Monitoring and early warning model based on multi-dimensional structure of power grid data

With the continuous improvement of information technology, the monitoring of various conditions on power system is under continuous construction. The multiple monitoring system caused by network disaster is unable to achieve complete data exchange, so it is easy to lead to early warning of persistent conditions and chain conditions. In this paper, a DQN-based power monitoring node identification method for complex networks is proposed, and a key node identification algorithm for complex networks based on the Internet of Things is proposed. The reward function is improved and designed to integrate the influence of edge weights and node attributes. By acting on the power multi-dimensional structure monitoring and early warning of conditions, the key monitoring data are preferentially provided to other monitoring networks for analysis and prompt. Experiments show that in undirected ARPA networks, compared with degree centrality, betweenness centrality, Page Rank algorithm and two comprehensive methods, the recognition results are verified by using the evaluation method based on network robustness. The evaluation based on network robustness is improved by 12.5% compared with other algorithms; the node evaluation based on dynamics is more reasonable from the global attribute, which verifies the application effect of this algorithm in power multi-dimensional condition monitoring network.