Treffer: “Forecasting Cloud Application Workloads with Cloud Insight for Predictive Resource Management”.

In cloud computing, effective resource management is essential to maintain performance, reduce operational costs, and meet servicelevel agreements (SLAs). Traditional autoscaling techniques are mostly reactive, adjusting resources only after a workload surge is detected. This delay often causes over-provisioning, which wastes resources, or under-provisioning, which leads to performance degradation. This project introduces Cloud Insight, an intelligent and proactive workload forecasting framework that enables predictive cloud resource management. Unlike single-model approaches, Cloud Insight uses an ensemble of machine learning algorithms—including Linear Regression, ARIMA, Support Vector Machines (SVM), and Neural Networks—to accurately forecast upcoming application workloads. A key innovation in Cloud Insight is the Model Builder, which assigns dynamic weights to each predictor based on real-time performance using SVM-based regression. These weighted predictions are combined to form a robust ensemble model that adapts to varying workload patterns such as bursty, periodic, or irregular loads. The system continuously learns and improves through feedback loops that compare predicted and actual workloads. By anticipating demand, Cloud Insight enables proactive resource provisioning, leading to improved efficiency, cost-effectiveness, and SLA compliance. The framework has been implemented using Java, Oracle, and Apache Tomcat, and tested with real-time data. Results show that Cloud Insight significantly enhances prediction accuracy and system responsiveness compared to traditional methods. This solution demonstrates the power of machine learning in automating cloud infrastructure and provides a scalable, intelligent approach to modern cloud workload management. [ABSTRACT FROM AUTHOR]

Copyright of International Scientific Journal of Engineering & Management is the property of International Scientific Journal of Engineering & Management and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)