A Service-Oriented Framework for GNU Octave-Based Performance Prediction

Abstract

Cloud/Grid environments are characterized by a diverse set of technologies used for communication, execution and management. Service Providers, in this context, need to be equipped with an automated process in order to optimize service provisioning through advanced performance prediction methods. Furthermore, existing software solutions such as GNU Octave offer a wide range of possibilities for implementing these methods. However, their automated use as services in the distributed computing paradigm includes a number of challenges from a design and implementation point of view. In this paper, a loosely coupled service-oriented implementation is presented, for taking advantage of software like Octave in the process of creating and using prediction models during the service lifecycle of a SOI. In this framework, every method is applied as an Octave script in a plug-in fashion. The design and implementation of the approach is validated through a case study application which involves the transcoding of raw video to MPEG4.

5G & SLAs: Automated proposition and management of agreements towards QoS enforcement

“…In this approach, the main goal of the ANN is to set up technical targets of design attributes of web service systems, in terms of quality goals. Moreover, in [3], the LoM2HiS framework is presented. In this case, the authors provide a framework that implements the reverse process of the one that we suggest, where the translation of low level metrics to high-level terms that are used in Cloud Service Level Agreements is achieved.…”

“…To this direction, performance prediction and modeling are considered to be of major importance, since the service providers need to determine the resources to fulfill the QoS requirements of the service, while at the same time, resource utilization must be maximized [3].…”

Translation of application-level terms to resource-level attributes across the Cloud stack layers

“…In our case, this is described in detail in [14]. In this work, we implemented a layered, decoupled approach in which any proposed method can be inserted as a GNU Octave or Matlab script.…”

Virtualised e-Learning on the IRMOS real-time Cloud

“…Other works exist that address QoS assurance in Grid environments focusing on performance prediction [16] and control via service selection [17]. While numerous promising solutions exist to the problem of performance analysis of VMs in presence of real-time scheduling, these either are not focused on critical parameters that are necessary for running real time applications on SOIs, or they lack for a proper low-level realtime scheduling infrastructure which is needed for supporting temporal isolation among concurrently running VMs.…”