Abstract
The selection of input variables and their amount has been an important issue in big data load forecasting. Taking heating load forecasting as an example, this paper proposed a method for data filtering based on information entropy. First, the heating data from an air source heat pump system adopted by a rural residence in northern China were employed. Moreover, the training data were classified based on linear or nonlinear variations of outdoor temperature and its changing ranges, while the validation data included three different types of weather conditions, namely, cold, cool, and mild. Then, the information entropy under 2-h, 4-h, 6-h and 8-h training window was quantified to be 1.811, 1.839, 1.877 and 1.856, respectively. For the employed rural residence, an equivalent three-resistance and two-capacity model was established to validate the effectiveness of the training window. Using the derived optimal thermal resistance and capacity, the various selection of outdoor temperature variation trend and range were compared and optimized. Results showed that 6 h of training data had the maximum information entropy and the most abundant information, the minimum errors between actual and forecasting data were observed under 6 h of training data, linear change, and lower outdoor temperature. The mean absolute percentage errors for the load forecasting of three typical days were 5.63%, 8.46%, and 12.10%, respectively.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Abbreviations
- C:
-
thermal capacitance
- E:
-
information entropy
- R:
-
thermal resistance
- T:
-
Temperature
- cp:
-
specific heat
- m:
-
mass flow rate of water
- in:
-
indoor air
- out:
-
outdoor air
- p:
-
probability distribution
- s:
-
supply water
- r:
-
return water
- w:
-
building opaque envelope
- inf:
-
infiltration
- m:
-
internal thermal mass
- AT:
-
Actual temperature
- GA:
-
Genetic algorithm
- PCA:
-
Principle component analysis
- RC:
-
Resistance–capacitance
- RF:
-
Random forest
- MAE:
-
Mean absolute error
- MAPE:
-
Mean absolute percentage error
- RMSE:
-
Root-mean square error
- R2 :
-
R-squared
References
Al-Musaylh, M. S., Deo, R. C., Li, Y., et al., 2018, Two-phase particle swarm optimized-support vector regression hybrid model integrated with improved empirical mode decomposition with adaptive noise for multiple-horizon electricity demand forecasting: Applied Energy, 217, 422–439.
Amasyali, K., El-Gohary, N., 2021, Machine learning for occupant-behavior-sensitive cooling energy consumption prediction in office buildings: Renewable and Sustainable Energy Reviews, 142, 110714.
Chen, Y. B., Zhang, F. Y., Berardi, U., 2020, Day-ahead prediction of hourly subentry energy consumption in the building sector using pattern recognition algorithms: Energy, 211, 118530.
Dai, J. H., Hu, H., Hu, Q. H., et al, 2016, Attribute reduction in interval-valued information systems based on information entropies: Frontiers of Information Technology and Electronic Engineering. 17, 919–928.
Datale, L. D., Svetozarevic, B., Heer, P., et al, 2022, Physically Consistent Neural Networks for building thermal modeling: Theory and analysis: Applied Energy, 325, 119806.
Deng, Z. X., Li, T. R., Deng, D. Y., et al., 2022, Feature selection for label distribution learning using dual-similarity based neighborhood fuzzy entropy: Information Sciences, 615, 385–404.
Ding, Y., Zhang, Q., Yuan, T. H., et al., 2018, Effect of input variables on cooling load prediction accuracy of an office building: Applied Thermal Engineering, 128, 225–234.
Dong, Z. X., Liu, J. Y., Liu, B., et al., 2021, Hourly energy consumption prediction of an office building based on ensemble learning and energy consumption pattern classification: Energy and Buildings, 241(2), 110929.
Chen, Y. B., Zhang, F. Y., Berardi, U., 2020, Day-ahead prediction of hourly subentry energy consumption in the building sector using pattern recognition algorithms: Energy, 211, 118530.
Ghosh, S., Yadav, V. K., Mukherjee, V., 2018, Evaluation of cumulative impact of partial shading and aerosols on different PV array topologies through combined Shannon’s entropy and DEA: Energy, 144, 765–775.
He, J. L., Qu, L. D., Li, Z. W., 2024, An oscillatory particle swarm optimization feature selection algorithm for hybrid data based on mutual information entropy: Applied Soft Computing, 152, 111261.
Kang, L. G., Li, H., Wang, Z. C., et al., 2023, Investigation of Energy Consumption via an Equivalent Thermal Resistance-Capacitance Model for a Northern Rural Residence: Energies, 16 (23),7835.
Kang, L. G., Wang, J. Z., Yuan, X. X., et al., 2023, Research on energy management of integrated energy system coupled with organic Rankine cycle and power to gas: Energy Conversion and Management, 287, 117117.
Ledesma S., Hernández-Pérez, I., Belma, J. M., et al., 2020, Using Artificial Intelligence to Analyze the Thermal Behavior of Building Roofs: Journal of Energy Engineering, 146 (4), 0000677.
Li, H., Li, Y. H., Wang, Z. C., et al., 2022, Integrated building envelope performance evaluation method towards nearly zero energy buildings based on operation data: Energy and Buildings, 268, 112219.
Li, K. J., Zhang, J. X., Chen, X., et al., 2022, Building’s hourly electrical load prediction based on data clustering and ensemble learning strategy: Energy and Buildings, 261, 111943.
Li, Z. W., Wang, P., Mu, S., 2022, A strategy of improving indoor air temperature prediction in HVAC system based on multivariate transfer entropy: Building and Environment, 219, 109164.
