基于改进深度森林的短期电力负荷预测模型
作者:
中图分类号:

TP391

基金项目:

国家自然科学基金资助项目(61672123)。


Short term power load forecasting model based on improved deep forest
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    深度学习模型通过学习数据的深层特征能够有效提高电力负荷预测的准确率,但同时也带来了超参数较多、模型可解释性差等问题。针对这些问题,文中将深度森林模型引入短期电力负荷预测领域。在多粒度级联森林模型的基础上改进了多粒度窗口扫描方法,调整窗口大小与滑动步长,使模型能够在不同时间尺度下提取电力负荷数据的周期性特征。此外,改进深度森林输出层的计算方法,将输出结果由离散的类向量改进为连续的预测值,进而提高模型的精确度。最后在中国东北电网的实测数据中验证了文中所提出方法的可行性与有效性。从实验结果可知,改进深度森林算法在较高预测精度的情况下能取得更高的准确率,并且相较于深度神经网络具有更快的学习速度。

    Abstract:

    Deep learning method can help to learn the deep features of power load data and improve the accuracy of prediction, but it also brings problems, such as large amounts of super parameters and poor interpretability of the model. To solve these problems, this paper introduces the deep forest model for short-term load forecasting. Based on the multi-Grained Cascade forest model, the multi-granularity window scanning method is improved with adjusted window size and sliding step size, so that the model can extract the periodicity characteristics of power load data in different time scales. In addition, the calculation method of deep forest output layer is improved with changing the output result from discrete class vector to continuous predicted value, improving the accuracy of the model. Finally, the feasibility and effectiveness of the proposed method are verified with the measured data of northeast China power grid. The experimental results show that the improved deep forest algorithm can achieve higher accuracy with higher prediction accuracy, and has faster learning speed than the deep neural network.

    参考文献
    [1] 杨博宇, 陈仕军. 电力负荷预测研究综述及预测分析[J]. 四川电力技术, 2018, 41(3):56-60, 91.Yang B Y, Chen S J. Overview of electrical load forecasting researches and forecasting analysis[J]. Sichuan Electric Power Technology, 2018, 41(3):56-60, 91. (in Chinese)
    [2] 牟丰. 基于机器学习的短期电力负荷预测算法研究[D]. 西安:西安科技大学, 2018.Mou F. Research on short-term power load forecasting algorithm based on machine learning[D]. Xi'an:Xi'an University of Science and Technology, 2018. (in Chinese)
    [3] 孙建梅, 钱秀婷, 王永晴. 基于改进灰色模型的中长期电力负荷预测[J]. 电工技术, 2019(19):28-31.Sun J M, Qian X T, Wang Y Q. Medium and long term power load forecasting based on improved grey model[J]. Electric Engineering, 2019(19):28-31.(in Chinese)
    [4] 张志, 延菱, 崔慧军, 等. 考虑关联因素的智能化中长期电力负荷预测方法[J]. 电力系统保护与控制, 2019, 47(2):24-30.Zhang Z, Du Y L, Cui H J, et al. Intelligent mid-long electricity load forecast method considering associated factors[J]. Power System Protection and Control, 2019, 47(2):24-30. (in Chinese)
    [5] 邢海军, 程浩忠, 张沈习, 等. 主动配电网规划研究综述[J]. 电网技术, 2015, 39(10):2705-2711.Xing H J, Cheng H Z, Zhang S X, et al. Review of active distribution network planning[J]. Power System Technology, 2015, 39(10):2705-2711. (in Chinese)
    [6] 罗宁, 高华, 贺墨琳. 基于神经网络的电力负荷预测方法研究[J]. 自动化与仪器仪表, 2020(1):157-160.Luo N, Gao H, He M L. Research on power load forecasting method based on neural network[J]. Automation & Instrumentation, 2020(1):157-160. (in Chinese)
    [7] 简献忠, 顾祎婷. 一种基于全过程优化支持向量机的短期电力负荷预测方法[J]. 电力科学与工程, 2018, 34(11):45-51.Jian X Z, Gu Y T. Short-term electric load forecasting method based on global optimization support vector machine[J]. Electric Power Science and Engineering, 2018, 34(11):45-51. (in Chinese)
    [8] 张静, 石鑫. 基于改进MOPSO-BP算法的短期电力负荷预测研究[J]. 电力学报, 2019, 34(6):556-563.Zhang J, Shi X. Short-term power load forecasting based on improved MOPSO-BP algorithm[J]. Journal of Electric Power, 2019, 34(6):556-563. (in Chinese)
    [9] Kong W, Dong Z Y, Jia Y, et al. Short-term residential load forecasting based on LSTM recurrent neural network[J]. IEEE Transactions on Smart Grid, 2017, 10(1):841-851.
    [10] Kuo P H, Huang C J. A high precision artificial neural networks model for short-term energy load forecasting[J]. Energies, 2018, 11(1):213.
    [11] Chen K, Chen K, Wang Q, et al. Short-term load forecasting with deep residual networks[J]. IEEE Transactions on Smart Grid, 2018, 10(4):3943-3952.
    [12] Zhou Z H, Feng J. Deep forest[J]. arXiv preprint arXiv:1702.08835, 2017.
    [13] Guo Y, Liu S, Li Z, et al. BCDForest:a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data[J]. BMC bioinformatics, 2018, 19(5):118.
    [14] Su R, Liu X, Wei L, et al. Deep-resp-forest:a deep forest model to predict anti-cancer drug response[J]. Methods, 2019, 166:91-102.
    [15] Tanno R, Arulkumaran K, Alexander D C, et al. Adaptive neural trees[J]. arXiv preprint arXiv:1807.06699, 2018.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

彭飞,马煜,张晓华,吴奕,邓文琛,陈志奎.基于改进深度森林的短期电力负荷预测模型[J].重庆大学学报,2022,45(5):1-8.

复制
分享
文章指标
  • 点击次数:402
  • 下载次数: 883
  • HTML阅读次数: 819
  • 引用次数: 0
历史
  • 收稿日期:2020-02-15
  • 在线发布日期: 2022-06-11
文章二维码