Research on the Implementation Method of Situational Awareness Strategy by Fusing Computational Migration Models

Abstract

Abstract With the exponential growth of the scale of domain monitoring data, the existing situational awareness technology suffers from low efficiency of processing data, long transmission time, and slow warning response. To address these problems, this paper proposes a situational awareness strategy (Computational Migration Situational Awareness (CMSA)) that incorporates the computational migration model. First, the strategy introduces a computational migration model, based on Monte Carlo-Shannon mathematical ideas, using sensors to collect heterogeneous monitoring data from multiple sources in real time, and distributing the collected data to each synaptic node in the edge layer; then, the strategy extracts the eigenvalues of the data, and then obtains the eigenvalue matrix; finally, it introduces the Modified Cosine Similarity algorithm, which analyzes the collected data from the levels of perceiving, understanding, and predicting and makes decisions accordingly. data is analyzed from three levels of perception, comprehension and prediction, and decisions are made accordingly. The experimental results show that the CMSA strategy is able to reduce the data transmission and comparison time by 35.3% compared with the existing methods, and also improves the comparison accuracy by 20.22%.