Six questions are posed that are likely to be of interest to one considering applying the dual heuristic programming (DHP) methodology. Tentative answers to these questions are provided in the last section of the pape...
详细信息
Six questions are posed that are likely to be of interest to one considering applying the dual heuristic programming (DHP) methodology. Tentative answers to these questions are provided in the last section of the paper. As a basis for these, the paper first describes observations made from a series of explorations into various aspects of using the DHP method to design the controller for the pole-cart benchmark problem. Parameters of the explorations included training gains, plant parameter variations, fidelity of plant model, controller sampling rates, networkarchitectures, training strategies, and generalization tests.
Adopting the Telecommunication Information networking Architecture (TINA) Service Architecture as the foundation services and network model, this work addresses the federation concept and mechanisms, to enable the han...
详细信息
ISBN:
(纸本)0780350839
Adopting the Telecommunication Information networking Architecture (TINA) Service Architecture as the foundation services and network model, this work addresses the federation concept and mechanisms, to enable the handling of same or compatible services, shared sessions and resources, in multiple domains. Apart from analyzing the accurate and efficient formalization of the intended services system functionality, involving multiple stakeholders domains, insight is given on the organizational counterpart aspects. The observations are validated through a case study concerning service provision supporting customer personal mobility across different retailers domain.
Shared memory programming systems present a helpful abstraction to the parallel programmer. However, modern commodity and near commodity architectures, such as networks-of-Workstations (IBM SP/2) and Piles-of-PCs (Beo...
详细信息
Shared memory programming systems present a helpful abstraction to the parallel programmer. However, modern commodity and near commodity architectures, such as networks-of-Workstations (IBM SP/2) and Piles-of-PCs (Beowulf) lack hardware support for memory operations that span multiple memory busses. Such architectures require software support for shared memory operations. Two important design choices by which software shared memory can be characterized are namespace model and access method. In order to provide the semantics and ease-of-use of shared memory multiprocessors, distributed memory systems must provide a global namespace and a transparent (implicit) access method. This paper describes Hrunting, a freeware distributed shared memory (DSM) system for Beowulf-class multicomputers that satisfies both requirements. In order to reduce network communications, the DSM system uses the release consistency model. It has been shown that release consistency is equivalent to serial consistency with sufficient synchronization. In order to take advantage of the existing memory management hardware and software, the DSM system deals with the shared memory on the granularity of virtual memory pages. The DSM system employs a multiple writer protocol to allow several processes to write to different parts of the same virtual memory page, and an invalidate protocol to allow processes to keep copies of shared pages until the pages are modified. The performance of the DSM system was tested with a Barnes-Hut N-body galaxy simulation and with a parallel sort.
A direct method for creating a neural network to approximate an optimal feedback controller is presented in this paper. The method is direct in the sense that the weight adaptation is tied directly to the solution of ...
详细信息
A direct method for creating a neural network to approximate an optimal feedback controller is presented in this paper. The method is direct in the sense that the weight adaptation is tied directly to the solution of the optimal control problem. To achieve this goal, the optimal control problem is first converted into a parameter optimization problem with the weights and biases of the network being the adaptable parameters. Any state and/or control limitations are turned into the appropriate equality or inequality constraints. Then a nonlinear programming algorithm is used to solve the resulting constrained minimization problem. The method is demonstrated by solving three example optimal control problems of varying complexity. Recommendations for future improvements are given.
Research axis covered by TINA, which is considered as a long term telecom architecture solution, are the intelligent networks (IN), then telecommunication management network (TMN), the open distributed processing (ODP...
详细信息
Research axis covered by TINA, which is considered as a long term telecom architecture solution, are the intelligent networks (IN), then telecommunication management network (TMN), the open distributed processing (ODP), the object oriented methodologies (OOA, OOD) and multimedia service aspects. The evolution of the IN towards TINA (migration and interworking) is currently subject of world-wide research. The long-term passage of the IN to TINA will depend on the success of migration studies and on the TINA demonstrations performance. In this framework, this paper does not propose an approach for migration nor interworking, but instead, it presents an integrated one that benefits from the advantages of the two IN-TINA architectures (capabilities, intelligence, real time, deployment...). This new architecture will satisfy the needs of new services creation and new techniques evolution.
