针对传统分解技术与人工智能模型结合存在的预测精度低、多种负荷之间复杂的耦合关系导致的预测困难等问题,提出一种基于完全自适应噪声集合经验模态分解（CEEMDAN）、鲸鱼优化算法（WOA）和门控循环单元（GRU）的短期负荷预测模型。采用斯皮尔曼相关性系数（SRCC）选择不同的负荷作为输入特征,挖掘多种负荷在不同季节的内在联系;对负荷序列进行CEEMDAN分解处理,以解决负荷序列过于复杂而导致预测精度低的问题;并引入WOA算法对GRU网络的内部参数进行寻优,以克服GRU网络选取参数过程的随机性问题;最后,通过对比仿真验证所提模型的有效性。实验结果表明,CEEMDAN-WOA-GRU相较于RNN、TCN、LSTM、GRU,均方根误差和平均绝对误差分别下降44.5%、43.1%、44.4%、32.2%和47.2%、46.9%、44.1%、36.4%,决定系数分别提高了27.4%、34.8%、25.7%、17.7%。
Abstract
Aiming at the problems of low prediction accuracy and difficult prediction caused by complex coupling relationship between multiple loads in the combination of traditional decomposition technology and artificial intelligence model, a short-term load forecasting model based on Completely Adaptive Ensemble Empirical Mode Decomposition（CEEMDAN）,Whale Optimization Algorithm（WOA）and Gated Recurrent Unit（GRU）is proposed. The Spearman correlation coefficient（SRCC）is used to select different loads as input features to mine the internal relationship of multiple loads in different seasons. The load sequence is decomposed by CEEMDAN to solve the problem of low prediction accuracy caused by too complex load sequence. The WOA algorithm is introduced to optimize the parameters in the GRU network to overcome the randomness of the parameter selection process of the GRU network. Finally,the effectiveness of the proposed model is verified by comparative simulation. The experimental results showed that compared with RNN, TCN, LSTM, and GRU, CEEMDAN-WOA-GRU reduced root mean square error and mean absolute error by 44.5%, 43.1%, 44.4%, 32.2%, and 47.2%, 46.9%, 44.1%, and 36.4%, respectively, and increased coefficient of determination by 27.4%, 34.8%, 25.7%, and 17.7%, respectively.
关键词
自适应噪声完备经验模态分解 /
鲸鱼优化算法 /
综合能源系统 /
门控循环单元 /
负荷预测
Key words
CEEMDAN /
whale optimization algorithm /
integrated energy system /
gated recurrent unit /
load forecasting
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] WANG Y, WANG Y, HUANG Y, et al.Planning and operation method of the regional integrated energy system considering economy and environment[J]. Energy, 2019, 171(2019): 731-750.
[2] ZENG M, LIU Y, ZHOU P, et al.Review and prospects of integrated energy system modeling and benefit evaluation[J]. Power system technology, 2018, 42(6): 1697-1708.
[3] GUO Y, LI Y, QIAO X, et al.BiLSTM multitask learning-based combined load forecasting considering the loads coupling relationship for multienergy system[J]. IEEE transactions on smart grid, 2022, 13(5): 3481-3492.
[4] YAN Y, ZHANG Z.Cooling, heating and electrical load forecasting method for integrated energy system based on SVR model[C]//2021 6th Asia conference on power and electrical engineering (ACPEE). IEEE, 2021: 1753-1758.
[5] CHEN J, HU Z, CHEN W, et al.Load prediction of integrated energy system based on combination of quadratic modal decomposition and deep bidirectional long short-term memory and multiple linear regression[J]. Automation of electric power systems, 2021, 45(13): 85-94.
[6] SHI H, XU M, LI R.Deep learning for household load forecasting—a novel pooling deep RNN[J]. IEEE transactions on smart grid, 2017, 9(5): 5271-5280.
