AI-Powered Anomaly Detection for Real-Time Performance Monitoring in Cloud Systems

Owing to the ever growing popularity of cloud computing, there is increased need for performance monitoring coupled with real time monitoring for detection of anomalous behavior for assured availability and reliability. Nevertheless, the current practical implementation of performance monitoring in the cloud systems have certain limitations which prevent their efficient usage in the real time performance anomaly detection. The first important limitation is related to the limitations of approaches like anomalous behaviour detection in large scale and dynamically changing cloud environments, which make the task to detect such anomalies slow and highly unsuitable for large distributed systems [1], [2]. Besides, these methods apply predefined thresholds or continue data baselines, leading to higher false alarm ratio and frequent overlook of significant anomalies within altered cloud systems [3], [5]. A final problem is the rigidity of many current methods that can often fail to identify new or previously unidentified performance problems [4], [6]. Also, there is practice that requires more sophistication in the triggering of the mitigation measures to be automated to eliminate the overhead and delay in responding that cloud administrators face [7]. This paper examines these shortcomings in the existing methods for real-time anomaly detection in cloud systems, and presents the arguments for newer approaches for addressing the evolving challenges of cloud computing.