基于SVMD的改进BWO-TimesNet短期热负荷预测模型

doi:10.16088/j.issn.1001-6600.2023122402

摘要/Abstract

摘要： 精准高效的热负荷预测对于保障热力系统稳定运行和合理规划热力资源至关重要。为了提升热负荷预测的准确性,本文提出一种基于逐次变分模态分解(successive variational mode decomposition,SVMD)和改进白鲸优化算法(improved Beluga whale optimization,IBWO)的TimesNet短期热负荷预测模型。首先,利用SVMD将原始热负荷数据进行分解,去除噪声后得到若干个平稳且有规律的模态分量;其次,根据每个模态分量的特点选择合适的特征作为输入;然后,引入3种策略来改进白鲸优化算法,从而建立IBWO-TimesNet预测模型;最后,通过算例对模型的预测性能进行详细评估。结果表明:SVMD-IBWO-TimesNet模型的MAE、RMSE和R²分别为0.647、1.190和99.1%。与其他主流预测模型相比,该模型具有更高的预测精度。同时,在减少训练样本的情况下,SVMD-IBWO-TimesNet模型仍能有效预测热负荷,具有较强的泛化能力。验证了所提出模型的有效性,为热力系统供热负荷的精准调控提供了参考。

关键词: 热负荷预测, TimesNet, 逐次变分模态分解, 白鲸优化算法

Abstract: Accurate and efficient heat load forecasting is very important to ensure the stable operation of thermal system and rational planning of thermal resources. In order to improve the accuracy of heat load forecasting, a TimesNet short-term heat load forecasting model based on successive variational mode decomposition (SVMD) and an improved beluga optimization algorithm (IBWO) is proposed. Firstly, SVMD is used to decompose the original heat load data, and several stable and regular modal components are obtained after removing noise. Secondly, according to the characteristics of each modal component, the appropriate feature is selected as the input. Then, three strategies are introduced to improve the Beluga optimization algorithm, and the IBWO-TimesNet prediction model is established. Finally, the prediction performance of the model is evaluated in detail by an example. The results show that MAE, RMSE and R² of SVMD-IBWO-TimesNet model are 0.647, 1.190 and 99.1%, respectively. Compared with other mainstream prediction models, this model has higher prediction accuracy. At the same time, the SVMD-IBWO-TimesNet model can still effectively predict the heat load and has strong generalization ability when the training samples are reduced. Therefore, the validity of the proposed model is verified, and the reference is provided for the precise regulation and control of the heating load of the thermal system.

Key words: heat load forecasting, TimesNet, successive variational mode decomposition, beluga optimization algorithm

中图分类号: TM715

段沁宇, 薛贵军, 谭全伟, 谢文举. 基于SVMD的改进BWO-TimesNet短期热负荷预测模型[J]. 广西师范大学学报（自然科学版）, 2024, 42(6): 101-116.

DUAN Qinyu, XUE Guijun, TAN Quanwei, XIE Wenju. Improved BWO-TimesNet Short-term Heat Load Forecasting Model Based onSVMD[J]. Journal of Guangxi Normal University(Natural Science Edition), 2024, 42(6): 101-116.

