance in the district heating system

To accomplish precise heating, district heating systems need to understand the demand of heat users comprehensively. Most current heating load prediction models were built on energy center control, with only a few involving user-side control. Thermal disturbance factors differ depending on the type of heat user. This work established a novel heating load model (BHLP-UN model) for the user side in an existing district heating system. The uncertain thermal disturbances were identified and integrated into the base model (BHLP model) with hybrid mechanisms and deep learning methods. The model was calibrated and validated using actual operational data from different types of heat users during multiple heating seasons. The findings showed that the mean absolute percentage error of the BHLP-UN model was decreased by 53.512% −65.338% for different types of heat users compared with the BHLP model, which only considered the meteorological factors and the thermal inertia. Indoor temperature was set as an input variable to effectively analyze the time-varying property of user demand for temperature. When the indoor temperature was 22℃ / 18℃ (working /non-working), the annual load could decrease to 26.501% − 28.572%. The model achieves long-term load trends with short-term forecast accuracy.

Prediction of heating and cooling loads based on light gradient boosting machine algorithms

Machine learning models have been widely used to study the prediction of heating and cooling loads in residential buildings. However, most of these methods use the default hyperparameters, resulting in inaccurate prediction accuracy. In this work, based on hyperparametric optimization algorithms of random search (Random), grid search (Grid), covariance matrix adaptive evolution strategy (CMA-ES), and tree-structured parzen estimator (TPE), were combined with the light gradient boosting machine (LightGBM) model, to construct four hybrid models (Random-LightGBM, Grid-LightGBM, CMA-ES-LightGBM and TPE-LightGBM) for improved prediction accuracy of heating and cooling loads. The LightGBM model was trained using a dataset consisting of building features, cooling set points, and occupant behavior parameters. Feature selection was performed by a random forest-based feature selection method, which determines the input features of the load prediction model. The TPE- LightGBM model achieved the best prediction accuracy among all proposed models with a root mean square error (RMSE) of 0.2714, mean absolute error (MAE) of 0.1416, coefficient of determination (R2) of 0.9981, and mean absolute percentage error (MAPE) of 0.4699% for heating load prediction, and RMSE of 0.1901, MAE of 0.1394, R2 of 0.9924, and MAPE of 2.3509% for cooling load prediction. The proposed TPE-LightGBM model provides an efficient strategy for predicting heating and cooling loads, which can provide better energy efficiency measures at the early design stages of residential buildings.

Automated machine learning-based framework of heating and cooling load prediction for quick residential building design

Reducing the heating and cooling load through energy-efficient building design can help decarbonize the building sector. Heating and cooling load prediction using machine learning (ML) techniques become increasingly important in the rapid assessment of building design variables at the early design stage. However, when applying the ML techniques, it still requires expert knowledge and manually frequent intervention to improve the prediction performance. Hence, this study proposed an automated machine learning (AutoML)-based framework to automatically generate the optimal ML pipelines for heating and cooling load prediction. An experimental dataset of residential buildings was used to evaluate the proposed framework. The proposed framework achieved the best performance with R2 of 0.9965 and RMSE of 0.602 kWh/m2 for heating load prediction, and R2 of 0.9899 and RMSE of 0.973 kWh/m2 for cooling load prediction. The prediction results showed that the proposed framework outperformed the other improved ML models from the representative studies in the last five years. Further, an explainable analysis of the ML models was explored to reveal the relationships between design variables and heating and cooling load. The proposed framework aims at promoting the AutoML-based framework to designers for building energy performance prediction without excessive ML knowledge and manually frequent intervention.

