An Adaptive Fusion Method of Multi-Source Heterogeneous Data for Inter-Area Pumped Storage Plant Operation

Due to the variety of data sources, there may be problems of uneven data quality, such as different data accuracy, inconsistent data format, missing or incorrect data, etc., which will affect the effectiveness and accuracy of data fusion. Therefore, this study aims to propose an adaptive fusion method of heterogeneous data from multiple sources for the operation of cross-area pumped storage power plants, in order to achieve comprehensive and accurate integration and analysis of power plant operation data. Firstly, a data acquisition and transmission system is established for multiple regions and multiple data sources involved in pumped storage power plants to achieve real-time acquisition and transmission of various data. Then, data fusion algorithms and models are designed to adaptively fuse data from different sources by taking into account the heterogeneity and spatial and temporal characteristics of the data, in order to obtain more comprehensive and accurate information about the operating status of the power plant. Then, the adaptive fusion of heterogeneous data from multiple sources is realised by combining data mining and machine learning techniques. The experimental results show that the security management of data can be strengthened by fusion technology to prevent data leakage and misuse and to guarantee the security of data. In addition, by fusing data from different sources, the supply and demand situation of the power system can be analysed more accurately, so as to achieve better resource allocation and improve the efficiency of energy use.