摘要
当前综合能源系统的多源数据融合及参数协同测量方法存在实时性低、数据质量不高等问题。提出一种风光储能数据融合及测量方法。将监控与数据采集系统和同步向量测量单元这两种测量方法结合,对系统参数进行动态测量;再利用云边协同系统提升其测量数据传输效率,将数据输入到双向长短期记忆网络(Bi-directional Long Short-Term Memory,BiLSTM)模型中进行预测,并结合Spline插值法进行多源数据融合;最后利用相关系数法对测量数据进行进一步修正。实验结果表明,所提方法获取的测量数据的信息熵和均方根误差值分别为0.53 bits和0.05 bits,其处理延时仅为0.05 s。该方法能够提升综合能源系统的参数测量效率和精度,为能源系统调度提供实时有效的数据依据。
At present,the multi-source data fusion and parameter cooperative measurement methods of integrated energy system struggle with low real-time and low data quality.To address this issue,a new data fusion and measurement method of landscape energy storage was proposed.The monitoring and data acquisition system and synchronous vector measurement unit were combined to measure system parameters dynamically,and then the cloud-edge collaborative system was used to improve the efficiency of measurement data transmission.The measured data was input into the BiLSTM(Bi-directional Long Short-Term Memory)for prediction,and multi-source data fusion was combined with interpolation method.Finally,the correlation coefficient method was used to further modify the measurement data.Experimental results showed that the information entropy and root mean square error of the measurement data obtained by the proposed method are 0.53 bits and 0.05 bits respectively,and the processing delay is only 0.05 s.The proposed method can improve the efficiency and accuracy of parameter measurement in the integrated energy system,and provide real-time and effective data basis in the process of energy system scheduling.
作者
李智
叶海峰
王京景
戴东升
LI Zhi;YE Haifeng;WANG Jingjing;DAI Dongsheng(State Grid Anhui Electric Power Co.,Ltd.,Hefei 230022,China)
出处
《国外电子测量技术》
2025年第5期161-167,共7页
Foreign Electronic Measurement Technology
基金
国网安徽省电力有限公司科技项目(521200230002)。