Attention mechanism-based deep learning for heat load prediction in blast furnace ironmaking process

Attention mechanism-based deep learning for heat load prediction in blast furnace ironmaking process

A novel combined model for heat load prediction in district heating systems

Accurate heat load prediction is essential for improving the operational efficiency of district heating systems (DHSs). Numerous heat load prediction models have been proposed to improve the accuracy and stability. However, previous prediction models are limited by training data and hyperparameters and cannot obtain accurate and stable prediction results. This study proposed a combined prediction model to overcome the limitations of a single model. In the proposed model, four classical single models were selected as individual models for prediction. Subsequently, the minimum sum of squares of the combined prediction errors algorithm was used to calculate the weighting coefficient of each individual model. The final prediction results were obtained by combining the prediction results of the four models. The 1-h historical operation data from three heat substations in a DHS in northeast China were adopted to evaluate the performance of the proposed model. The multi-step prediction experiment results of the three datasets revealed that the average mean absolute percentage error values of the proposed model for the one-step, two-step, and three-step predictions reached 2.6%, 4.9%, and 7.0%, respectively; these percentages were significantly lower than those of the four individual models and three representative combined models. Therefore, the proposed model has better prediction performance than previous models in terms of accuracy and stability and can provide a theoretical basis for the precise regulation of DHSs.

Prediction identification method of time-varying internal heat source based on inverse heat transfer problem

Purpose This paper aims to discuss the inverse problems that arise in various practical heat transfer processes. The purpose of this paper is to provide an identification method for predicting the internal boundary conditions for thermal analysis of mechanical structure. A few examples of heat transfer systems are given to illustrate the applicability of the method and the challenges that must be addressed in solving the inverse problem. Design/methodology/approach In this paper, the thermal network method and the finite difference method are used to model the two-dimensional heat conduction inverse problem of the tube structure, and the heat balance equation is arranged into an explicit form for heat load prediction. To solve the matrix ill-conditioned problem in the process of solving the inverse problem, a Tikhonov regularization parameter selection method based on the inverse computation-contrast-adjustment-approach was proposed. Findings The applicability of the proposed method is illustrated by numerical examples for different dynamically varying heat source functions. It is proved that the method can predict dynamic heat source with different complexity. Practical implications The modeling calculation method described in this paper can be used to predict the boundary conditions for the inner wall of the heat transfer tube, where the temperature sensor cannot be placed. Originality/value This paper presents a general method for the direct prediction of heat sources or boundary conditions in mechanical structure. It can directly obtain the time-varying heat flux load and thtemperature field of the machine structure.

Feasibility of Harris Hawks Optimization in Combination with Fuzzy Inference System Predicting Heating Load Energy Inside Buildings

Heating and cooling systems account for a considerable portion of the energy consumed for domestic reasons in Europe. Burning fossil fuels is the main way to produce this energy, which has a detrimental effect on the environment. It is essential to consider a building’s characteristics when determining how much heating and cooling is necessary. As a result, a study of the related buildings’ characteristics, such as the type of cooling and heating systems required for maintaining appropriate indoor air conditions, can help in the design and construction of energy-efficient buildings. Numerous studies have used machine learning to predict cooling and heating systems based on variables that include relative compactness, orientation, overall height, roof area, wall area, surface area, glazing area, and glazing area distribution. Fuzzy logic, however, is not used in any of these methods. In this article, we study a fuzzy logic approach, i.e., HHO−ANFIS (combination of Harris hawks optimization and adaptive neuro-fuzzy interface system), to predict the heating load in residential buildings and investigate the feasibility of this technique in predicting the heating load. Fuzzy techniques obtain perfect results. The analysis results show that the HHO−ANFIS with a population size of 400, the highest value of R2 (0.98709 and 0.98794), and the lowest value of RMSE (0.08769 and 0.08281) in the training and testing dataset, respectively, can predict the heating load with high accuracy. According to the high value of R2 (98%) and low value of RMSE, HHO−ANFIS can be used in predicting the heating load of residential buildings.

