+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
DOI:
作者:
作者单位:

作者简介:

通讯作者:

基金项目:


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

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    针对机器学习方法在电力系统短期负荷预测领域的应用过程中,存在数据样本不 足、模型泛化能力差以及数据隐私保护要求较高等问题,以气象、日期以及历史负荷数据为输 入特征,构建基于长短期记忆(Long Short-Term Memory,LSTM)网络的短期负荷预测模型,提 出基于联邦学习(Federated Learning,FL)的短期负荷预测模型协同训练方法. 通过分散训练、 中心聚合的方式对模型参数进行迭代更新,实现各负荷运营商在保证数据隐私的情况下协同 构建预测模型. 在GEFCom2012比赛的多个地区负荷数据集上进行仿真验证,结果表明,所提 方法在保证各运营商数据隐私的同时,有效提升了短期负荷预测准确率,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 have been widely used in the field of short-term load forecasting of power systems. However,it is difficult for load operators to obtain high-performance forecasting models due to insufficient data samples,poor model generalization ability, and high data privacy protection requirements in the application pro? cess. In this paper, meteorological, date, and historical load are used as input features to construct a short-term load forecasting model based on Long Short-Term Memory(LSTM). A federated learning(FL) based coordinated training method of a short-term load forecasting model is proposed. The proposed method mainly iteratively updates model pa? rameters through decentralized training and aggregation of centers, so as to realize cooperative construction of the pre? diction model by all load operators under the condition of data privacy. The simulation results based on the GEF?Com2012 dataset show that the proposed method not only ensures the data privacy of operators but also effectively im? proves the forecasting accuracy of the load forecasting model, and the trained model has satisfied generalization abil? ity 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

车亮 ,徐茂盛 ,崔秋实 .基于联邦学习的短期负荷预测模型协同训练方法[J].湖南大学学报:自然科学版,2022,49(8):117~127

复制
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2022-09-07
  • 出版日期:
版权声明:稿件一经被本刊录用,即视为作者将版权授予本刊,本刊有权根据工作需要,允许合作的数据库、新媒体平台及其他媒体进行二次转载、推介、下载和传播,如有异议,请在来稿中声明。
关闭