参考文献

[1] IDOWU S, SAGUNA S, ÅHLUND C, et al. Applied machine learning: Forecasting heat load in district heating system[J]. Energy and Buildings, 2016, 133: 478-488. DOI: 10.1016/j.enbuild.2016.09.068.
[2] VERHELST J, VAN HAM G, SAELENS D, et al. Model selection for continuous commissioning of HVAC-systems in office buildings: A review[J]. Renewable and Sustainable Energy Reviews, 2017, 76: 673-686. DOI: 10.1016/j.rser.2017.01.119.
[3] DAHL M, BRUN A, ANDRESEN G B. Using ensemble weather predictions in district heating operation and load forecasting[J]. Applied Energy, 2017, 193: 455-465. DOI: 10.1016/j.apenergy.2017.02.066.
[4] HAHN H, MEYER-NIEBERG S, PICKL S. Electric load forecasting methods: Tools for decision making[J]. European Journal of Operational Research, 2009, 199(3): 902-907. DOI: 10.1016/j.ejor.2009.01.062.
[5] DONG B, LI Z X, RAHMAN S M M, et al. A hybrid model approach for forecasting future residential electricity consumption[J]. Energy and Buildings, 2016, 117: 341-351. DOI: 10.1016/j.enbuild.2015.09.033.
[6] CHENG R Y, YU J Q, ZHANG M, et al. Short-term hybrid forecasting model of ice storage air-conditioning based on improved SVR[J]. Journal of Building Engineering, 2022, 50: 104194. DOI: 10.1016/j.jobe.2022.104194.
[7] ENESCU D. A review of thermal comfort models and indicators for indoor environments[J]. Renewable and Sustainable Energy Reviews, 2017, 79: 1353-1379. DOI: 10.1016/j.rser.2017.05.175.
[8] KHAMMAYOM N, MARUYAMA N, CHAICHANA C. Simplified model of cooling/heating load prediction for various air-conditioned room types[J]. Energy Reports, 2020, 6(Supplement 2): 344-351. DOI: 10.1016/j.egyr.2019.11.086.
[9] SUN Y, HAGHIGHAT F, FUNG B C M. A review of the-state-of-the-art in data-driven approaches for building energy prediction[J]. Energy and Buildings, 2020, 221: 110022. DOI: 10.1016/j.enbuild.2020.110022.
[10] ALI A, JAYARAMAN R, MAYYAS A, et al. Machine learning as a surrogate to building performance simulation: Predicting energy consumption under different operational settings[J]. Energy and Buildings, 2023, 286: 112940. DOI: 10.1016/j.enbuild.2023.112940.
[11] WANG Z, HONG T Z, PIETTE M A. Building thermal load prediction through shallow machine learning and deep learning[J]. Applied Energy, 2020, 263: 114683. DOI: 10.1016/j.apenergy.2020.114683.
[12] SONG J C, XUE G X, MA Y P, et al. An indoor temperature prediction framework based on hierarchical attention gated recurrent unit model for energy efficient buildings[J]. IEEE Access, 2019, 7: 157268-157283. DOI: 10.1109/ACCESS.2019.2950341.
[13] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C] // Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010.
[14] WU H X, XU J H, WANG J M, et al. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting[C] // Advances in Neural Information Processing Systems 34. Red Hook: Curran Associates, Inc., 2021: 22419-22430.
[15] WU H X, HU T G, LIU Y, et al. TimesNet: Temporal 2D-variation modeling for general time series analysis[EB/OL]. (2023-04-12)[2024-05-08]. https://arxiv.org/abs/2210.02186. DOI: 10.48550/arXiv.2210.02186.
[16] DU B G, HUANG S, GUO J, et al. Interval forecasting for urban water demand using PSO optimized KDE distribution and LSTM neural networks[J]. Applied Soft Computing, 2022, 122: 108875. DOI: 10.1016/j.asoc.2022.108875.
[17] SEKHAR C, DAHIYA R. Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand[J]. Energy, 2023, 268: 126660. DOI: 10.1016/j.energy.2023.126660.
[18] ZHAO W G, WANG L Y, MIRJALILI S. Artificial hummingbird algorithm: A new bio-inspired optimizer with its engineering applications[J]. Computer Methods in Applied Mechanics and Engineering, 2022, 388: 114194. DOI: 10.1016/j.cma.2021.114194.
[19] ARORA S, SINGH S. Butterfly optimization algorithm: A novel approach for global optimization[J]. Soft Computing, 2019, 23(3): 715-734. DOI: 10.1007/s00500-018-3102-4.
[20] 高博,刘建兴,孙浩,等.基于自适应引力搜索算法的定日镜场优化布置 [J].太阳能学报,2022,43(10):119-125.DOI:10.19912/j.0254-0096.tynxb.2021-0397.
[21] 许伦辉,苏楠,骈宇庄,等.基于优化极限学习机的公交行程时间预测方法[J].广西师范大学学报(自然科学版),2021,39(5):64-77.DOI:10.16088/j.issn.1001-6600.2020073102.
[22] 朱菊香,谷卫,钱炜,等.基于IF-SVMD-BWO-LSTM的空气质量预测建模[J/OL].中国测试:1-12[2024-05-08].http://kns.cnki.net/kcms/detail/51.1714.TB.20230207.1749.013.html.
[23] 薛涛,丘森辉,陆豪,等.基于经验模态分解和多分支LSTM网络汇率预测[J].广西师范大学学报(自然科学版),2021,39(2):41-50.DOI:10.16088/j.issn.1001-6600.2020080201.
[24] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544. DOI: 10.1109/TSP.2013.2288675.
[25] NAZARI M, SAKHAEI S M. Successive variational mode decomposition[J]. Signal Processing, 2020, 174: 107610. DOI: 10.1016/j.sigpro.2020.107610.
[26] 谭全伟,薛贵军,谢文举.基于VMD和RDCInformer的短期供热负荷预测模型[J/OL]. 广西师范大学学报(自然科学版):1-17[2024-05-08].https://doi.org/10.16088/j.issn.1001-6600.2023082702. DOI: 10.16088/j.issn.1001-6600.2023082702.
[27] LAHOUAR A, BEN HADJ SLAMA J. Day-ahead load forecast using random forest and expert input selection[J]. Energy Conversion and Management, 2015, 103: 1040-1051. DOI: 10.1016/j.enconman.2015.07.041.

Metrics

Viewed

Full text

147

HTML			PDF

Just accepted	Online first	Issue	Just accepted	Online first	Issue
0	0	0	0	0	147

From	Others	local

Times	38	109
Rate	26%	74%

Abstract

Just accepted	Online first	Issue

0	0	60

From	Others	local

Times	48	12
Rate	80%	20%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared

Discussed