Multi-Source Data Processing and Fusion Method for Power Distribution Internet of Things Based on Edge Intelligence

With the rapid advancement of Energy Internet strategy, number sensors within Power Distribution Things (PD-IoT) has increased dramatically. In this paper, an edge intelligence-based PD-IoT multi-source data processing and fusion method is proposed to solve problems confusing storage insufficient computing performance heterogeneous distribution data. First, a architecture based on smart terminals designed. Second, realize uniform conversion various sensor sources in network terms magnitude order magnitude. By introducing Box-Cox transform improve offset problem Zscore normalization process, for networks proposed. Then, conflicting phenomena DS inference methods source are optimally handled PCA algorithm. A model with conflict optimization constructed ensure effective from different domains. Finally, effectiveness verified by experimental analysis IEEE39 node system regional China.