Resource optimization in distributed real-time multimedia applications

The research area of multimedia content analysis (MMCA) considers all aspects of the automated extraction of knowledge from multimedia archives and data streams. To adhere to strict time constraints, large-scale multimedia applications typically are being executed on distributed systems consisting of large collections of compute clusters. In a distributed scenario, it is first essential to determine the optimal number of compute nodes used by each cluster, properly balancing the complex tradeoff between computation and communication. This issue is referred as the ??resource utilization?? (RU) problem. Next, it is important to tune the transmission of newly generated data sent to each cluster, so as to obtain the highest service utilization, while minimizing the need for buffering. This latter issue is referred as the problem of ??just-in-time?? (JIT) communication. In this paper, we first present a simple and easy-to-implement method for the RU problem, which is based on the classical binary search method. Second, we address the JIT problem by introducing a smart adaptive control method that properly reacts to the continuously changing circumstances in distributed systems. Extensive experimental validation of the two approaches on a real distributed system shows that our optimization approaches are indeed highly effective.     

A flexible environment for rapid prototyping and analysis of distributed real-time safety-critical systems

Currently, there is a plethora of low-cost commercial off-the-shelf (COTS) hardware available for implementing control systems. These range from devices with fairly low intelligence, e.g. smart sensors and actuators, to dedicated controllers such as PowerPC, programmable logic controllers (PLCs) and PC-based boards to dedicated systems-on-a-chip (SoC) ASICS and FPGAs. When considering the construction of complex distributed systems, e.g. for a ship, aircraft, car, train, process plant, the ability to rapidly integrate a variety of devices from different manufacturers is essential. A problem, however, is that manufacturers prefer to supply proprietary tools for programming their products. As a consequence of this lack of ‘openness’, rapid prototyping and development of distributed systems is extremely difficult and costly for a systems integrator. Great opportunities thus exist to produce high-performance, dependable distributed systems. However, the key element that is missing is software tool support for systems integration. The objective of the Flexible Control Systems Development and Integration Environment for Control Systems (FLEXICON) project IST-2001-37269 is to solve these problems for industry and reduce development and implementation costs for distributed control systems by providing an integrated suite of tools to support all the development life-cycle of the system. Work within the Rolls-Royce supported University Technology Centre (UTC) is investigating rapid prototyping of controllers for aero-engines, unmanned aerial vehicles and ships. This paper describes the use of the developed co-simulation environment for a high-speed merchant vessel propulsion system application.     

Adaptive resource management for dynamic distributed real-time applications

The dynamic distributed real-time applications run on clusters with varying execution time, so re-allocation of resources is critical to meet the applications’s deadline. In this paper we present two adaptive recourse management techniques for dynamic real-time applications by employing the prediction of responses of real-time tasks that operate in time sharing environment and run-time analysis of scheduling policies. Prediction of response time for resource reallocation is accomplished by historical profiling of applications’ resource usage to estimate resource requirements on the target machine and a probabilistic approach is applied for calculating the queuing delay that a process will experience on distributed hosts. Results show that as compared to statistical and worst-case approaches, our technique uses system resource more efficiently.     

Rapid design exploration of safety-critical distributed automotive applications via virtual integration platforms

Modern automotive applications such as Drive-by-Wire are implemented over distributed architectures where electronic control units (ECU’s) communicate via broadcast buses. In this paper, we present the concept of virtual integration platform for automotive applications. The platform provides the basis for early analysis and validation of distributed applications, therefore enhancing the current model based development process techniques that are applied to one ECU at a time. The virtual prototype includes both functional and performance (time) models of the application software, scheduling policies, and the bus communication protocols. As a result, since design errors can be found earlier in the design process before the different sub-systems are integrated in the car, savings in both production and development costs can be achieved. The virtual integration platform concept is supported by an integrated IP-based tool environment for authoring, integration, and validation. First, a model of the distributed application is built by composing models of HW and SW components. The models can be either authored or imported from different tools. Functional simulation of the overall distributed control algorithm can be carried out first. Then, the mapping phase can take place: sub-functions of the control algorithm are mapped to architectural resources (CPUs), and zero-time communication links between the sub-functions are mapped to bus protocol delay models. Changing mappings, parameters such as task priorities, and bus schedule enables the exploration of alternative implementations. The validation is carried out by simulating the resulted virtual prototype of the distributed control algorithm running on the ECU network. The design environment shortens design turn-around time by supporting (semi)-automatic configuration of the architecture model (e.g. frame packaging, redundancy level, communication matrix, bus and RTOS scheduling, etc.).     

