An Approach to Failure Prediction in a Cloud Based Environment

Abstract

Failure in a cloud system is defined as an even that occurs when the delivered service deviates from the correct intended behavior. As the cloud computing systems continue to grow in scale and complexity, there is an urgent need for cloud service providers (CSP) to guarantee a reliable on-demand resource to their customers in the presence of faults thereby fulfilling their service level agreement (SLA). Component failures in cloud systems are very familiar phenomena. However, large cloud service providers' data centers should be designed to provide a certain level of availability to the business system. Infrastructure-as-a-service (Iaas) cloud delivery model presents computational resources (CPU and memory), storage resources and networking capacity that ensures high availability in the presence of such failures. The data in-production-faults recorded within a 2 years period has been studied and analyzed from the National Energy Research Scientific computing center (NERSC). Using the real-time data collected from the Computer Failure Data Repository (CFDR), this paper presents the performance of two machine learning (ML) algorithms, Linear Regression (LR) Model and Support Vector Machine (SVM) with a Linear Gaussian kernel for predicting hardware failures in a real-time cloud environment to improve system availability. The performance of the two algorithms have been rigorously evaluated using K-folds cross-validation technique. Furthermore, steps and procedure for future studies has been presented. This research will aid computer hardware companies and cloud service providers (CSP) in designing a reliable fault-tolerant system by providing a better device selection, thereby improving system availability and minimizing unscheduled system downtime.

A Combined System Metrics Approach to Cloud Service Reliability Using Artificial Intelligence

“…Mohammed et al [19], Xu et al [20], Lai et al [21], Das et al [22], Chigurupati et al [23], Tehrani et al [24], and Adamu et al [25] carried out a study on server (or server-level) failure prediction. The research by Mohammed et al [19] focused on the prediction of containerised high-performance computing (HPC) system failures using failure information, such as hardware, software, network, undetermined, and human error.…”

“…Similarly, Chigurupati et al [23], Tehrani et al [24], and Adamu et al [25] used techniques such as SVM for failure prediction. While the study by Chigurupati et al [23] focused on predicting communication hardware failure 5 min ahead, the study by Tehrani et al [24] focused on failure prediction in cloud systems in a simulated environment, using system metrics such as temperature, CPU, RAM, and bandwidth utilisation.…”

“…While the study by Chigurupati et al [23] focused on predicting communication hardware failure 5 min ahead, the study by Tehrani et al [24] focused on failure prediction in cloud systems in a simulated environment, using system metrics such as temperature, CPU, RAM, and bandwidth utilisation. Adamu et al [25], like other previous studies, focused on failure prediction in a cloud environment using data from the National Energy Research Scientific Computing Center's [27] Computer Failure Data Repository. The author separated the failures of a disc, a dual in-line memory module (DIMM), the CPU, and other components.…”

Autonomic rejuvenation of cloud applications as a countermeasure to software anomalies

“…Sahoo et al 33 base their detection on time series and rule‐based classification, taking in input a set of logs collected over a year of execution. Adamu et al 34 rely on ML‐based prediction models to detect hardware failures in real‐time cloud environments. Liu et al 35 propose a composite model‐based approach to detect aging of cloud resources, in the context of anomalies.…”

Whose Fault is It? Correctly Attributing Outages in Cloud Services

“…Some papers have focussed on the analysis of the cloud architecture to get a high availability by design [9]- [11]. A different approach has been taken in [12] and [13], where machine learning technique have been employed to predict cloud outages (and react accordingly).…”