Optimal control of TABS using a combined method of MPC and heat load prediction

AbstractThermally activated building systems (TABS), which use the building frame as a radiative and thermal storage site, have attracted attention as a means of achieving a thermal environment in office spaces that combines comfort and energy conservation. However, TABS have a large thermal capacity and a slow thermal response, making it desirable to introduce a control method based on model predictive control (MPC). There are problems with this method, such as its inability to predict periodic fluctuations in thermal load. Therefore, in this study, we propose a control method combining MPC and heat load prediction using a Neural Network, a type of supervised learning in machine learning, for an office space with TABS. The method was validated by co‐simulation using CFD and MATLAB/Simulink on a one‐span (7.20 × 7.20 × 3.87 m) TABS model. As a result, the proposed method reduced the integrated water flow rate and improved the energy performance while improving the control performance.

A hybrid energy-saving prediction model based on SSA-DNN for district heating system

ABSTRACT Accurate heat load prediction is a prerequisite for feed-forward control and on-demand heat supply in district heating system. However, considering that the experimental data used to train the prediction model are often not optimal or most energy efficient, accurate prediction is difficult to achieve effective energy-saving. This paper proposes a hybrid energy-saving prediction model that combines similar sample selection approach (SSA) and deep neural network. A new weighted Euclidean norm (WEN) is used to select suitable similar sample datasets, and a novel energy-saving strategy is proposed to reduce energy consumption. To make the prediction performance more stable, a low-pass filter is used to filter the prediction results. In the case study, real data from a heat exchange station in Tianjin are used to verify the prediction performance of the hybrid model for 1 test day, 3 test days, and 7 test days. Experimental results show that: (a) the proposed model is able to capture the change trend of heat load, with Pearson correlation coefficient of 0.971, 0.969, and 0.954 on different test days, respectively; (b) the proposed model is able to effectively reduce energy consumption, with energy-saving of 5.4%, 7.6%, and 4.8% on different test days, respectively.

Development and Test of a New Fast Estimate Tool for Cooling and Heating Load Prediction of District Energy Systems at Planning Stage

During the design and planning stage of a district energy system, the prediction of the cooling and heating loads is an important step. The accurate estimate of the load pattern can provide a basis for the configuration and optimization of the system. To meet the demand in practical application, this paper proposes a fast load prediction method for district energy systems based on a presimulated forward modelling database and KNN (K-nearest neighbor) algorithm and develops it into a practical tool. Owing to the absence of some design parameters at the planning stage, scenario analysis is also used to determine some input conditions for load prediction. In this paper, the scenarios cover three types of building: office, shopping mall and hotel. To test the performance of this new method, we randomly selected 15 virtual buildings (5 buildings for each type) with different design parameters and took their detailed BPS (building performance simulation) model as a benchmark to assess the prediction results of the new method. The index “ratio of the hours with effective prediction” is defined as the ratio of the hours whose relative error of hourly load prediction is less than 15% to the hours whose load is not 0 in the whole year, and the test result shows that this index is not less than 0.9 (90%) for the predicted cooling load of all 45 test cases and the predicted heating load of 25 of the 45 cases. As a research achievement with practical value, this paper accomplishes the programming work of the tool and makes it into a software. The application of this software in the actual project of district energy system is also presented. The performance of the new load prediction tool was compared with the traditional approach commonly used in engineering—the load estimation based on reference building models—and the result shows that the fast load estimate tool can provide the same level of prediction accuracy as traditional simulation methods.

Building Heating and Cooling Load Prediction Using Ensemble Machine Learning Model.

Building energy consumption prediction has become an important research problem within the context of sustainable homes and smart cities. Data-driven approaches have been regarded as the most suitable for integration into smart houses. With the wide deployment of IoT sensors, the data generated from these sensors can be used for modeling and forecasting energy consumption patterns. Existing studies lag in prediction accuracy and various attributes of buildings are not very well studied. This study follows a data-driven approach in this regard. The novelty of the paper lies in the fact that an ensemble model is proposed, which provides higher performance regarding cooling and heating load prediction. Moreover, the influence of different features on heating and cooling load is investigated. Experiments are performed by considering different features such as glazing area, orientation, height, relative compactness, roof area, surface area, and wall area. Results indicate that relative compactness, surface area, and wall area play a significant role in selecting the appropriate cooling and heating load for a building. The proposed model achieves 0.999 for heating load prediction and 0.997 for cooling load prediction, which is superior to existing state-of-the-art models. The precise prediction of heating and cooling load, can help engineers design energy-efficient buildings, especially in the context of future smart homes.

