A Data-Efficient Building Electricity Load Forecasting Method Based on Maximum Mean Discrepancy and Improved TrAdaBoost Algorithm
Abstract
:1. Introduction
1.1. Related Works
1.2. Contribution and Novelty
1.3. Paper Organization
2. Principles and Methods
2.1. Principle of Transfer Learning
2.2. The Improved TrAdaBoost Algorithm
Algorithm 1 iTrAdaBoost algorithm |
Input: Target training dataset , source training dataset , merged training dataset , target dataset S, weak predictive models (Learner) and number of iterations N. Initialization Initialize the weight vector , For : Set the weight to meet: Call Learner. Based on the merged training data T and the weights of each data , a hypothesis is obtained, . Calculate the error of on : Set the mean square error , and threshold Calculate the error rate of the prediction. If the error of on is less than the threshold , the prediction is considered accurate; if the error of on is greater than the threshold , the prediction is considered inaccurate. Set , and , where . f is the number of inaccurate predictions. Update the new weight vector as follows: Output: The final result at the end of the iteration. |
2.3. Maximum Mean Discrepancy (MMD) Similarity Judgment
2.4. General Framework
3. Data Sources and Data Preprocessing
3.1. Data Sources
3.2. Data Preprocessing
4. Results and Analysis
4.1. Parameter Setting
4.2. Results with Different Ratios of Target-Domain Data
4.3. Verification of MMD Effectiveness
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Daut, M.A.M.; Hassan, M.Y.; Abdullah, H.; Rahman, H.A.; Abdullah, M.P.; Hussin, F. Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: A review. Renew. Sustain. Energy Rev. 2017, 70, 1108–1118. [Google Scholar] [CrossRef]
- Li, K.; Xue, W.; Tan, G.; Denzer, A.S. A state of the art review on the prediction of building energy consumption using data-driven technique and evolutionary algorithms. Build. Serv. Eng. Res. Technol. 2020, 41, 108–127. [Google Scholar] [CrossRef]
- Khalil, M.; McGough, A.S.; Pourmirza, Z.; Pazhoohesh, M.; Walker, S. Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption—A systematic review. Eng. Appl. Artif. Intell. 2022, 115, 105287. [Google Scholar] [CrossRef]
- Fathi, S.; Srinivasan, R.; Fenner, A.; Fathi, S. Machine learning applications in urban building energy performance forecasting: A systematic review. Renew. Sustain. Energy Rev. 2020, 133, 110287. [Google Scholar] [CrossRef]
- Manfren, M.; James, P.A.; Tronchin, L. Data-driven building energy modelling–An analysis of the potential for generalisation through interpretable machine learning. Renew. Sustain. Energy Rev. 2022, 167, 112686. [Google Scholar] [CrossRef]
- Etemad, A.; Shafaat, A.; Bahman, A.M. Data-driven performance analysis of a residential building applying artificial neural network (ANN) and multi-objective genetic algorithm (GA). Build. Environ. 2022, 7, 109633. [Google Scholar]
- Tian, J.; Li, K.; Xue, W. An adaptive ensemble predictive strategy for multiple scale electrical energy usages forecasting. Sustain. Cities Soc. 2021, 66, 102654. [Google Scholar] [CrossRef]
- Xiao, L.; Li, M.; Zhang, S. Short-term power load interval forecasting based on nonparametric Bootstrap errors sampling. Energy Rep. 2022, 8, 6672–6686. [Google Scholar] [CrossRef]
- Xiao, J.; Li, Y.; Xie, L.; Liu, D.; Huang, J. A hybrid model based on selective ensemble for energy consumption forecasting in China. Energy 2018, 159, 534–546. [Google Scholar] [CrossRef]
- Li, K.; Zhang, J.; Chen, X.; Xue, W. Building’s hourly electrical load prediction based on data clustering and ensemble learning strategy. Energy Build. 2022, 261, 111943. [Google Scholar] [CrossRef]
