摘要
电力行业需要精确的短期电力负荷预测,为电力系统的控制和调度提供精确的负载需求。为提高短期电力负荷预测的精度,提出了一种基于FFT优化ResNet模型的方法。模型首先将电力负荷预测定义为时间序列问题,随后引入一维ResNet进行电力负荷的回归预测,并提出使用FFT优化ResNet,通过对一层卷积结果进行FFT变换,赋予模型提取数据中周期性特征的能力。实验表明,在6 h电力负荷预测中,FFT-ResNet的预测精度优于几种基准模型,说明该方法在电力负荷预测方面具有良好的应用前景。
Power industry requires accurate short-term load forecasting to provide precise load requirements for power system control and scheduling. In order to improve the accuracy of short-term power load forecasting, a method based on FFT optimized ResNet model is proposed. The model first defines power load forecasting as a time series problem, then introduces one-dimensional ResNet for power load regression prediction, and proposes to use FFT to optimize ResNet, the FFT transform of a layer of convolution results gives the model the ability to extract periodic features in the data. Experiments show that the prediction accuracy of FFT-ResNet is better than several benchmark models in 6-hour power load forecasting, which indicates that this method has a good application prospect in power load forecasting.
引文
[1]Hippert H S,Pedreira C E,Souza R C.Neural Networks for Short-Term Load Forecasting:A Review and Evaluation[J].IEEETransactions on Power Systems,2001,16(1):44-55.
[2]郑岗,刘斌,周勇,等.基于神经元网络的短期电力负荷预测[J].西安理工大学学报,2002,18(2):126-130.Zheng G,Liu B,Zhou Y,et al.Short-Term Load Forecasting Based on Neural Network[J].Journal of Xi'an University of Technology,2002,18(2):126-130.
[3]何川,舒勤,贺含峰,等.ICA特征提取与BP神经网络在负荷预测中的应用[J].电力系统及其自动化学报,2014,26(8):40-46.He C,Shu Q,He H F,et al.Application of BP Neural Network and ICA Feature Extraction in Power Load Forecasting[J].Electric Power System and Automation,2014,26(8):40-46.
[4]Greff K,Srivastava R K,Koutnik J,et al.LSTM:A Search Space Odyssey[J].IEEE Transactions on Neural Networks&Learning Systems,2017,28(10):2222-2232.
[5]Marino D L,Amarasinghe K,Manic M.Building Energy Load Forecasting Using Deep Neural Networks[C]//IECON 2016-42nd Annual Conference of the IEEE Industrial Electronics Society.IEEE,2016.
[6]Cho K,Merrienboer B V,Bahdanau D,et al.On the Properties of Neural Machine Translation:Encoder-Decoder Approaches[J].Computer Science,2014,47(10):103-111.
[7]路宽,孟祥荣,孙雯雪,等.多层Bi-GRU的Seq2seq网络短期电力负荷预测模型[C]//2017智能电网新技术发展与应用研讨会论文集,2017.Lu K,Meng X R,Sun W X,et al.Multi-Layer Bi-GRU Seq2seq Network Model for Short-Term Power Load Forecasting[C]//2017the Smart Grid Development and Application of New Technology Symposium Proceedings,2017.
[8]Ba J,Hinton G E,Mnih V,et al.Using Fast Weights to Attend to the Recent Past[C]//Advances in Neural Information Processing Systems.2016:4331-4339.
[9]Oord A V D,Dieleman S,Zen H,et al.WaveNet:A Generative Model for Raw Audio[J].arXiv preprint arXiv:1609.03499,2016.
[10]Kalchbrenner N,Espeholt L,Simonyan K,et al.Neural Machine Translation in Linear Time[J].arXiv preprint arXiv:1610.10099,2016.
[11]Dauphin Y N,Fan A,Auli M,et al.Language Modeling with Gated Convolutional Networks[J].arXiv preprint arXiv:1612.08083,2016.
[12]Gehring J,Auli M,Grangier D,et al.A convolutional encoder model for neural machine translation[J].arXiv preprint arXiv:1611.02344,2016.
[13]Gehring J,Auli M,Grangier D,et al.Convolutional sequence to sequence learning[J].arXiv preprint arXiv:1705.03122,2017.
[14]Dong X,Qian L,Huang L.Short-term load forecasting in smart grid:A combined CNN and K-means clustering approach[C]//Big Data and Smart Computing(BigComp),2017 IEEE International Conference on.IEEE,2017:119-125.
[15]He K,Zhang X,Ren S,et al.Deep Residual Learning for Image Recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2016:770-778.
[16]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems.Curran Associates Inc.2012:1097-1105.
[17]Hong T,Fan S.Probabilistic electric load forecasting:A tutorial review[J].International Journal of Forecasting,2016,32(3):914-938.