Abstract
Given the significant practical implications of energy consumption prediction for the design and energy conservation control of refrigeration systems, numerous methods have been proposed in this field. However, existing approaches face two primary challenges. Firstly, refrigeration system energy consumption is heavily influenced by external factors, making it difficult for current methods or models to capture the randomness of energy consumption data. Secondly, prediction models struggle to control error accumulation during inference, leading to difficulties in forecasting energy consumption data over extended time ranges. To address these issues, this paper proposes an energy consumption prediction model based on adversarial networks and Transformer networks—ANFormer. The ANFormer model, leveraging self-attention mechanisms and feedforward neural networks, encodes and models input sequences to forecast future energy consumption of refrigeration systems. Ultimately, validation experiments conducted on datasets from two real refrigeration systems demonstrate the accuracy and efficiency of ANFormer.The experimental results show that the ANFormer model proposed in this paper has optimized the values of MSE and RMSE by approximately 3%-15% compared to FreTS, DLinear, and NLinear models. Compared to Linear, Transformer, AutoFormer, and Informer models, the results in terms of MSE, RMSE, and MAE have all been optimized by more than 79%.
This work was supported in part by the Key R&D Plan of Shandong Province (2022CXGC020106).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Soltani, M., Dehghani-Sanij, A., Sayadnia, A., et al.: Investigation of airflow patterns in a new design of wind tower with a wetted surface. Energies 11(5), 1100 (2018)
De, R.K., Ganguly, A.: Modeling and analysis of a solar thermal-photovoltaic-hydrogen-based hybrid power system for running a standalone cold storage. J. Clean. Prod. 293, 126202 (2021)
Ahmad, T., Chen, H., Guo, Y., Wang, J.: A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: a review. Energy Build. 165(5), 301–320 (2018)
Tamba, J.G., Essiane, S.N., Sapnken, E.F., et al.: Forecasting natural gas: a literature survey. Int. J. Energy Econ. Policy 8(3), 216–249 (2018)
De Vega, M., Venegas, M., GarcÃa-Hernando, N.: Modeling and performance analysis of an absorption chiller with a microchannel membrane-based absorber using LiBr-H2O, LiCl-H2O, and LiNO3-NH3. Int. J. Energy Res. 42(11), 3544–3558 (2018)
Brownbridge, O., Sully, M., Noons, J., Albayati, I.M.: Modeling and simulation of a retail commercial refrigeration system. J. Thermal Sci. Eng. Appl. 13(6), 061028 (2021)
Yi, K., Zhang, Q., Fan, W., et al.: Frequency-domain MLPs are more effective learners in time series forecasting. In: Advances in Neural Information Processing Systems, vol. 36 (2024)
Luo, X., Oyedele, L.O.: Forecasting building energy consumption: adaptive long-short term memory neural networks driven by genetic algorithm. Adv. Eng. Inform. 50(3), 101357 (2021)
Wu, H., Xu, J., Wang, J., Long, M.: Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. Adv. Neural. Inf. Process. Syst. 34, 22419–22430 (2021)
Zhou, H., et al: Informer: Beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11106–11115 (2021)
Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., Jin, R.: Fedformer: frequency enhanced decomposed transformer for long-term series forecasting. In: Proceedings of the International Conference on Machine Learning, PMLR, pp. 27268–27286 (2022)
Tuli, S., Casale, G., Jennings, N.R.: Tranad: Deep transformer networks for anomaly detection in multivariate time series data. arXiv preprint arXiv:220107284 (2022)
Audibert, J., Michiardi, P., Guyard, F., Marti, S., Zuluaga, M.A.: USAD: unsupervised anomaly detection on multivariate time series. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3395–3404 (2020)
Zeng, A., Chen, M., Zhang, L., Xu, Q.: Are transformers effective for time series forecasting? In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 11121–11128(2023)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, H. et al. (2024). Energy Consumption Prediction Method for Refrigeration Systems Based on Adversarial Networks and Transformer Networks. In: Cao, C., Chen, H., Zhao, L., Arshad, J., Asyhari, T., Wang, Y. (eds) Knowledge Science, Engineering and Management. KSEM 2024. Lecture Notes in Computer Science(), vol 14888. Springer, Singapore. https://doi.org/10.1007/978-981-97-5489-2_27
Download citation
DOI: https://doi.org/10.1007/978-981-97-5489-2_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5488-5
Online ISBN: 978-981-97-5489-2
eBook Packages: Computer ScienceComputer Science (R0)