Improved Harris Hawks Optimization with Hybrid Deep Learning Based Heating and Cooling Load Prediction on residential buildings

In digital era, energy efficient building remains a hot research topic because of increasing concern regarding their environmental impact and energy consumption. Designing a suitable energy efficient building based on their layout namely overall areas, distribution of the glazing areas, orientation, height, and relative compactness. Such components directly impact the heating load (HL) and cooling load (CL) of residential buildings. A precise predicting of load facilitates effective management of energy consumption and improves the quality of life. Lately, several studies have been implemented to predict the CL and HL. The most significant and challenging parts of predictive are defining the effective input parameter and developing a higher accuracy predictive model. The accuracy of predictive model based on machine learning algorithm must be enhanced by hybrid model. With this motivation, this article introduces an Improved Harris Hawks Optimization with Hybrid Deep Learning Based Heating and Cooling Load Prediction (IHHOHDL-HCLP) model on Residential Buildings. The major aim of the IHHOHDL-HCLP model is to determine the CL and HL to accomplish effective energy utilization. To accomplish this, the IHHOHDL-HCLP primarily pre-processes the raw data in two levels namely min-max normalization and polynomial equation. In addition, the HDL model involves convolutional neural network (CNN) along with long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) for HL and CL prediction process. Finally, the IHHO technique was applied for fine-tuning the hyperparameters related to the DL model. The IHHOHDL-HCLP model has demonstrated maximum prediction results with low RMSE values of 0.00874 and 0.00821, respectively, when applied to HL and CL, respectively. The experimental result analysis of the IHHOHDL-HCLP model demonstrates the better performance of the IHHOHDL-HCLP model over other DL models.

Ultrashort-Term Heat Load Prediction for Heat Exchange Stations Based on Dual-Source Data Feature Fusion

Accurate load prediction plays a vital role in the field of district heating. However, it is challenging to establish an accurate mathematical model for heat load prediction because of the technical characteristics of heating systems, such as their large-scale, multidimensional, long delay, strong coupling, time-varying, and nonlinear characteristics. This article proposes a heat load prediction model based on feature fusion of dual-source data (DSDF), and this model fully extracts the characteristics of the working condition data of pipe networks and the data of building energy consumption to make high-precision predictions of the ultrashort-term heat load of heat exchange stations. First, to address the problem of incomplete feature coverage of a single-mode data set, the network working condition data set and building energy consumption data set were constructed, and the random forest method was used to select characteristic variables. Second, a neural network prediction model was constructed. The model captures short- and long-term features through the convolution layer and cyclic layer and captures periodic features through the cyclic jump layer. Finally, the scoring idea of the attention mechanism is introduced, and the predicted results of energy consumption data were used to calibrate the predicted results of pipe network working condition data to improve the model’s prediction performance. Comparative experiments with several algorithms showed that the proposed new method performs well in the task of ultrashort-term prediction of heat load.

Measurements of AC Loss Evolution in ITER TF Conductors

AC loss in the Nb <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub> Sn cable-in-conduit conductors (CICC) usually decreases after the conductor undergoes electromagnetic cycling. This can be attributed to the increase of inter-strand resistance due to the detachment of the strand-bonding during cyclic loading. In the years 2018 to 2020, ITER launched a series of test campaigns in SULTAN test facility, whose aim was to study the T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cs</sub> degradation of TF conductors of all manufactures. Along the main scope of the project, an accompanying study of the AC loss evolution has been measured on two samples. The AC loss was measured prior to any electromagnetic loading, after 1, 5, 50 and 1000 cycles, and at the very end also after a thermal cycle to room temperature. Sinusoidal AC loss was measured in the frequency range of 0.1 to 1.0 Hz. The measured AC evolution will help to predict heat load generated in the TF coils during the initial phase of ITER operation. It may also serve as an input to analysts for deducing the evolution of inter-strand resistance during electromagnetic cycling. The main observation is that already after the first electromagnetic cycle the AC loss reduction is significant, namely 80-90% lower compared to the initial conductor state.

