基于深度学习的电力数据合规性审查方法

A Deep Learning Based Compliance Review Method for Power Data

为了保障电力数据的安全、完整、真实和可靠,维护国家能源安全和电力市场秩序,促进电力行业的健康发展,提出基于深度学习的电力数据合规性审查方法研究。本次研究首先基于供电企业的远程采集系统完成电力数据的采集,其次过滤处理电力数据,组成电力时序数据集,再次预处理电力时序数据集,最后基于改进卷积神经网络(Convolutional Neural Network,CNN)算法建立电力数据合规性审查模型。试验结果表明,所提方法查准率和查全率均高于95%,应用效果较好。

In order to ensure the safety,completeness,authenticity,and reliability of power data,maintain national energy security and power market order,and promote the healthy development of the power industry,this study proposes a deep learning based method for power data compliance review.This study first completed the collection of power data based on the remote collection system of power supply enterprises,filtered and processed it to form a power time series dataset.Then,the power time series dataset was preprocessed,and an improved Convolutional Neural Network(CNN)algorithm was used to establish a compliance review model for power data.Finally,the practicality of the proposed method was demonstrated through experiments.The experimental results show that the accuracy and recall of the proposed method are both higher than 95%,and the application effect is good.