Search

Abstract: Within agent-based Ambient Intelligence applications agents react to humans based on information obtained by sensoring and their knowledge about human functioning. Appropriate types of reactions depend on the extent to which an agent understands the human and is able to interpret the available information (which is often incomplete, and hence multi-interpretable) in order to create a more complete internal image of the environment, including humans. Such an understanding requires that the agent has knowledge to a certain depth about the human’s physiological and mental processes in the form of an explicitly represented model of the causal and dynamic relations describing these processes. In addition, given such a model representation, the agent needs reasoning methods to derive conclusions from the model and interpret the (partial) information available by sensoring. This paper presents the development of a toolbox that can be used by a modeller to design Ambient Intelligence applications. This toolbox contains a number of model-based reasoning methods and approaches to control such reasoning methods. Formal specifications in an executable temporal format are offered, which allows for simulation of reasoning processes and automated verification of the resulting reasoning traces in a dedicated software environment. A number of such simulation experiments and their formal analysis are described. The main contribution of this paper is that the reasoning methods in the toolbox have the possibility to reason using both quantitative and qualitative aspects in combination with a temporal dimension, and the possibility to perform focused reasoning based upon certain heuristic information. [Copyright &y& Elsevier]

Detailed modeling of processors is required for validating processor behavior and evaluating parameters such as performance and power consumption. Fast cycle-accurate simulators are essential in handling today's complex hardware and software designs at a reasonable time. These problems are challenging enough by themselves and have seen many previous research efforts. Addressing both simultaneously is even more challenging, with many existing approaches focusing on one over another. Abstract models in fast simulators do not provide enough information required for different phases of the design. On the other hand, detailed models are very difficult to generate and result in very slow simulators. In this paper, a modeling approach based on reduced colored Petri net (RCPN) is proposed, which has the following three advantages: 1) it is very generic and support a wide range of processor features; 2) it offers a very simple and intuitive yet formal way of modeling pipelined processors; and 3) it can generate high-performance cycle-accurate simulators. RCPN inherits all useful features of colored Petri nets while avoiding their exponential growth in complexity. In this paper, it is shown how this approach is general enough to model features such as very long instruction word out-of-order execution, dynamic scheduling, register renaming, hazard detection, and branch prediction. Furthermore, the results of generating cycle-accurate simulators from RCPN models of XScale and StrongArm processors are shown, where an order of magnitude (∼15 times on the average) speedup over the popular SimpleScalar advanced reduced instruction set computing machine simulator is achieved. [ABSTRACT FROM AUTHOR]

The BaBar experiment requires simulated events beyond the ability of a single computing site to provide. This paper describes the evolution of simulation and job management methods to meet the physics community requirements and how production became distributed to use resources beyond any one computing center. The evolution of BaBar simulation along with the development of the distribution of the computing effort is described. As the computing effort is distributed to more sites there is a need to simplify production so the effort does not multiply with number of production centers. Tools are created to be flexible in handling errors and failures that happen in the system and respond accordingly, this reduces failure rates and production effort. This paper will focus on one cycle of simulation production within BaBar as a description of a large scale computing effort which was fully performed, and provided new simulation data to the users on time. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, simulation based performance analysis of an autonomous vehicle storage and retrieval system (AVS/RS) is presented. AVS/RS represents relatively a new system for automated unit-load (UL) storage based on autonomous vehicle (AV) technology. This new system consists of AVs, lifts and storage racks. It is implemented at scores of facilities in Europe. The aim of this study is to find out near optimum values for number of AVs and lifts in the system that result in high performance under various pre-defined storage rack configuration scenarios. The storage rack of the system is defined in terms of number of aisles, bays and tiers. We consider seven rack configuration scenarios, ten and nine vehicles per zone and two arrival rates – 450 and 500pallets/h. The performance measures considered are: average cycle time of storage and retrieval transactions, average utilizations of AVs and lifts. The simulation model of the system is developed using ARENA 12.0, a commercial software. We find that having a large number of lifts (zones) and a large footprint yield better performance. [Copyright &y& Elsevier]

