计算机科学 ›› 2024, Vol. 51 ›› Issue (4): 158-164.doi: 10.11896/jsjkx.230100089
陈润桓1, 戴华1,2, 郑桂能3, 李惠1, 杨庚1,2
CHEN Runhuan1, DAI Hua1,2, ZHENG Guineng3, LI Hui1 , YANG Geng1,2
摘要: 城市电力负荷预测是城市智能电网规划和调度的一项重要内容。然而,城市电力负荷预测中存在数据不均的问题,给城市电力负荷预测带来了巨大挑战。传统的基于单一模型的方法难以解决数据不均的问题,而现有的基于多模型的预测方法根据电力负荷分布将数据集拆分成多个子数据集,然后分别建立多个预测模型进行预测,该类方案在一定程度上解决了数据不均问题,但存在模型构建成本较高、不同分布样本间共有的电力分布特征发生分离等问题。基于此,提出了一个轻量级城市电力负荷预测模型(Lighten-DCSC-LSTM)。该模型通过在长短期记忆网络的基础上引入差异补偿的思想和短期采样对比损失进行构建,同时构建共享特征提取层来降低模型构建成本。其中,差异补偿思想通过学习不同电力负荷分布样本之间的差异对主序列预测模块的预测结果进行差异补偿,短期采样对比损失通过动态类中心的对比学习损失对模型的训练进行正则化。为了验证模型的性能,进行了参数调优和对比实验。对比实验结果表明,模型在预测电力负荷的任务中取得了良好的性能。
中图分类号:
[1]SHAHIDEHPOUR M,YAMIN H,LI Z.Market operations in electric power systems:forecasting,scheduling,and risk ma-nagement[M].John Wiley & Sons,2003. [2]PENYA Y K,BORGES C E,FERNÁNDEZ I.Short-term load forecasting in non-residential buildings[C]//IEEE Africon'11.IEEE,2011:1-6. [3]MANSOOR M,GRIMACCIA F,LEVA S,et al.Comparison of echo state network and feed-forward neural networks in electrical load forecasting for demand response programs[J].Mathematics and Computers in Simulation,2021,184:282-293. [4]KOENKER R,XIAO Z.Quantile autoregression[J].Journal ofthe American statistical association,2006,101(475):980-990. [5]SINGH S,PARMAR K S,KUMAR J,et al.Developmentof new hybrid model of discrete wavelet decomposition and autoregressive integrated moving average(ARIMA) models in application to one month forecast the casualties cases of COVID-19[J].Chaos,Solitons & Fractals,2020,135:109866. [6]JOSHUVA A,SUGUMARAN V.A machine learning approachfor condition monitoring of wind turbine blade using autoregressive moving average(ARMA) features through vibration signals:a comparative study[J].Progress in Industrial Ecology,an International Journal,2018,12(1/2):14-34. [7]CHEN J F,WANG W M,HUANG C M.Analysis of an adap-tive time-series autoregressive moving-average(ARMA) model for short-term load forecasting[J].Electric Power Systems Research,1995,34(3):187-196. [8]KHAN A R,MAHMOOD A,SAFDAR A,et al.Load Forecas-ting and Dynamic Pricing based Energy Management in Smart Grid-A Review[C]//International Multi-topic Conference.2015. [9]SAVIOZZI M,MASSUCCO S,SILVESTRO F.Implementation of advanced functionalities for Distribution Management Systems:Load forecasting and modeling through Artificial Neural Networks ensembles[J].Electric Power Systems Research,2019,167:230-239. [10]ZHAO H,MAGOULÈS F.A review on the prediction of build-ing energy consumption[J].Renewable and Sustainable Energy Reviews,2012,16(6):3586-3592. [11]HOPFIELD J.Neural networks and physical systems withemergent collective computational abilities[J].Proceedings of the national academy of sciences,1982,79(8):2554-2558. [12]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural computation,1997,9(8):1735-1780. [13]SCHUSTER M,PALIWAL K K.Bidirectional recurrent neural networks[J].IEEE transactions on Signal Processing,1997,45(11):2673-2681. [14]ALHUSSEIN M,AURANGZEB K,HAIDER S I.Hybrid CNN-LSTM model for short-term individual household load forecasting[J].IEEE Access,2020,8:180544-180557. [15]CHOI M,KIM H,HAN B,et al.Channel attention is all you need for video frame interpolation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:10663-10671. [16]LI X,LU X L.ethod for Forecasting Short-Term Power Load Based on Dual-Stage Attention Mechanism and Gated Recurrent Unit Network[J].Computer Engineering,2022,48(2):291-296,305. [17]QIN J,ZHANG Y,FAN S,et al.Multi-task short-term reactive and active load forecasting method based on attention-LSTM model[J].International Journal of Electrical Power & Energy Systems,2022,135:107517. [18]GHOSH S,VINYALS O,STROPE B,et al.Contextual lstm(clstm) models for large scale nlp tasks[J].arXiv:1602.06291,2016. [19]WENINGER F,ERDOGAN H,WATANABE S,et al.Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR[C]//International Conference on Latent Variable Analysis and Signal Separation.Cham:Sprin-ger,2015:91-99. [20]CAO J,LI Z,LI J.Financial time series forecasting model based on CEEMDAN and LSTM[J].Physica A:Statistical mechanics and its applications,2019,519:127-139. [21]HU Y L,CHEN L.A nonlinear hybrid wind speed forecasting model using LSTM network,hysteretic ELM and Differential Evolution algorithm[J].Energy conversion and management,2018,173:123-142. [22]LIANG T,ZHAO Q,LV Q,et al.A novel wind speed prediction strategy based on Bi-LSTM,MOOFADA and transfer learning for centralized control centers[J].Energy,2021,230:120904. [23]AGRAWAL R,FALOUTSOS C,SWAMI A.Efficient similarity search in sequence databases[C]//International Conference on Foundations of Data Organization and Algorithms.Berlin:Springer,1993:69-84. [24]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014. |
|