A flexible context stabilization approach for self-adaptive application

Nzekwa, Russel; Rouvoy, Romain; Seinturier, Lionel

doi:10.1109/percomw.2010.5470595

Cited by 8 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nzekwa et Al. [18] propose the composition of different mechanisms to obtain a flexible model for implementing stabilization in Context-aware systems. In [19,20] Padovitz et Al.…”

Section: Related Workmentioning

confidence: 99%

Formal assessment of some properties of Context-Aware Systems

Schreiber,

Valcher

2020

Preprint

View full text Add to dashboard Cite

Context-Aware systems are becoming useful components in autonomic and monitoring applications and the assessment of their properties is an important step towards reliable implementation, especially in safety-critical applications. In this paper, using an avalanche/landslide alert system as a running example, we propose a technique, based on Boolean Control Networks, to verify that the system dynamics has stable equilibrium states, corresponding to constant inputs, and hence it does not exhibit oscillatory behaviors, and to establish other useful properties in order to implement a precise and timely alarm system.

show abstract

“…Nzekwa et Al. [18] propose the composition of different mechanisms to obtain a flexible model for implementing stabilization in Context-aware systems. In [19,20] Padovitz et Al.…”

Section: Related Workmentioning

confidence: 99%

Formal assessment of some properties of Context-Aware Systems

Schreiber,

Valcher

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…To prevent this, we use a Kalman filter to smooth the input-i.e., the memory utilization. It helps to stabilize the value and eliminate the noise induced by the memory fluctuation [18]. Concretely, we apply Algorithm 3 Balancing LoJP and LoJT.…”

Section: Handling Drops Of Memory Utilizationmentioning

confidence: 99%

Self-Balancing Job Parallelism and Throughput in Hadoop

Zhang

Křikava

Rouvoy

et al. 2016

Distributed Applications and Interoperable Systems

Self Cite

View full text Add to dashboard Cite

In Hadoop cluster, the performance and the resource consumption of MapReduce jobs do not only depend on the characteristics of these applications and workloads, but also on the appropriate setting of Hadoop configuration parameters. However, when the job workloads are not known a priori or they evolve over time, a static configuration may quickly lead to a waste of computing resources and consequently to a performance degradation. In this paper, we therefore propose an on-line approach that dynamically reconfigures Hadoop at runtime. Concretely, we focus on balancing the job parallelism and throughput by adjusting Hadoop capacity scheduler memory configuration. Our evaluation shows that the approach outperforms vanilla Hadoop deployments by up to 40% and the best statically profiled configurations by up to 13%.

show abstract

“…Reconfigurations of data involve a set of conflicting requirements that should be carefully taken into account by the framework module implementing the variation of data. Among these requirements we have stability of data [18,27], i.e., a measure defined as the ratio between variations of data (output) and variation of context (input), user benefit, i.e., a metric expressing the satisfaction of the user, and reconfiguration cost which is a metric defined over the operations that have to be completed for reconfiguring data. Let us consider the e-heath case study where the doctor changes his task from check-up activity to an emergency activity.…”

Section: Data-variability Aware Performance Optimizationmentioning

confidence: 99%

Towards Highly Adaptive Data-Intensive Systems: A Research Agenda

Mori

Cleve

2013

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Data-intensive software systems work in different contexts for different users with the aim of supporting heterogeneous tasks in heterogeneous environments. Most of the operations carried out by dataintensive systems are interactions with data. Managing these complex systems means focusing the attention to the huge amount of data that have to be managed despite limited capacity devices where data are accessed. This rises the need of introducing adaptivity in accessing data as the key element for data-intensive systems to become reality. Currently, these systems are not supported during their lifecycle by a complete process starting from design to implementation and execution while taking into account the variability of accessing data. In this paper, we introduce the notion of data-intensive self-adaptive (DISA) systems as dataintensive systems able to perform context-dependent data accesses. We define a classification framework for adaptation and we identify the key challenges for managing the complete lifecycle of DISA systems. For each problem we envisage a possible solution and we present the technological support for an integrated implementation.

show abstract

A flexible context stabilization approach for self-adaptive application

Cited by 8 publications

References 11 publications

Formal assessment of some properties of Context-Aware Systems

Formal assessment of some properties of Context-Aware Systems

Self-Balancing Job Parallelism and Throughput in Hadoop

Towards Highly Adaptive Data-Intensive Systems: A Research Agenda

Contact Info

Product

Resources

About