Sensor Monitoring Techniques in Edge Computing Using Spatio-Temporal Correlation Anomaly Detection Algorithms

Due to the rapid development of technologies such as cloud computing and the Internet of Things (IoT), wireless sensor networks are becoming increasingly popular in the field of environmental monitoring. Anomaly detection algorithm is often used as the main method of sensor data detection. The development and application of IoT technology has led to a significant increase in data traffic. However, current anomaly detection methods are difficult to effectively detect heterogeneous data sequences from multiple sources. In this study, the sensor monitoring model of an intelligent greenhouse is constructed by using the spatio-temporal correlation anomaly detection algorithm in edge computing. The data is chunked by a sliding window to reduce the error of one-sided estimation of single data on the detection results. The spatial correlation anomaly detection algorithm is formed on the basis of the temporal correlation detection algorithm, fusing the two algorithms with the edge computation to construct a multi-source multi-dimensional data anomaly detection model. The results of the time-related anomaly detection algorithm experiment showed that the F1-score of the algorithm was 91.26%. Compared with other methods, the false alarm rate of spatial correlation anomaly detection algorithm was reduced by 56.50% ~ 83.45%, and F1-score was increased by 1.37% ~ 22.25%. In the case of big data, the detection time of the sensor monitoring model was 0.47s, the required energy consumption was reduced by 36.75% ~ 79.20%, and the delay time was the least. The anomaly detection algorithm in this study is related to time and space, which effectively improves the detection rate and detection accuracy, thus reducing the computing load of the cloud platform, and is superior to the deep learning method in processing delay.