An Architecture of a Quality of Service Resource Manager Middleware for Flexible Embedded Multimedia Systems

2009 International Conference on Embedded Software and Systems

Alonso

Puente

2009

Self Cite

Media processing in High-Quality MultimediaEmbedded Systems (HQMES) has real-time constraints. Timely processing and rendering of video frames and audio samples is essential to meet user expectations. The nature of incoming media suffers unforeseen variations which have different resource requirements. Therefore, HQMES have to integrate policies for efficiently and smoothly adapting to these changes. Mode change protocols allow applications to switch their state (for instance, to transition from one quality level to another) by controlling the way in which the application tasks change from one state to another. This paper provides a solution for timely mode change protocols based on a contract model between applications and the execution platform. A new mode change algorithm, progressive mode change protocol, is introduced for applications with no tolerance to data loss during their transitions. The execution platform is based on a quality of service resource manager (QoSRM) that arbitrates the greedy execution of multimedia applications, and that is implemented on top of the services of a real-time operating system. A task model and a temporal characterization of multimedia application tasks is also presented as the basic platform for the QoSRM operation. Validation experiments show stable execution of applications with the proposed task characterization and progressive mode change protocol.

Section: Architectural Principles For Qosrm Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mode Change Protocols for Predictable Contract-Based Resource Management in Embedded Multimedia Systems

2009 International Conference on Embedded Software and Systems

Alonso

Puente

2009

Self Cite

“…QoS data as time bounds [4][8] [10], etc.). This process returns a new service graph (that implements the new state) to be enforced in the system.…”

Section: A Reconfiguration Processmentioning

confidence: 99%

Real-time reconfiguration in complex embedded systems: A vision and its reality

2011 9th IEEE International Conference on Industrial Informatics

Gomez-Molinero

2011

Future networked embedded systems (NES) will be complex systems deeply integrated in the environment that they monitor. They will have to react to both user and environmental events, and this may require modifying their structure to handle the changing situations. For a number of domains, such adaptation will need to take place in real-time, introducing a hard problem that will require novel and paradigmatic solutions involving cross-domain knowledge. The ARTEMIS iLAND 1 project focuses on time-deterministic reconfiguration in complex NES. The project contributions gather around the construction of a light-weight real-time middleware architecture and of the development the required processes and algorithms to support system reconfiguration in bounded-time with bounded-error. This paper presents the context of this challenging problem by describing the contributions and vision of the project and discussing a number of limitations found in current approaches. The paper also discusses the set of realistic bounds and assumptions in order to provide valid contributions to reconfiguration in its target application domains. A use case scenario that has already been implemented as a demonstrator is described in order to illustrate the validity of the presented approach.

“…This paper presents an architecture for an intelligent distributed video surveillance system that is completely dynamic and reactive to environmental conditions. The architecture is based on real-time middleware solutions as [7,14] that allow the application to integrate decoupled components. Using a middleware solution brings a flexibility not known by traditional video and image processing applications which directly execute over network protocols and have very limited flexibility.…”

Section: Introductionmentioning

confidence: 99%

Adaptive real-time video transmission over DDS

2010 8th IEEE International Conference on Industrial Informatics

Val

Estévez-Ayres

2010

An increasing number of industrial applications include video processing capacities, which allow, among others, remote monitoring of industrial processes and control of private and public areas. Image processing has real-time requirements which result in resource demands at both node and network levels. Moreover, video is usually compressed and coded to be transmitted which generates variable bit-rate streams. This introduces variable processing requirements inside the node in terms of memory and processor cycles required for the processing of the sequence of different video frames. A direct impact on the network resource is also obvious since variable network bandwidth will be required to transmit the frames that may affect the bandwidth assigned to other streams. Efficient distributed video surveillance requires that real-time constraints be respected or, at least, quality of service guarantees (QoS) be provided. The traditional approach to video transmission has focused at the level of the network protocols. However, architectural solutions at the middleware level introduce higher flexibility and more efficiency in development time. This paper presents an architecture that precisely defines an integral set up of the different components that are relevant in achieving realtime and QoS-based video surveillance. The paper describes how the DDS standard for real-time distributed systems, can be used for this purpose; based on the decoupled interaction paradigm of DDS, higher complexity surveillance deployments are possible. A prototype surveillance system is presented which includes video transmission and adaptation to environmental sensing events.