With the rapid development of the smart grid, the power system has been driven toward intelligent and efficient development. In the process of predicting power load, problems such as unreasonable decomposition of load data and low prediction accuracy have been observed. A BiLSTNet combined prediction model based on optimized quadratic decomposition was proposed. Firstly, the load data were decomposed and reconstructed using improved complete ensemble empirical modal decomposition with adaptive noise (ICEEMDAN) to reduce the overall noise effect of the data. Secondly, the variational mode decomposition (VMD) was applied for the secondary decomposition and reconstruction. To optimize the decomposition parameters of VMD, the enhanced sand cat swarm optimization (ESCSO) was utilized, in which the Kent chaotic map was introduced to initialize the algorithm population, and both the vertical-horizontal search strategy and adaptive t-distribution perturbation were adopted to enhance global search and the ability to jump out of the local optimum. Finally, the reconstructed data were fed into BiLSTNet hybrid model for prediction. Experimental results demonstrate that the proposed method achieves better decomposition results and prediction accuracy on the Australian electricity load dataset than other traditional hybrid models, showing higher practical value.
电力负荷模型主要有:数学模型、机器学习模型以及深度学习混合模型。随着目前技术不断进步,建立数学模型已成为过去式,应用深度学习模型成为主流,在简化模型建立的同时提高了预测精度。Mounir等[6]提出了使用长短期记忆网络(long short term memory, LSTM)网络对负荷数据进行预测,但LSTM只能处理单向时间序列数据,无法充分考虑负荷的内在联系。Wu等[7]提出一种CNN-LSTM-BiLSTM的混合网络预测模型。Chen等[8]将卷积神经网络(convolutional neural networks, CNN)集成到Transformer的编码位置,并且使用因果卷积代替点积计算,证实了模型的可靠性。Liu等[9]提出CNN-双向长短期记忆网络(bidirectional long short-term memory, BiLSTM)-Attention混合预测模型。Luo等[10]提出了CNN-BiLSTM-Attention和XGBoost的混合预测方法。网络的超参数配置对预测结果的影响也至关重要,Zhou等[11]使用改进的麻雀搜索算法对LSTM网络参数进行优化。Asiri等[12]提出白鲸优化算法(beluga whale optimization, BWO)对CNN-BiLSTM网络的超参数进行寻优,使预测结果更加精准。夏梦等[13]提出一种改进鱼鹰算法优化双向门控循环单元(bidirectional gated recurrent unit, BiGRU)网络超参数的预测方法,通过混沌映射、动态精英引导机制和最优-随机均值变异3种策略对鱼鹰算法进行寻优,使用优化后的算法对BiGRU模型进行超参数配置,提高模型对数据处理的性能。
ErenY, Küçükdemiralİ. A comprehensive review on deep learning approaches for short-term load forecasting[J]. Renewable and Sustainable Energy Reviews, 2024, 189: 114031.
[2]
TarmaniniC, SarmaN, GezeginC, et al. Short term load forecasting based on ARIMA and ANN approaches[J]. Energy Reports, 2023, 9: 550-557.
XuShixin, LiWenting, PengDaogang, et al. Power load forecasting based on quadratic mode decomposition and Informer BiLSTM[J]. Zhejiang Electric Power, 2025, 44(10): 55-68.
[5]
ZhuJ, DongH, ZhengW, et al. Review and prospect of data-driven techniques for load forecasting in integrated energy systems[J]. Applied Energy, 2022, 321: 119269.
[6]
LimB, ZohrenS. Time-series forecasting with deep learning: a survey[J]. Philosophical Transactions of the Royal Society A, 2021, 379(2194): 20200209.
[7]
MounirN, OuadiH, JrhilifaI. Short-term electric load forecasting using an EMD-BI-LSTM approach for smart grid energy management system[J]. Energy and Buildings, 2023, 288: 113022.
[8]
WuK, WuJ, FengL, et al. An attention-based CNN-LSTM-BiLSTM model for short-term electric load forecasting in integrated energy system[J]. International Transactions on Electrical Energy Systems, 2021, 31(1): e12637.
