Understanding and predicting incident mitigation time

Wang, Weijing; Chen, Junjie; Yang, Lin; Zhang, Hongyu

doi:10.1016/j.infsof.2022.107119

Cited by 5 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, interpretable models (see [15,16]) in RCA are preferable compared to their blackbox versions to produce justified recommendations to users and mitigate potential impacts and risks induced by those recommendations. There are specific use cases (e.g., [17][18][19][20]) recently modeled by researchers in the domain of intelligent cloud applications relevant to our current study. In some related areas, such as cellular networks [21] and cloud databases [22], authors perform domain-specific modeling for similar problem solutions, which, in our use cases, are not readily achievable because of many factors, including a lack of labeled/annotated datasets, which are hard to obtain for cloud infrastructures.…”

Section: Related Researchmentioning

confidence: 99%

A Study on Automated Problem Troubleshooting in Cloud Environments with Rule Induction and Verification

Poghosyan,

Harutyunyan,

Davtyan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In a vast majority of cases, remediation of IT issues encoded into domain-specific or user-defined alerts occurring in cloud environments and customer ecosystems suffers from accurate recommendations, which could be supplied in a timely manner for recovery of performance degradations. This is hard to realize by furnishing those abnormality definitions with appropriate expert knowledge, which varies from one environment to another. At the same time, in many support cases, the reported problems under Global Support Services (GSS) or Site Reliability Engineering (SRE) treatment ultimately go down to the product teams, making them waste costly development hours on investigating self-monitoring metrics of our solutions. Therefore, the lack of a systematic approach to adopting AI Ops significantly impacts the mean-time-to-resolution (MTTR) rates of problems/alerts. This would imply building, maintaining, and continuously improving/annotating a data store of insights on which ML models are trained and generalized across the whole customer base and corporate cloud services. Our ongoing study aligns with this vision and validates an approach that learns the alert resolution patterns in such a global setting and explains them using interpretable AI methodologies. The knowledge store of causative rules is then applied to predicting potential sources of the application degradation reflected in an active alert instance. In this communication, we share our experiences with a prototype solution and up-to-date analysis demonstrating how root conditions are discovered accurately for a specific type of problem. It is validated against the historical data of resolutions performed by heavy manual development efforts. We also offer experts a Dempster–Shafer theory-based rule verification framework as a what-if analysis tool to test their hypotheses about the underlying environment.

show abstract

Section: Related Researchmentioning

confidence: 99%

A Study on Automated Problem Troubleshooting in Cloud Environments with Rule Induction and Verification

Poghosyan,

Harutyunyan,

Davtyan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

Utilizing Technology for Effective Maritime Incident Management Towards the Safe Ship Operation

Melnyk,

Onishchenko,

Onyshchenko

et al. 2024

Studies in Systems, Decision and Control

View full text Add to dashboard Cite

The ship safety evaluation and analysis on the multilayer model case study

Melnyk,

Onishchenko,

Drozhzhyn

et al. 2024

E3S Web Conf.

View full text Add to dashboard Cite

The article provides an in-depth analysis of the various methodologies used to assess the safety of seagoing vessels during their operational phase. Central to this analysis is the ‘layers of safety’ model, which identifies potential safety risks at different levels of the vessel. An extensive review of safety models widely used in the shipping industry is provided and the article emphasizes the crucial role of accurate data in their development. In addition, the article advocates the need for various methods to assess the probability of potential hazards, including fire hazards. The article highlights the need to comply with maritime safetyrules and regulations and makes recommendations aimed at improving safety methods and techniques. All these measures together contribute to the improvement of operational safety and reliability of maritime cargo transport.

show abstract

Understanding and predicting incident mitigation time

Cited by 5 publications

References 17 publications

A Study on Automated Problem Troubleshooting in Cloud Environments with Rule Induction and Verification

A Study on Automated Problem Troubleshooting in Cloud Environments with Rule Induction and Verification

Utilizing Technology for Effective Maritime Incident Management Towards the Safe Ship Operation

The ship safety evaluation and analysis on the multilayer model case study

Contact Info

Product

Resources

About