- Li, K.; Tian, J.; Xue, W.; Tan, G. Short-term electricity consumption prediction for buildings using data-driven swarm intelligence based ensemble model. Energy Build. 2021, 231, 110558. [Google Scholar] [CrossRef]
- Nastasi, B.; Manfren, M.; Groppi, D.; Lamagna, M.; Mancini, F.; Garcia, D.A. Data-driven load profile modelling for advanced measurement and verification (M&V) in a fully electrified building. Build. Environ. 2022, 221, 109279. [Google Scholar]
- Li, X.; Jiang, H.; Liu, Y.; Wang, T.; Li, Z. An integrated deep multiscale feature fusion network for aeroengine remaining useful life prediction with multisensor data. Knowl.-Based Syst. 2022, 235, 107652. [Google Scholar] [CrossRef]
- Tronchin, L.; Manfren, M.; Nastasi, B. Energy analytics for supporting built environment decarbonisation. Energy Procedia 2019, 157, 1486–1493. [Google Scholar] [CrossRef]
- Weiss, K.; Khoshgoftaar, T.M.; Wang, D. A survey of transfer learning. J. Big Data 2016, 3, 1–40. [Google Scholar] [CrossRef] [Green Version]
- Pan, S.J.; Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 2009, 22, 1345–1359. [Google Scholar] [CrossRef]
- Zhuang, F.; Qi, Z.; Duan, K.; Xi, D.; Zhu, Y.; Zhu, H.; Xiong, H.; He, Q. A comprehensive survey on transfer learning. Proc. IEEE 2020, 109, 43–76. [Google Scholar] [CrossRef]
- Reddy, S.; Akashdeep, S.; Harshvardhan, R.; Kamath, S. Stacking Deep learning and Machine learning models for short-term energy consumption forecasting. Adv. Eng. Inform. 2022, 52, 101542. [Google Scholar]
- Peirelinck, T.; Kazmi, H.; Mbuwir, B.V.; Hermans, C.; Spiessens, F.; Suykens, J.; Deconinck, G. Transfer learning in demand response: A review of algorithms for data-efficient modelling and control. Energy AI 2022, 7, 100126. [Google Scholar] [CrossRef]
- Begum, N.; Hazarika, M.K. Maturity detection of tomatoes using Transfer Learning. Meas. Food 2022, 7, 100038. [Google Scholar] [CrossRef]
- Zhong, J.; Li, J.; Lotfi, A.; Liang, P.; Yang, C. An incremental cross-modal transfer learning method for gesture interaction. Robot. Auton. Syst. 2022, 155, 104181. [Google Scholar] [CrossRef]
- Jamil, F.; Verstraeten, T.; Nowé, A.; Peeters, C.; Helsen, J. A deep boosted transfer learning method for wind turbine gearbox fault detection. Renew. Energy 2022, 197, 331–341. [Google Scholar] [CrossRef]
- Ruder, S.; Peters, M.E.; Swayamdipta, S.; Wolf, T. Transfer learning in natural language processing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials, Florence, Italy, 28 July–2 August 2019; pp. 15–18. [Google Scholar]
- Zhao, W.; Queralta, J.P.; Westerlund, T. Sim-to-real transfer in deep reinforcement learning for robotics: A survey. In Proceedings of the 2020 IEEE Symposium Series on Computational Intelligence (SSCI), Canberra, Australia, 1–4 December 2020; IEEE: New York, NY, USA, 2020; pp. 737–744. [Google Scholar]
- Ahn, Y.; Kim, B.S. Prediction of building power consumption using transfer learning-based reference building and simulation dataset. Energy Build. 2022, 258, 111717. [Google Scholar] [CrossRef]
- Jain, M.; Gupta, K.; Sathanur, A.; Chandan, V.; Halappanavar, M.M. Transfer-learnt models for predicting electricity consumption in buildings with limited and sparse field data. In Proceedings of the 2021 American Control Conference (ACC), New Orleans, LA, USA, 26–28 May 2021; IEEE: New York, NY, USA, 2021; pp. 2887–2894. [Google Scholar]
- Ye, R.; Dai, Q. A relationship-aligned transfer learning algorithm for time series forecasting. Inf. Sci. 2022, 593, 17–34. [Google Scholar] [CrossRef]
- Yang, K.; Lu, J.; Wan, W.; Zhang, G.; Hou, L. Transfer learning based on sparse Gaussian process for regression. Inf. Sci. 2022, 605, 286–300. [Google Scholar] [CrossRef]
- Li, B.; Rangarajan, S. A conceptual study of transfer learning with linear models for data-driven property prediction. Comput. Chem. Eng. 2022, 157, 107599. [Google Scholar] [CrossRef]
