+高级检索
基于联邦学习的短期负荷预测模型协同训练方法
作者单位:

1.湖南大学;2.重庆大学

基金项目:

国家电网湖南省电力公司科技项目(5216A221001G)


Federated Learning Based Coordinated Training Method of a Short-term Load Forecasting Model
Affiliation:

1.Hunan University;2.Chongqing University

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
    摘要:

    机器学习方法被广泛应用于电力系统短期负荷预测领域,但现有短期负荷预测方法未考虑以下问题:一是在配电网中各负荷运营商数据样本数量与特征不足;二是负荷预测模型泛化能力较差;三是由于负荷相关数据具有高度隐私保护要求,参与者们无法共享数据训练负荷预测模型。因此,目前亟需一个在保护各参与方数据隐私的前提下实现协同训练预测模型的方法。针对上述问题,本文引入联邦学习(Federated Learning, FL)方法,结合LSTM负荷预测模型与短期负荷预测场景特点,构建基于联邦学习的短期负荷预测模型协同训练方法,实现各负荷聚合商在满足保证数据隐私的前提下协同训练短期负荷预测模型。在GEFCom2012比赛的多个地区负荷数据集上的仿真验证结果表明,所提方法有效提升了负荷预测模型的预测准确率,所训练出的模型在多场景下具有优秀的泛化能力。

    Abstract:

    Machine learning methods are widely used in the field of short-term load forecasting of power systems, but the existing forecasting methods don't consider the following problems: one is the insufficient number and characteristics of each load operator data in the distribution network; the other is the ability to transform of the extensive load forecasting model is poor; third, because load data have privacy protection requirements, participants can't share data to train models together.Therefore, there's an urgent need for a method to achieve collaborative construction of the load forecasting model under the premise of protecting the privacy of load data. To solve this problem, we proposed the cooperative training method of a short-term load prediction model based on federated learning(FL). This method considers the LSTM load forecasting model with the characteristics of short-term load forecasting scenarios so that all participants can meet the premise of ensuring data privacy, and train the short-term load forecasting model together. The simulation results on multiple regional load data sets of the GEFCom2012 competition show that the proposed framework effectively improves the prediction performance, and has excellent generalization ability in multiple scenarios.

    参考文献
    相似文献
    引证文献
文章指标
  • PDF下载次数:
  • HTML阅读次数:
  • 摘要点击次数:
  • 引用次数:
引用本文
历史
  • 收稿日期: 2021-12-03
  • 最后修改日期: 2021-12-31
  • 录用日期: 2022-01-20
作者稿件一经被我刊录用,如无特别声明,即视作同意授予我刊论文整体的全部复制传播的权利,包括但不限于复制权、发行权、信息网络传播权、广播权、表演权、翻译权、汇编权、改编权等著作使用权转让给我刊,我刊有权根据工作需要,允许合作的数据库、新媒体平台及其他数字平台进行数字传播和国际传播等。特此声明。
关闭