Commercial workloads form an important class of applications and have performance characteristics that are distinct from scientific and technical benchmarks such as the SPEC CPU. However, due to the prohibitive simulation time of commercial workloads, it is extremely difficult to use them in computer architecture research. In this paper, we study the efficacy of using statistical sampling-based simulation methodology for two classes of commercial workloads: a Java server benchmark SPECjbb2000 and an Online Transaction Processing (OLTP) benchmark DBT-2. Our results show that, although SPECjbb2000 shows distinct garbage collection phases, there are no large-scale phases in the OLTP benchmark. We take advantage of this stationary behavior in the steady phase and propose a statistical sampling-based simulation technique DynaSim with two dynamic stopping rules. In this approach, the simulation terminates once the target accuracy has been met. We apply DynaSim to simulate commercial workloads and show that, with the simulation of only a few million total instructions, the error can be within 3 percent, at a confidence level of 99 percent. DynaSim compares favorably with random sampling and representative sampling in terms of the total number of instructions simulated (time cost) and with representative sampling in terms of the number of checkpoints (storage cost). DynaSim increases the usability of a sampling-based simulation approach for commercial workloads and will encourage the use of commercial workloads in computer architecture research. [ABSTRACT FROM AUTHOR]

By integrating the vehicle tracking system, discrete-event simulation algorithm, and evolutionary optimization algorithm, we developed HKCONSIM-Realtime, a decision-support platform created specifically for handling ready-mixed concrete operations. This platform is capable of (1) tracking the positions of concrete trucks and monitoring the motion and status of concrete deliveries in real time, (2) transforming the tracking records into data that provide updated input to simulation, and (3) optimizing the operations and logistics of concrete production based on simulation of the production system using the most current data. This paper presents an overview of the design and development of (1) the hardware and software modules, (2) the data flow and processing throughout the system, and (3) the role of the system in providing interactive, effective support for the human operator to attain cost efficiency. Case studies are given to demonstrate the functionality and application of the prototype system. [ABSTRACT FROM AUTHOR]

We discuss the problem of estimating probabilities of rare events in static simulation models using the recently proposed cross-entropy method, which is a type of importance-sampling technique in which the new distributions are successively calculated by minimizing the cross-entropy with respect to the ideal (but unattainable) zero-variance distribution. In our approach, by working on a functional space we are able to provide an efficient procedure without assuming any specific family of distributions. We then describe an implementable algorithm that incorporates the ideas described in the paper. Some convergence properties of the proposed method are established, and numerical experiments are presented to illustrate the efficacy of the algorithm. [ABSTRACT FROM AUTHOR]

As networking systems have become more complex and expensive, hands-on experiments based on networking simulation have become essential for teaching the key computer networking topics to students. The simulation approach is the most cost effective and highly useful because it provides a virtual environment for an assortment of desirable features such as modeling a network based on specific criteria and analyzing its performance under different scenarios with no cost. In this paper, we present our approach to develop an OPNET simulation networking laboratory that complements classroom lectures. Our simulation labs emphasize the understanding of the dynamics of network protocols instead of configuration and management. Students learn, through these experiments, a wide range of networking aspects including the design and the limitations of protocols, simulation and performance evaluation techniques, interpretation of data and packet analysis. Furthermore, we try to ensure that labs contain some extension or development of the topic beyond the lecture/reading and provide students additional active learning opportunities to discover knowledge. We have been using OPNET simulation in an introductory computer networks course for the past three years. Feedback from the students has been very positive. Overwhelmingly, students have indicated that the OPNET labs help them better understand the intricate details of actual networking protocols, and they generally indicate that they enjoy these labs as well. In summary, students benefit from the OPNET simulation laboratory in the following three ways. First, the OPNET simulation labs reinforce the networking theory taught by regular lectures. Second, the open design of the labs encourages active learning. Third, students gain the knowledge of modeling and simulation techniques for performance evaluation of networking systems. This active learning approach gives students experience in the subtleties of the design of a complex system, as well as prepares them for the networking industry. [ABSTRACT FROM PUBLISHER]

Both simulation and analytic models of computer systems can be very useful for predicting the performance of proposed new systems or proposed changes to existing systems. Unfortunately, many potential users of models are reluctant to use them because of the complexity of many such models and the difficulty of relating the model to the real system. This tutorial paper leads the reader through the development and use of an easily understood analytic model. This is then placed in context with a class of similar analytic models. In spite of the simplicity of these models they have proved useful and quite accurate in predicting performance (utilization, throughput, and response) using only the most basic system data as input. These parameters can either be estimates or measurements from a running system. The model equations and assumptions are defined, and a detailed case study is presented as an example of their use. [ABSTRACT FROM AUTHOR]