[9]
ChenB, YangW, YanB, et al. An advanced airport terminal cooling load forecasting model integrating SSA and CNN-Transformer[J]. Energy and Buildings, 2024, 309: 114000.
[10]
LiuF, LiangC. Short-term power load forecasting based on AC-BiLSTM model[J]. Energy Reports, 2024, 11: 1570-1579.
[11]
LuoS, WangB, GaoQ, et al. Stacking integration algorithm based on CNN-BiLSTM-Attention with XGBoost for short-term electricity load forecasting[J]. Energy Reports, 2024, 12: 2676-2689.
[12]
ZhouM, WangL, HuF, et al. ISSA-LSTM: a new data-driven method of heat load forecasting for building air conditioning[J]. Energy and Buildings, 2024, 321: 114698.
[13]
AsiriM M, AldehimG, AlotaibiF A, et al. Short-term load forecasting in smart grids using hybrid deep learning[J]. IEEE Access, 2024, 12: 23504-23513.
XiaMeng, YuHuijun. Short term power load forecasting based on VMD IOOA Bi GRU model and error compensation[J]. Science Technology and Engineering, 2025, 25(27): 11642-11650.
XiaoWei, FangNa, DengXin. Power load forecasting based on VMD-LSTM-IPSO-GRU[J]. Science Technology and Engineering, 2024, 24(16): 6734-6741.
[18]
MengZ, XieY, SunJ. Short-term load forecasting using neural attention model based on EMD[J]. Electrical Engineering, 2022, 104(3): 1857-1866.
[19]
ChenT, HuangW, WuR, et al. Short term load forecasting based on SBiGRU and CEEMDAN-SBiGRU combined model[J]. IEEE Access, 2020, 9: 89311-89324.
[20]
LiK, HuangW, HuG, et al. Ultra-short term power load forecasting based on CEEMDAN-SE and LSTM neural network[J]. Energy and Buildings, 2023, 279: 112666.
[21]
DragomiretskiyK, ZossoD. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2013, 62(3): 531-544.
[22]
LüL, WuZ, ZhangJ, et al. A VMD and LSTM based hybrid model of load forecasting for power grid security[J]. IEEE Transactions on Industrial Informatics, 2021, 18(9): 6474-6482.
[23]
GengG, HeY, ZhangJ, et al. Short-term power load forecasting based on PSO-optimized VMD-TCN-attention mechanism[J]. Energies, 2023, 16(12): 4616.
[24]
WangN, LiZ. Short term power load forecasting based on BES-VMD and CNN-Bi-LSTM method with error correction[J]. Frontiers in Energy Research, 2023, 10: 1076529.
[25]
ShiJ, TehJ. Load forecasting for regional integrated energy system based on complementary ensemble empirical mode decomposition and multi-model fusion[J]. Applied Energy, 2024, 353: 122146.
[26]
ColominasM A, SchlotthauerG, TorresM E. Improved complete ensemble EMD: a suitable tool for biomedical signal processing[J]. Biomedical Signal Processing and Control, 2014, 14: 19-29.
ZhouKun, MaTianyi, LiTing, et al. Summer peak power load forecasting method based on BSLO optimized VMD-CNN-GRU model[J]. Research on Printing and Digital Media Technology, 2025(5): 335-346.
[29]
SeyyedabbasiA, KianiF. Sand cat swarm optimization: a nature-inspired algorithm to solve global optimization problems[J]. Engineering with Computers, 2023, 39(4): 2627-2651.
[30]
LaiG, ChangW, YangY, et al. Modeling long-and short-term temporal patterns with deep neural networks[C]// Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. Pittsburgh, PA: ACM, 2018: 95-104.
ZhaoXingyu, WuQuanjun, ZhuWei. Short term power load forecasting based on CEEMDAN and TCN-LSTM models[J]. Science Technology and Engineering, 2023, 23(4): 1557-1564.