A Machine Learning-Based Framework for Building Application Failure Prediction Models

Pellegrini, Alessandro; Sanzo, Pierangelo Di; Avresky, Dimiter R.

doi:10.1109/ipdpsw.2015.110

Cited by 23 publications

(20 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For technical details and experimental results regarding PCAM, we refer the reader to [2]. Further, as for details on ML-based prediction models used by PCAM, we refer to [4].…”

Section: Introductionmentioning

confidence: 99%

Proactive Scalability and Management of Resources in Hybrid Clouds via Machine Learning

Avresky¹,

Sanzo

Pellegrini³

et al. 2015

2015 IEEE 14th International Symposium on Network Computing and Applications

Self Cite

View full text Add to dashboard Cite

In this paper, we present a novel framework for supporting the management and optimization of application subject to software anomalies and deployed on large scale cloud architectures, composed of different geographically distributed cloud regions. The framework uses machine learning models for predicting failures caused by accumulation of anomalies. It introduces a novel workload balancing approach and a proactive system scale up/scale down technique. We developed a prototype of the framework and present some experiments for validating the applicability of the proposed approaches.

show abstract

“…For technical details and experimental results regarding PCAM, we refer the reader to [2]. Further, as for details on ML-based prediction models used by PCAM, we refer to [4].…”

Section: Introductionmentioning

confidence: 99%

Proactive Scalability and Management of Resources in Hybrid Clouds via Machine Learning

Avresky¹,

Sanzo

Pellegrini³

et al. 2015

2015 IEEE 14th International Symposium on Network Computing and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning has been extensively used for failure detection [8], [28], [30], [32], attack prediction [1], [3], [4], [19], [20], [48], and face recognition [35], [37], [42]. Considering noisy labels in classification algorithms is also a problem that has been explored in the machine learning community as discussed in [5], [12], [24].…”

Section: Related Workmentioning

confidence: 99%

Robust Anomaly Detection on Unreliable Data

Zhao

Cerf

Birke

et al. 2019

2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)

View full text Add to dashboard Cite

Classification algorithms have been widely adopted to detect anomalies for various systems, e.g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i.e., features and labels are correctly set. However, data collected from the wild can be unreliable due to careless annotations or malicious data transformation for incorrect anomaly detection. In this paper, we present a two-layer on-line learning framework for robust anomaly detection (RAD) in the presence of unreliable anomaly labels, where the first layer is to filter out the suspicious data, and the second layer detects the anomaly patterns from the remaining data. To adapt to the on-line nature of anomaly detection, we extend RAD with additional features of repetitively cleaning, conflicting opinions of classifiers, and oracle knowledge. We on-line learn from the incoming data streams and continuously cleanse the data, so as to adapt to the increasing learning capacity from the larger accumulated data set. Moreover, we explore the concept of oracle learning that provides additional information of true labels for difficult data points. We specifically focus on three use cases, (i) detecting 10 classes of IoT attacks, (ii) predicting 4 classes of task failures of big data jobs, (iii) recognising 20 celebrities faces. Our evaluation results show that RAD can robustly improve the accuracy of anomaly detection, to reach up to 98% for IoT device attacks (i.e., +11%), up to 84% for cloud task failures (i.e., +20%) under 40% noise, and up to 74% for face recognition (i.e., +28%) under 30% noisy labels. The proposed RAD is general and can be applied to different anomaly detection algorithms.

show abstract

“…Recent years, some research concentrated on building the prediction frameworks which make remarkable advances in all aspects. Pellegrini et al proposed a machine learning based framework to provide the remaining time to failure [Pellegrini et al, 2015]. However, several procedures require manual intervention and parameters need to be set in advance, complicating automation.…”

Section: Related Workmentioning

confidence: 99%

An anomaly prediction framework for financial IT systems using hybrid machine learning methods

Wang

Liu

et al. 2019

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Informatization grows rapidly in all walks of life, going with the enhancement of dependence on IT systems. It is of vital importance to ensure the safe and stable running of the system especially in the field of finance. This paper puts forward a machine learningbased framework for predicting the occurrence of the alarm cases of a financial IT system. We extracted the features from the system logs then build three sub modules which are time-series prediction module, alarm classification module and level division module that composing the whole work flow. We take multiple methods to deal with the problems facing the obstacles in each module. We built the time-series prediction model in terms of time and accuracy performance. To gain higher performance, we introduced ensemble learning methods in designing alarm classifier and alleviated the class-imbalance problem in alarm level division process. The evaluation results from all sides show that our framework could be exploited for real time applications with the veracity and reliability ensured.

show abstract

A Machine Learning-Based Framework for Building Application Failure Prediction Models

Cited by 23 publications

References 8 publications

Proactive Scalability and Management of Resources in Hybrid Clouds via Machine Learning

Proactive Scalability and Management of Resources in Hybrid Clouds via Machine Learning

Robust Anomaly Detection on Unreliable Data

An anomaly prediction framework for financial IT systems using hybrid machine learning methods

Contact Info

Product

Resources

About