A dual-band priority assignment algorithm for dynamic QoS resource management

Touahria

2017

Sensors

Medical and eHealth systems are progressively realized in the context of standardized architectures that support safety and ease the integration of the heterogeneous (and often proprietary) medical devices and sensors. The Integrated Clinical Environment (ICE) architecture appeared recently with the goal of becoming a common framework for defining the structure of the medical applications as concerns the safe integration of medical devices and sensors. ICE is simply a high level architecture that defines the functional blocks that should be part of a medical system to support interoperability. As a result, the underlying communication backbone is broadly undefined as concerns the enabling software technology (including the middleware) and associated algorithms that meet the ICE requirements of the flexible integration of medical devices and services. Supporting the on line composition of services in a medical system is also not part of ICE; however, supporting this behavior would enable flexible orchestration of functions (e.g., addition and/or removal of services and medical equipment) on the fly. iLandis one of the few software technologies that supports on line service composition and reconfiguration, ensuring time-bounded transitions across different service orchestrations; it supports the design, deployment and on line reconfiguration of applications, which this paper applies to service-based eHealth domains. This paper designs the integration between ICE architecture and iLand middleware to enhance the capabilities of ICE with on line service composition and the time-bounded reconfiguration of medical systems based on distributed services. A prototype implementation of a service-based eHealth system for the remote monitoring of patients is described; it validates the enhanced capacity of ICE to support dynamic reconfiguration of the application services. Results show that the temporal cost of the on line reconfiguration of the eHealth application is bounded, achieving a low overhead resulting from the addition of ICE compliance.

Section: Iland Middleware: On Line Service Composition and Timely mentioning

confidence: 99%

On Line Service Composition in the Integrated Clinical Environment for eHealth and Medical Systems

Touahria

2017

Sensors

“…Finally, QoS assurance is considered as the capability to assure that the QoS (i.e., non‐functional properties) provided by the system will not be affected by any reconfiguration process. An interesting element that makes the platform able to provide QoS assurance is the use of contracts as proposed in , and . Such contracts represent the quality levels provided and required by installed components as well as the platform.…”

Section: Concepts and Related Workmentioning

confidence: 99%

“…Other work to provide QoS assurance during the reconfiguration is tackled by, for instance, , which proposed methods to reserve resources to enable system reconfiguration according to varying needs. This method is oriented to multimedia systems and based on a budget scheduling model and dynamic priority assignment , where resources are reserved for every component independently so that these components can perform a reconfiguration to be adapted to the QoS requirements of the system. This method focuses on providing QoS assurance for a continuously reconfiguring system in multimedia domains.…”

Section: Concepts and Related Workmentioning

confidence: 99%

Scheduling component replacement for timely execution in dynamic systems

Romero

2013

Softw Pract Exp

Timely run-time software replacement techniques are a corner stone for reconciling real-time systems development and dynamic behavior. Typical real-time systems do not consider dynamic behavior because it deeply challenges predictability and timeliness. Current efforts are starting to merge the safe and predictable execution with a controllable level of dynamicity by imposing a set of bounds and limitations to the system dynamic behavior. One of the obstacles for this is how to time-bound the different operations required to effectively implement component replacement. In this paper, the main challenges for this problem are identified, and a model to ensure that components can be replaced at run time preserving the temporal properties of the system is provided that also avoids failures in replacements. A real example and simulations of our replacement model are provided that validate the presented ideas.

“…This concept of service can be applied to heterogeneous real‐time distributed systems facilitating the application of QoS techniques , to fulfil the requirements of a user, the application of fault tolerance and load‐balancing mechanisms by the system or the dynamic updating of running applications .…”

Section: Real‐time Service‐based Architecture Basic Requirementsmentioning

confidence: 99%

“…This research has been carried out within the context of middleware for deterministic dynamically reconfigurable networked embedded systems (iLAND) project . This project targets at providing support for time‐deterministic reconfiguration in distributed applications by means of providing efficient light‐weight middleware architecture , the appropriate algorithms for time‐deterministic composition and reconfiguration, mechanisms for QoS resource management and real‐time reconfiguration , and an approach for modelling services and applications .…”

Section: Introductionmentioning

confidence: 99%

Composing and scheduling service‐oriented applications in time‐triggered distributed real‐time Java environments

Estévez-Ayres

Val

Concurrency and Computation

2012

During the last decade, the number of distributed application domains with temporal requirements has significantly augmented, arising the necessity of exploring new concepts and paradigms that allow, on the one hand, the development of dynamic and flexible distributed applications and, on the other hand, the reusability of code. Service-oriented paradigms have been successfully applied to distributed environments, increasing their flexibility and allowing the reusability of their components. Besides, distributed real-time Java technologies have shown to be a good candidate to deploy real-time distributed applications. This paper presents a model for service-oriented applications on a time-triggered distributed real-time Java environment, focusing on the definition of the temporal model of an application and its schedulability, applying and evaluating this model in real-time service-oriented composition algorithms. COMPOSING AND SCHEDULING TT-DISTRIBUTED RT-JAVA SOAS 153 used by distributed real-time applications, such as the concept of connection-pool, memory-pool and thread-pool or the usage of a distributed garbage collector, defining a dual programming model that allows the choice of between a development based on remote invocation or based on distributed events [7][8][9]. DREQUIEMI also includes a synchronous scheduling service [10] that allows the establishment of a common temporal axis for a distributed application.This work aims to give the basis to design and develop a service-oriented application in a distributed real-time Java environment. The support given by the synchronous scheduling service over DREQUIEMI for real-time coordination between entities within the system (allowing the coordination between services within an application) and between the system and external actions (allowing the system to interact with sensors and actuators or the cooperation between different autonomous applications) makes it a good candidate for supporting real-time service-based applications. This service is based on a time-triggered communications paradigm and also supports asynchronous traffic, with temporal isolation, needed for the communication of events between different entities of a real-time service-based distributed system.This RTRMI middleware will be used as underlying platform in a real-time service-based system. In a real-time service-based architecture, the underlying paradigm (RMI or any other) should be transparent from the point of view of the application programmer, so she only needs to be aware of the abstract notion of a service and of the desired behaviour and quality of service (QoS) of an application. The system is, then, in charge of building loosely coupled communications (one of the main characteristics of a service-based approach) on top of the given underlying platform. This is achieved by the definition of suitable architectures [11][12][13][14] and translation rules between application and communication concepts (as the presented in Section 4.2.1).When composing real-time service-oriented ...