Typical avionics systems today are structured in a federated architecture. Upgrading such systems has proven unwieldy and expensive, even as the advance of technology and increased functional requirements have made up...
详细信息
Typical avionics systems today are structured in a federated architecture. Upgrading such systems has proven unwieldy and expensive, even as the advance of technology and increased functional requirements have made upgrades more imperative. Of particular concern is the systemic integration required for information superiority through multi-source data fusion. To improve this situation, the Maritime Avionics Subsystems and Technology Scalable open Architecture Project (MAST SOAP) has designed a distributed avionics architecture. It is characterized by general-purpose hardware resources linked by an extensible communications network, an Object Request Broker infrastructure, and commercially available components with open interface standards. This paper outlines our approach to legacy system upgrades in the context of an open distributed architecture, presents the lessons we have learned that are applicable to such a system evolution, and discusses the performance implications involved in the use of such an architecture for an avionics system.
The object-oriented programming language Java is an ideal companion to an object-oriented database system. This paper describes our approach to provide a seamless application programmer interface. It is based on a mod...
详细信息
The object-oriented programming language Java is an ideal companion to an object-oriented database system. This paper describes our approach to provide a seamless application programmer interface. It is based on a modular architecture with components for database engines, a communications protocol and a JAVA API facilitator. The open architecture is flexible, scalable and distributed in nature.
Metacomputing is an emergent paradigm that makes possible to distribute applications over a heterogeneous set of computing systems to exploit all available resources. The paper presents the HPO environment for object-...
详细信息
ISBN:
(纸本)0818681306
Metacomputing is an emergent paradigm that makes possible to distribute applications over a heterogeneous set of computing systems to exploit all available resources. The paper presents the HPO environment for object-oriented metacomputing. The HPO programming model is based on the object-oriented paradigm and defines architecture-independent and portable applications. The HPO support makes it possible to distribute applications over a network of heterogeneous architectures. The paper describes this approach via several examples and evaluates its achieved performances.
Asynchronous Transfer Mode (ATM) network are scalable via a wide variety of physical lint speeds and can be run in both local and wide area. Bandwidth reservation and quality of service guarantees make ATM attractive ...
详细信息
ISBN:
(纸本)0818677805
Asynchronous Transfer Mode (ATM) network are scalable via a wide variety of physical lint speeds and can be run in both local and wide area. Bandwidth reservation and quality of service guarantees make ATM attractive to deliver multimedia information in real-lime. Existing protocol suites can be extended. However, they do not give access to those characteristics. Therefore, applications demand an ATM Application programming Interface (API) to tale advantage of those features. This paper covers a special syntax mapping of the ATM API services on top of X/open Transport Interface (XTI) which is able to give applications access directly to the special quality and traffic services of an ATM network. A particular realization of the API on XTI environment is proposed and implemented on the MacOS networking platform. It provides a flexible and modular design of the ATM networking. Finally, the paper concludes with one ATM-aware application (video on demand) which requires real-time streaming data.
This paper extends fuzzy criterion dynamic programming to the multidimensional case for an open inventory network which is an instructive framework for treating problems typified by stochastic multi-location inventory...
详细信息
This paper extends fuzzy criterion dynamic programming to the multidimensional case for an open inventory network which is an instructive framework for treating problems typified by stochastic multi-location inventory systems and multi-reservoir operations. The objective is to maximize the expected fuzzy criterion function of the product of fuzzy criterion sets. We prove the existence, uniqueness and stability theorems of solutions to this model. Further, we develop a decomposition algorithm for solving large scale problems associated with the model and give an illustrative example.
暂无评论