Analysis of anomaly detection method for Internet of things based on deep learning
Wei Ma
Abstract
Abstract With the rapid development of the Internet of things technology, the connection between things and people is realized in a real sense, and the intelligent perception, recognition, and management of goods and processes are also achieved. Cloud computing, as one of the core technologies of the Internet of Things, has been widely used in online services of various networks, but the generation of abnormal data will affect the service performance of cloud computing systems. Therefore, effective detection of abnormal data is of great significance to improve the efficiency of the system. Because of the large amount of data and nonlinear distribution in the cloud computing system, the accuracy of traditional methods is low. Based on this, this article proposes a deep learning algorithm based on recurrent neural network (RNN) to implement anomaly detection in the cloud computing system. Based on the basic principle of the RNN algorithm, this article analyses the properties and defects of the activation functions commonly used in RNN, and then improves the RNN algorithm, so as to realize the effective detection of abnormal data in cloud computing system. The simulation results show that the optimized RNN deep learning algorithm for anomaly detection in cloud computing system can effectively improve the detection success rate, effectively reduce the detection time and cost, show strong robustness, and effectively improve the online service efficiency of the Internet of things technology.