Anomaly Detection in Cloud Environments Using Bayesian Networks and Reinforcement Learning

A significant shift from traditional data centers to multi-cloud systems has transpired due to the emergence of cloud computing as a means for application service providers and corporations to reduce both initial and continuing operational costs. This move enhances scalability, latency, and load balancing, but it also introduces security vulnerabilities, particularly concerning anomaly detection. This research introduces a three-phase anomaly detection system utilizing BN-RL to address these issues. The system functions in the following manner: preprocessing, feature selection, and model training. This work introduces ECOFS, an innovative method for feature removal and the effective management of linear and nonlinear data dependencies. Furthermore, RL and BN collaborate to enhance decision-making precision, enabling the agent to select the optimal course of action from a range of options. The proposed model outperformed prior methods in a cloud environment, with an accuracy of 99.39% in anomaly detection. The BN-RL architecture is proficient in safeguarding cloud-based systems, as evidenced by these findings. The model demonstrates potential in cloud security due to its incorporation of sophisticated feature selection and uncertainty mitigation methods. The scalability and deployment across various cloud infrastructures might be enhanced in future endeavours.