[7] WEI L Y, TSAI C H, CHUNG Y C, et al.A study of the hybrid recurrent neural network model for electricity loads forecasting[J]. International journal of academic research in accounting, finance and management sciences, 2017, 7(2): 21-29.
[8] MUZAFFAR S, AFSHARI A.Short-term load forecasts using LSTM networks[J]. Energy procedia, 2019, 158: 2922-2927.
[9] 薛阳, 燕宇铖, 贾巍, 等. 基于改进灰狼算法优化长短期记忆网络的光伏功率预测[J]. 太阳能学报, 2023, 44(7): 207-213.
XUE Y, YAN Y C, JIA W, et al.Photovoltaic power prediction model based on IGWO-LSTM[J]. Acta energiae solaris sinica, 2023, 44(7): 207-213.
[10] 杨国清, 刘世林, 王德意, 等. 基于Attention-GRU风速修正和Stacking的短期风电功率预测[J]. 太阳能学报, 2022, 43(12): 273-281.
YANG G Q, LIU S L, WANG D Y, et al.Short-term wind power forecasting based on Attention-GRU wind speed correction and Stacking[J]. Acta energiae solaris sinica, 2022, 43(12): 273-281.
[11] 王智冬, 刘连光, 刘自发, 等. 基于量子粒子群算法的风火打捆容量及直流落点优化配置[J]. 中国电机工程学报, 2014, 34(13): 2055-2062.
WANG Z D, LIU L G, LIU Z F,et al.Optimal configuration of wind & coal power capacity and DC placement based on quantum PSO algorithm[J]. Proceedings of the CSEE, 2014, 34(13): 2055-2062.
[12] 李畸勇, 张伟斌, 赵新哲, 等. 改进鲸鱼算法优化支持向量回归的光伏最大功率点跟踪[J]. 电工技术学报, 2021, 36(9): 1771-1781.
LI J Y, ZHANG W B, ZHAO X Z,et al.Global maximum power point tracking for PV array based on support vector regression optimized by improved whale algorithm[J]. Transactions of China Electrotechnical Society, 2021, 36(9): 1771-1781.
[13] MIRJALILI S, LEWIS A.The whale optimization algorithm[J]. Advances in engineering software, 2016, 95: 51-67.
[14] WU J, ZHOU T, LI T.A hybrid approach integrating multiple ICEEMDANs, WOA, and RVFL networks for economic and financial time series forecasting[J]. Complexity, 2020, 2020(1): 9318308.
[15] CHAN J C, MA H, SAHA T K, et al.Self-adaptive partial discharge signal de-noising based on ensemble empirical mode decomposition and automatic morphological thresholding[J]. IEEE transactions on dielectrics and electrical insulation, 2014, 21(1): 294-303.
[16] 金吉, 王斌, 喻敏, 等. 基于分形特征的自适应EEMD及其在风功率预测中的应用[J]. 太阳能学报, 2023, 44(5): 416-424.
JIN J, WANG B, YU M, et al.Adaptive EEMD on basis of fraction characteristics and its application on wind power forecasting[J]. Acta energiae solaris sinica, 2023, 44(5):416-424.
[17] 周小麟, 童晓阳. 基于CEEMD-SBO-LSSVR的超短期风电功率组合预测[J]. 电网技术, 2021, 45(3): 855-864.
ZHOU X L, TONG X Y, et al.Ultra-short-term wind power combined prediction based on CEEMD-SBO-LSSVR[J]. Power system technology, 2021, 45(3): 855-864.
[18] TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE international Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2011: 4144-4147.
[19] LI P, WANG Z, WANG J, et al.A multi-time-space scale optimal operation strategy for a distributed integrated energy system[J]. Applied energy, 2021, 289: 116698.
[20] ASU. Campus metabolism[EB/OL].2021, http://cm.asu.edu/.
[21] RICHMAN J S, LAKE D E, MOORMAN J R.Sample entropy[M]//Methods in Enzymology. Academic Press, 2004, 384: 172-184.
PDF(2851 KB)