Design optimization of the quantization and a pipelined 2D-DCT for real-time applications

The Discrete Cosine Transform (DCT) is one of the most widely used techniques for image compression. Several algorithms are proposed to implement the DCT-2D. The scaled SDCT algorithm is an optimization of the DCT-1D, which consists in gathering all the multiplications at the end. In this paper, in addition to the hardware implementation on an FPGA, an extended optimization has been performed by merging the multiplications in the quantization block without having an impact on the image quality. A simplified quantization has been performed also to keep higher the performances of the all chain. Tests using MATLAB environment have shown that our proposed approach produces images with nearly the same quality of the ones obtained using the JPEG standard. FPGA-based implementations of this proposed approach is presented and compared to other state of the art techniques. The target is an an Altera Cyclone II FPGA using the Quartus synthesis tool. Results show that our approach outperforms the other ones in terms of processing-speed, used resources and power consumption. A comparison has been done between this architecture and a distributed arithmetic based architecture.     

A design of RFTOG model for distributed real-time applications

In this paper, we design the Real-Time Fault-Tolerant Object Group (RFTOG) model that supports the grouping of distributed objects that are required for distributed application. The proposed model basically provides two services. One is the group management service, which supports both consistency maintenance and transparency of the replicated objects with a variety of replication mechanisms. It also provides the load balancing of distributed applications. The other is real-time service in an object group. When the clients request the service to the service object selected through the load balance, this service guarantees the service execution within deadline for the clients’ requests. We develop the Naval Air Defense System (NADS) simulator for verifying the effectiveness of the services proposed by the RFTOG model.     

A distributed multicast routing protocol for real-time multicast applications

Multicast routing is establishing a tree which is rooted from the source node and contains all the multicast destinations. A delay bounded routing tree is a tree in which the accumulated delay from the source node to any destination along the tree does not exceed a pre-specified bound. This paper presents a distributed routing protocol which constructs delay bounded routing trees for real-time multicast connections. A constructed routing tree has a near optimal network cost under the delay bound constraint. The proposed algorithm is fully distributed, efficient in terms of the number of messages required, and flexible in multicast membership changes. A large number of simulations have been done to show the network cost of the routing trees generated by our method is better than the other major existing algorithms.     

On design and formal verification of SNSP: a novel real-time communication protocol for safety-critical applications

The correct operation of time-triggered protocols highly depends on the well-synchronized clocks of the system. To maintain the global time, one strict constraint must be exerted on communication activities (e.g. temporal padding and sparse time base etc.), which not only increases complexity of the protocol design but also incurs a penalty in the network utilization. While for event-triggered protocols, it is difficult to achieve the real-time requirement and determinism. Therefore, it is necessary to explore the combination of the advantages of these two categories of protocol for applications in different scenarios. This paper proposes the Safe Node Sequence Protocol (SNSP), which is a variant of full time-triggered protocol TTP/C. In SNSP, a strict node sequence is defined and the order of communication events is established by this pre-configured order without binding to global time, so the protocol changes communication activities and error detection to an event-triggered model. Therefore, SNSP possesses the characteristics of both time-triggered and event-triggered model. Also, the potential impact of global time, such as byzantine clock failure, on the protocol is eliminated. At the same time, the formal verification of SNSP is much easier in the absence of global time. Moreover, we model the protocol and use formal checker SPIN to validate the basic fault-tolerant requirement of SNSP. The simulation results show the protocol enables better resource utilization and is more effective.     

A codesign approach for safety-critical automotive applications

This complex, bus-based air bag ignition system for automobiles demonstrates an effective way to design embedded fault-tolerant applications     

Reduced latency DRAM for multi-core safety-critical real-time systems

Real-Time Systems - Predictable execution time upon accessing shared memories in multi-core real-time systems is a stringent requirement. A plethora of existing works focus on the analysis of...     

Modeling distributed real-time applications with specification PEARL

The methodology of hardware/software co-design of embedded control systems with Specification PEARL is presented. Hardware and software are modeled with the language Specification~PEARL, which has its origins in standard Multiprocessor~PEARL. Its usefulness is enhanced for modeling hierarchical and asymmetrical multiprocessor systems, and by additional parameters for schedulability analysis. Graphical symbols are introduced for its constructs to enable graphical modeling while maintaining the semantical background. It is meant to be a superlayer for programs, based on the PEARL programming model. To model program tasks, Timed State Transition Diagrams have been defined. The model of a co-designed system is verified for feasibility with co-simulation. The resulting information should be used when considering changes in a current design with the goal of producing a temporally feasible model. To support dynamic re-configurations, configuration management is introduced into the models. Since UML is becoming a de facto standard also for designing embedded control systems, and since Timed State Transition Diagrams and State Chart Diagrams share great similarity, an interface of the methodology to UML 2 is defined, using UML's extension mechanisms.     