Lin, P. H., Zhang, L.M., Zuo, J., 2022, Data-driven prediction of building energy consumption using an adaptive multi-model fusion approach: Applied Soft Computing, 129, 109616.
Liu, H. Y., Yu, J. Q., Dai, J. W., et al., 2023, Hybrid prediction model for cold load in large public buildings based on mean residual feedback and improved SVR: Energy and Buildings, 294, 113229.
Liu, Z. Y., Yu, J. Q., Feng, C. Y., et al., 2023, A hybrid forecasting method for cooling load in large public buildings based on improved long short term memory: Journal of Building Engineering, 76, 107238.
Lu, H. F., Cheng, F. F., Ma, X., et al., 2020, Short-term prediction of building energy consumption employing an improved extreme gradient boosting model: A case study of an intake tower: Energy, 203, 117756.
Lu, S. L., Huo, Y. Q., Su, N., et al., 2023, Energy Consumption Forecasting of Urban Residential Buildings in Cold Regions of China: Journal of Energy Engineering, 149(2), 4556.
Luo, X. J., Oyedele, L. O., Ajayi, A. O., et al., 2020, Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings: Renewable and Sustainable Energy Reviews, 131, 109980.
Panapakidis, I. P., Papadopoulos, T. A., Christoforidis, G. C., et al., 2014, Pattern recognition algorithms for electricity load curve analysis of buildings: Energy and Buildings, 73, 137–145.
Quanga, D. N., Anh, N., Thia, N., et al., 2021, Hybrid online model based multi seasonal decompose for short-term electricity load forecasting using ARIMA and online RNN: Journal of Intelligent and Fuzzy Systems: Applications in Engineering and Technology, 41(5), 5639–5652.
Rossini, R., Poccia, S., Candan, K. S., et al., 2019, CA-Smooth: Content Adaptive Smoothing of Time Series Leveraging Locally Salient Temporal Features, MEDES19: 11th International Conference on Management of Digital EcoSystems.
Tan, M., Chen, J., Cao, Y. J., et al., 2023, A multi-task learning method for multi-energy load forecasting based on synthesis correlation analysis and load participation factor: Applied Energy, 343, 121177.
Wang, D., Zheng, W. F., Wang, Z., et al., 2023, Comparison of reinforcement learning and model predictive control for building energy system optimization: Applied Thermal Engineering, 228, 120430.
Wang, S., Sun, Y. H., Zhou, Y., et al., 2019, A New Hybrid Short-Term Interval Forecasting of PV Output Power Based on EEMD-SE-RVM: Energies, 13, 1–17.
Xiao, J. W., Cao, M. H., Fang, H. L., et al., 2023, Joint load prediction of multiple buildings using multi-task learning with selected-shared-private mechanism: Energy and Buildings, 293, 113178.
Yang, W. W., Shi, J., Li, S. J., et al., 2022, A combined deep learning load forecasting model of single household resident user considering multi-time scale electricity consumption behavior: Applied Energy, 307, 118197.
Yi, Y. K., Anis, M., Jang, K., et al., 2023, Application of machine learning (ML) and genetic algorithm (GA) to optimize window wing wall design for natural ventilation: Journal of Building Engineering, 68, 106218.
Zhang, H. Y., Sun, Q. Q., Dong, K. Z., 2023, Information-theoretic partially labeled heterogeneous feature selection based on neighborhood rough sets: International Journal of Approximate Reasoning, 154, 200–217.
Zhang, X., Mei, C. L., Chen, D. G., et al., 2016, Feature selection in mixed data: a method using a novel fuzzy rough set-based information entropy: Pattern Recognition, 56, 1–16.
Zhao, Z. W., Huang, D., Li, Z. W., 2023, Outlier detection for partially labeled categorical data based on conditional information entropy: International Journal of Approximate Reasoning, 164, 109086.
Zhou, Y., Liu, Y. F., Wang, D. J., 2021, Comparison of machine-learning models for predicting short-term building heating load using operational parameters: Energy and buildings, 253, 111505.
Zhu, Y. Q., Sun, S. X., Liu, C. Y., et al., 2023, PoQ-Consensus Based Private Electricity Consumption Forecasting via Federated Learning: Computer Modeling in Engineering and Sciences, 136(3), 3285–3297.
Acknowledgments
This work was supported by the Opening Funds of the State Key Laboratory of Building Safety and Built Environment (grant number: BSBE-EET2021-01).
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the Opening Funds of the State Key Laboratory of Building Safety and Built Environment (grant number: BSBE-EET2021-01).
Zhichao Wang, male, from Beijing, PhD, director of Environmental Measurement and Control Optimization Research Center, Environmental Energy Institute, China Academy of Building Science, mainly research on green building, regional energy planning and performance optimization of building electromechanical systems.
Ligai Kang, female, from Shijiazhuang, PhD, Associate Professor, Hebei University of Science and Technology, mainly research on integrated energy systems and building energy conservation.
Rights and permissions
About this article
Cite this article
Kang, Lg., Li, H., Wang, Zc. et al. Training data selection using information entropy: Application to heating load modeling of rural residence in northern China. Appl. Geophys. (2024). https://doi.org/10.1007/s11770-024-1120-9
Received:
Revised:
Published:
DOI: https://doi.org/10.1007/s11770-024-1120-9