- Wang, C.; Yuan, J.; Huang, K.; Zhang, J.; Zheng, L.; Zhou, Z.; Zhang, Y. Research on thermal load prediction of district heating station based on transfer learning. Energy 2022, 239, 122309. [Google Scholar] [CrossRef]
- Dai Wenyuan, Y.Q.; Guirong, X.; Yong, Y. Boosting for transfer learning. In Proceedings of the 24th International Conference on Machine Learning, Corvallis, OR, USA, 20–24 June 2007; pp. 193–200. [Google Scholar]
- Liu, B.; Liu, L.; Xiao, Y.; Liu, C.; Chen, X.; Li, W. AdaBoost-based transfer learning with privileged information. Inf. Sci. 2022, 593, 216–232. [Google Scholar] [CrossRef]
- Liu, B.; Liu, C.; Xiao, Y.; Liu, L.; Li, W.; Chen, X. AdaBoost-based transfer learning method for positive and unlabelled learning problem. Knowl.-Based Syst. 2022, 241, 108162. [Google Scholar] [CrossRef]
- Fan, C.; Sun, Y.; Xiao, F.; Ma, J.; Lee, D.; Wang, J.; Tseng, Y.C. Statistical investigations of transfer learning-based methodology for short-term building energy predictions. Appl. Energy 2020, 262, 114499. [Google Scholar] [CrossRef]
- Freund, Y.; Schapire, R.E. Experiments with a new boosting algorithm. Icml. Citeseer 1996, 96, 148–156. [Google Scholar]
- Freund, Y.; Schapire, R.E. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 1997, 55, 119–139. [Google Scholar] [CrossRef] [Green Version]
- Fang, X.; Gong, G.; Li, G.; Chun, L.; Peng, P.; Li, W. A general multi-source ensemble transfer learning framework integrate of LSTM-DANN and similarity metric for building energy prediction. Energy Build. 2021, 252, 111435. [Google Scholar] [CrossRef]
Parameter | Value |
---|---|
Prediction task | short-term building electricity load |
Building type | educational building |
Auxiliary data source | Great Energy Predictor III competition organized by ASHRAE |
Similarity judgment method | MMD |
Prediction algorithm | iTrAdaBoost |
External meteorological data | air temperature and dew temperature and wind speed |
and wind direction and sea-level pressure | |
Time step | hourly |
BP network structure | 8–10–1 |
Learning rate | 0.1 |
Initial threshold | 0.1 |
Iteration number | 100 |
Model | Ratio of Target Domain Data | MAPE (%) | RMSE (kWh) | MAE (kWh) |
---|---|---|---|---|
BP | 16.79 | 117.7988 | 106.3294 | |
AdaBoost | 10% | 10.01 | 80.4766 | 61.1933 |
iTrAdaBoost | 8.94 | 73.3029 | 58.3681 | |
BP | 16.35 | 117.6454 | 105.0066 | |
AdaBoost | 20% | 8.91 | 68.2793 | 52.3476 |
iTrAdaBoost | 7.37 | 64.8076 | 48.9637 | |
BP | 13.22 | 110.7241 | 90.0883 | |
AdaBoost | 30% | 7.51 | 64.0791 | 49.8123 |
iTrAdaBoost | 6.72 | 55.6497 | 43.2473 |
Model | MAPE (%) | RMSE (kWh) | MAE (kWh) |
---|---|---|---|
BP | 20.53 | 149.0932 | 135.4407 |
AdaBoost | 14.02 | 95.4129 | 84.3469 |
iTrAdaBoost | 12.26 | 84.2419 | 74.1522 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, K.; Wei, B.; Tang, Q.; Liu, Y. A Data-Efficient Building Electricity Load Forecasting Method Based on Maximum Mean Discrepancy and Improved TrAdaBoost Algorithm. Energies 2022, 15, 8780. https://doi.org/10.3390/en15238780
Li K, Wei B, Tang Q, Liu Y. A Data-Efficient Building Electricity Load Forecasting Method Based on Maximum Mean Discrepancy and Improved TrAdaBoost Algorithm. Energies. 2022; 15(23):8780. https://doi.org/10.3390/en15238780
Chicago/Turabian StyleLi, Kangji, Borui Wei, Qianqian Tang, and Yufei Liu. 2022. "A Data-Efficient Building Electricity Load Forecasting Method Based on Maximum Mean Discrepancy and Improved TrAdaBoost Algorithm" Energies 15, no. 23: 8780. https://doi.org/10.3390/en15238780
APA StyleLi, K., Wei, B., Tang, Q., & Liu, Y. (2022). A Data-Efficient Building Electricity Load Forecasting Method Based on Maximum Mean Discrepancy and Improved TrAdaBoost Algorithm. Energies, 15(23), 8780. https://doi.org/10.3390/en15238780