Module allocation of real-time applications to distributed systems

An allocation model for mapping a real-time application to certain k-processor multiprocessor systems is developed and analyzed. Its objective is minimizing the total processing time of the application by exploiting the parallelism of the application-architecture pair. The model is formulated in terms of the performance characteristics of the system and the resource requirements of the computation involved. Experience with the model suggests that it can be used effectively for the performance evaluation of application-distributed system pairs     

Design patterns for real-time distributed control system benchmarking

In this paper, we describe the design and development of a simulation–agent interface for real-time distributed control system benchmarking. This work is motivated by the need to test the feasibility of extending agent-based systems to the physical device level in manufacturing and other industrial automation systems. Our work focuses on the development of hybrid physical/simulation environment that can be used to perform tests at both the physical device level, as well as the planning and scheduling level of control. As part of this work, we have extended the proxy design pattern for this application. This paper focuses on the resulting software design pattern for distributed control system benchmarking and provides examples of its use in our hybrid physical/simulation environment.     

A multi-protocol real-time monitoring and validation system for distributed fieldbus-based automation applications

This work describes BR-Tool (Bus Real-Time Monitoring Tool), an on-line monitoring and validation system to evaluate timing characteristics of automation systems implemented as a distributed network of fieldbus devices. BR-Tool supports several industrial communication protocol standards. It includes a programmable messages logger module and a validation toolset that allows timing requirements specification, validation, and graphical visualization of results. In order to illustrate the main system characteristics, two industrial case studies are presented: a Profibus-DP-based manufacturing system and an energy systems application (a multitap-transformers position control system) based on the CANOpen protocol.     

Experimental evaluation of software development tools for safety-critical real-time systems

Since the early years of computing, programmers, systems analysts, and software engineers have sought ways to improve development process efficiency. Software development tools are programs that help developers create other programs and automate mundane operations while bringing the level of abstraction closer to the application engineer. In practice, software development tools have been in wide use among safety-critical system developers. Typical application areas include space, aviation, automotive, nuclear, railroad, medical, and military. While their use is widespread in safety-critical systems, the tools do not always assure the safe behavior of their respective products. This study examines the assumptions, practices, and criteria for assessing software development tools for building safety-critical real-time systems. Experiments were designed for an avionics testbed and conducted on six industry-strength tools to assess their functionality, usability, efficiency, and traceability. The results some light on possible improvements in the tool evaluation process that can lead to potential tool qualification for safety-critical real-time systems.     

DICOS: a real-time distributed industrial control system for embedded applications

The Fault-tolerant Systems Research Group of the Technical University of Valencia has developed the distributed industrial control system (DICOS) system. This paper describes DICOS nodes. The architecture of DICOS nodes and the error detection mechanisms used are presented. These mechanisms are based on the internal capabilities of the 16-bit microcontroller used and control flow checking and deadlines control with the aid of a second 8-bit microcontroller. Experimental results about the effectiveness of those mechanisms are shown in this paper.     

实时性分布嵌入式系统设计

分布嵌入式系统的应用通常具有实时性要求,其实时性需要从任务调度、通信协议、调用接口和嵌入式操作系统四个方面得到支持。采用两阶段调度策略既可以保证调用的透明性,又可以简化任务调度算法;基于优先级的线路竞争算法可以改进以太网使其符合实时性要求;采用微型Java虚拟机作为分布式中间件可以为系统调用接口提供一个统一的支持平台。     

Parallel extremal optimization in processor load balancing for distributed applications

The paper concerns parallel methods for extremal optimization (EO) applied in processor load balancing in execution of distributed programs. In these methods EO algorithms detect an optimized strategy of tasks migration leading to reduction of program execution time. We use an improved EO algorithm with guided state changes (EO-GS) that provides parallel search for next solution state during solution improvement based on some knowledge of the problem. The search is based on two-step stochastic selection using two fitness functions which account for computation and communication assessment of migration targets. Based on the improved EO-GS approach we propose and evaluate several versions of the parallelization methods of EO algorithms in the context of processor load balancing. Some of them use the crossover operation known in genetic algorithms. The quality of the proposed algorithms is evaluated by experiments with simulated load balancing in execution of distributed programs represented as macro data flow graphs. Load balancing based on so parallelized improved EO provides better convergence of the algorithm, smaller number of task migrations to be done and reduced execution time of applications.