International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Review of Automated Runtime Intelligence Systems for Cloud Computing |
|---|---|
| ABSTRACT | To guarantee the stable operation and sufficient performance of large computing systems, which may consist of many servers and are operated in centralized data centers or in cloud environments, all components have to be monitored automatically on a continuous basis. The large amount of monitoring data, which is generated by such large systems on a continuous basis, cannot be processed by manual monitoring. Therefore, many methods for the anomaly detection in such large amounts of data have been developed in the last years. However, Traditional machine learning techniques such as Isolation Forest, One-Class Support Vector Machine (OCSVM) and Local Outlier Factor may struggle to detect complex temporal relationships in system metrics. This paper provides an overview of recent approaches to automated anomaly detection, intelligent runtime monitoring, and error correction within cloud computing systems. These corresponding approaches try to combine deep learning with graph-based methods as well as with log-analysis. In addition to the survey, seven monitoring frameworks, namely AutoLog, CloudShield, The Dynamic Graph Transformer Parallel Framework (DGT-PF), ISOLATE, Maat, MoniLog and SEAD, are presented and compared to each other in terms of the used methods, the achieved goals as well as to the results, which were identified by the authors of the corresponding frameworks. This paper concludes the review by presenting the unsolved problems and research gaps, which were detected during the review. |
| AUTHOR | CHANDAN HEGDE, DANIA S, KOUSALYA C Assistant Professor, Department of Master of Computer Applications, Surana College (Autonomous), Bengaluru, India Student, Department of Master of Computer Applications, Surana College (Autonomous), Bengaluru, India |
| VOLUME | 187 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1408012 |
| pdf/12_A Review of Automated Runtime Intelligence Systems for Cloud Computing.pdf | |
| KEYWORDS | |
| References | [1] Huo, Y., et al. "AutoLog: A Log Sequence Synthesis Framework for Anomaly Detection." [2] He, Z. and Lee, K. "CloudShield: Real-time Anomaly Detection in the Cloud." [3] He, Z., et al. "Efficiently Localizing System Anomalies for Cloud Infrastructures: A Novel Dynamic Graph Transformer based Parallel Framework." [4] Gu, J., et al. "Identifying Performance Issues in Cloud Service Systems Based on Relational-Temporal Features." [5] Lee, C., et al. "Maat: Performance Metric Anomaly Anticipation for Cloud Services with Conditional Diffusion." [6] Vervaet, A. "MoniLog: An Automated Log-Based Anomaly Detection System for Cloud Computing Infrastructures." [7] Wang, T., et al. "Online Self-Evolving Anomaly Detection in Cloud Computing Environments." |
