Enhancing the Stadam SLA Trust Model with Machine Learning for Improved Anomaly Detection

In the realm of cloud computing, particularly for small and medium-sized IT businesses dependent on cloud services, anomaly detection plays a vital role in trust management. Traditional trust models have their limitations when it comes to evaluating trust while services are in operation. They often rely on a single cloud provider, overlooking the risks of service disruptions caused by Service Level Agreement (SLA) breaches. To tackle this issue, a new and improved Stadam model is proposed in this paper. This model utilizes anomaly detection technology to oversee cloud services' adherence to SLAs. By adopting a multi-cloud approach, the Stadam model enables consumers to utilize services from various providers while constantly monitoring them for anomalies using sophisticated algorithms. This dynamic method allows for the identification of anomalies during service delivery and facilitates smooth transitions between different providers, reducing the chances of service interruptions. The efficacy of the Stadam model has been proven by its capability to detect anomalies across different datasets, highlighting its potential for real-time anomaly detection in diverse applications. By prioritizing anomaly detection, the Stadam model offers a reliable solution for ensuring trustworthiness and dependability in cloud computing services.