A survey of online failure prediction methods

Salfner, Felix; Lenk, Maren; Malek, Miroslaw

doi:10.1145/1670679.1670680

Cited by 470 publications

(267 citation statements)

References 54 publications

Supporting

Mentioning

245

Contrasting

Unclassified

Order By: Relevance

“…Contingency table metrics [17] are used to investigate how accurately a decision approach works. An adaptation decision approach can terminate with two possible states: warning or silence (refer to Figure 3).…”

Section: B Evaluation Metricsmentioning

confidence: 99%

A Two-Phase Online Prediction Approach for Accurate and Timely Adaptation Decision

Wang

Pazat

2012

2012 IEEE Ninth International Conference on Services Computing

View full text Add to dashboard Cite

Abstract-A Service-Based Application (SBA) is built by defining a workflow that composes and coordinates different Web services available via the Internet. In the context of on-demand SBA execution, suitable services are selected and integrated at runtime to meet different non-functional requirements (such as price and execution time). In such dynamic and distributed environment, an important issue is to guarantee the end-toend Quality of Service (QoS). As a consequence, SBA provider is required to monitor each running SBA instance, analyze its runtime execution states, then identify proper adaptation plans if necessary, and finally apply the relative countermeasures. One of the main challenges is to accurately trigger the adaptation process as early as possible.In this paper, we present a two-phase decision approach that can accurately analyze the adaptation needs for on-demand SBA execution model. Our approach is based on the online prediction techniques: an adaptation decision is determined by predicting an upcoming end-to-end QoS degradation through two-phase evaluations. Firstly, the end-to-end QoS is estimated at runtime based on monitoring techniques; if a QoS degradation is tent to happen, in the second phase, both static and adaptive strategies are introduced to assess whether it is the best timing to draw the final adaptation decision. Our approach is evaluated and validated by a series of realistic simulations.

show abstract

Section: B Evaluation Metricsmentioning

confidence: 99%

A Two-Phase Online Prediction Approach for Accurate and Timely Adaptation Decision

Wang

Pazat

2012

2012 IEEE Ninth International Conference on Services Computing

View full text Add to dashboard Cite

show abstract

“…A similar problem of learning in component based systems, however, has been widely studied in systems recognizing the causes for system errors (see surveys in [5] and [6]). We have already discussed an important work [4], in Sections III and IV, which we also use for evaluating our approach.…”

Section: Related Work In Service Composition Learningmentioning

confidence: 99%

Utilizing PCFGs for Modeling and Learning Service Compositions in Sensor Networks

Geyik

Bulut

Szymanski

2012

2012 IEEE Ninth International Conference on Services Computing

View full text Add to dashboard Cite

Abstract-Service composition in sensor networks combines elementary services with a specific functionality to create a service with higher level functionality. The previous efforts in automating composition were sending full information about all services across the entire sensor network, creating a security risk and imposing significant communication overhead. Furthermore, learning based composition or error detection methods do not consider global information, leading to inefficiencies in the generated composition graphs. In this paper, we propose a probabilistic context-free grammar (PCFG) based modeling technique to construct service compositions. The successful compositions created for the given application are treated as statements belonging to an efficient composition PCFG of this application. The given set of such compositions is used to derive this PCFG automatically. Future composition could be then easily constructed with the help of such PCFG. We present our methodology for achieving such modeling and provide examples of its use to demonstrate its advantage over previous work. We also evaluate the resulting improvements in performance of compositions and in the costs of their creation.Index Terms-sensor networks; service composition; PCFGs;I. INTRODUCTION Service oriented architecture (SOA) for wireless sensor networks (WSN) have recently been proposed as a means to abstract the sensor network as a set of services (programs integrated within sensor nodes) that provide a certain functionality. In this context, the task of service composition is to efficiently combine a set of services so that a more complex functionality can be realized. In our initial work for SOA for WSN [1], we showed how to represent a composition as a graph of connection of services and how to automatically combine services in an efficient way. While such an automated scheme improves energy efficiency of the solution, during composition creation this scheme suffers from communication overhead and a security problem because metadata about services are sent between all potential services. Since the metada may include mission critical information, in domains such as military applications, the user may not want such information to be moved around freely. Manual connection of services by the user is a possible solution to this problem that has been followed in the literature. However, such a method becomes error-prone with the increasing composition size.

show abstract

“…The development of automated systems for pattern recognition is associated with the need of big data processing [1][2][3][4][5][6]. Typically, the original samples of data describing the objects or processes under investigation may contain redundant and uninformative information [7][8][9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Parallel Multiagent Method of Big Data Reduction for Pattern Recognition

Oliinyk

Skrupsky

Shkarupylo

et al. 2017

Radio Electronics, Computer Science, Control

View full text Add to dashboard Cite

Context. The problem of feature selection for big data processing based on the multi-agent approach and parallel computation has been solved. The object of research is the process of feature selection. The subject of the research are the methods of feature selection.Objective. The purpose of the work is to create a parallel multi-agent method for reducing of big data sets. Method. The article deals with the parallel multi-agent method for reducing of big data sets. The developed method involves splitting multiple agents into several subsets for parallel search of an informative combination of features in different areas of the search space. At the same time, it is suggested that the parallel nodes of the computer system perform the most resource-intensive operations associated with estimating the current set of agents, as well as the need to create and modify new sets of solutions based on stochastic computations. This allows to speed up the process of multi-agent search of informative combination of features, as well as to reduce the practical threshold for application of the multi-agent method with indirect communication between agents for reducing big data sets.Results. The software which implements the proposed method and allows to select informative features based on the multi-agent approach and parallel computation has been developed.Conclusions. The conducted experiments have confirmed the proposed software operability and allow recommending it for use in practice for solving the problems of big data processing for pattern recognition. The prospects for further research may include the modification of the developed parallel method for feature selection by using different criteria for estimation of the group information of features, as well as an experimental study of proposed method on more complex practical problems of different nature and dimensionality.

show abstract

A survey of online failure prediction methods

Cited by 470 publications

References 54 publications

A Two-Phase Online Prediction Approach for Accurate and Timely Adaptation Decision

A Two-Phase Online Prediction Approach for Accurate and Timely Adaptation Decision

Utilizing PCFGs for Modeling and Learning Service Compositions in Sensor Networks

Parallel Multiagent Method of Big Data Reduction for Pattern Recognition

Contact Info

Product

Resources

About