A study on data-driven hybrid heating load prediction methods in low-temperature district heating: An example for nursing homes in Nordic countries

In the face of green energy initiatives and progressively increasing shares of more energy-efficient buildings, there is a pressing need to transform district heating towards low-temperature district heating. The substantially lowered supply temperature of low-temperature district heating broadens the opportunities and challenges to integrate distributed renewable energy, which requires enhancement on intelligent heating load prediction. Meanwhile, to fulfill the temperature requirements for domestic hot water and space heating, separate energy conversion units on user-side, such as building-sized boosting heat pumps shall be implemented to upgrade the temperature level of the low-temperature district heating network. This study conducted hybrid heating load prediction methods with long-term and short-term prediction, and the main work consisted of four steps: (1) acquisition and processing of district heating data of 20 district heating supplied nursing homes in the Nordic climate (2016–2019); (2) long-term district heating load prediction through linear regression, energy signature curve in hourly resolution, providing an overall view and boundary conditions for the unit sizing; (3) short-term district heating load prediction through two Artificial Neural Network models, f72 and g120, with different prediction input parameters; (4) evaluation of the predicted load profiles based on the measured data. Although the three prediction models met the quality criteria, it was found that including the historical hourly heating loads as the input to the forecasting model enhanced the prediction quality, especially for the peak load and low-mild heating season. Furthermore, a possible application of the heating load profiles was proposed by integrating two building-sized heat pumps in low-temperature district heating, which may be a promising heat supply method in low-temperature district heating.

Data augmentation for improving heating load prediction of heating substation based on TimeGAN

Heating load predictions serve as one of the fundamental tasks in heating operation management. Many studies have used data-driven methods to build prediction models, and the quantity and quality of training data are key factors affecting the model performance. However, for some special cases, such as new heating substation and the end period of heating with different load characteristics, sufficient and high-quality data cannot be provided for model training, resulting in low accuracy of the model. In this paper, TimeGAN is applied in the heating field for the first time to augment the data and improve the prediction accuracy of the model. Results show that the prediction error reduces by 50% and CV-RMSE can reach 0.0405 after using TimeGAN in the early period of heating, and the accuracy is highest when the synthetic data are three times of original data. For the mid and end period of heating, the prediction errors can also be reduced by 3%–8% compared with training on original data, and the data amount reaches 15,000–30000, the performance of the model reaches the best.

A hybrid deep reinforcement learning ensemble optimization model for heat load energy-saving prediction

Accurate heat load forecasting is crucial to achieving feed-forward control and on-demand heat supply in the district heating system (DHS). However, accurate forecasting is difficult to achieve effective energy-saving because experimental data are often not optimal or the most energy-efficient. In this study, a hybrid heat load forecasting model with energy-saving consideration is proposed, which consists of similar sample selection approach, short-term forecasting model pool and deep reinforcement learning ensemble strategy. In similar sample selection module, a novel weighted Euclidean norm (EN) is used to select suitable similar samples set for the training samples set. In model pool module, six popular deterministic prediction models are constructed. For energy-saving consideration, the average of minimum and actual heat load is selected as the training target in the training samples set and similar samples set. In ensemble module, deep deterministic policy gradient (DDPG) is used to integrate the prediction results of the base predictors. In the case study, real data from a heat exchange station in Tianjin are used to perform the prediction of heat load 24 h, 72 h and 168 h, respectively. Experimental results show that: (a) The proposed hybrid model is able to capture the change of heat load. The average root mean square error for different prediction periods are 0.0825 MW, 0.1007 MW and 0.1152 MW, respectively; (b) The proposed hybrid model can reduce energy consumption. The energy-saving rate for different periods are 5.33%, 5.31% and 5.07%, respectively.