This paper studies the collective communication in the grid computing environment, which is characterized by the combination of distributed heterogeneous networks as well as uneven, long communication delay. Efficient collective communication requires communication schedule, which in turn requires network information. When the network information is not accurate or network faults occur, the per...

As a family of dynamic description logics, DDL(X) is constructed by embracing actions into the description logic X, where X represents well-studied description logics ranging from the ALC to the SHOIQ. To efficiently support automated interoperability between ontology-based information systems in distributed environments, we have to design an expressive mapping language to semantically understa...

Heterogeneous Distributed Storage Systems (DSS) are close to real world applications for data storage. Internet caching system and peer-to-peer storage clouds are the examples of such DSS. In this work, we calculate the capacity formula for such systems where each node store different number of packets and each having a different repair bandwidth (node can be repaired by contacting a specific s...

Center for Information Technology Integration University of Michigan 519 West William Street Ann Arbor, MI 48103-4943 CITI Technical Report 93–11 Managing Heterogeneous Distributed Computing Systems: Using Information Repositories

This paper presents CoFrame, a novel modular co-design framework for heterogeneous distributed systems. The center of the approach is a pool of dynamic data structures which is analyzed, modified and refined by algorithms and tools to map a system specification to a feasible implementation consisting of arbitrary linked processors, DSPs and FPGAs. Due to its modular structure, CoFrame can be ea...

The Abstract Schema Language (ASL) defines a hierarchical computational model for the development of distributed heterogeneous systems. ASL extends the capabilities and methodologies of concurrent object-oriented programming to enable the construction of highly complex multi-granular systems. The ASL model is described in terms of schemas (concurrent agents), supporting aggregation (schema asse...

This paper presents a PCIM-based framework for storing and enforcing RBAC (Role Based Access Control) policies in distributed heterogeneous systems. PCIM (Policy Core Information Model) is an information model proposed by IETF. PCIM permits to represent network policies in a standard form, allowing software from different vendors to read the same set of policy rules. This paper describes a PCIM...

A new approach to the design of distributed and multiprocessor operating systems is presented. This approach, called ARCADE, addresses the problems inherent in an interconnection of heterogeneous computers. It also allows efficient operation of uniprocessors and shared-memory multiprocessors. ARCADE specifies the conceptual structure and functional behavior of a platform which supports cooperat...

− Performance of distributed systems can be improved by load sharing (i.e., distributing load from heavily loaded nodes to lightly loaded ones). Dynamic load sharing policies take system state into account in making job distribution decisions. The state information can be maintained in one of two basic ways: distributed or centralized. Two examples of distributed policies are the sender-initiat...

Modern distributed systems tend to be conglomerates of heterogeneous subsystems, which have been designed separately, by di erent people, with little, if any, knowledge of each other | and which may be governed by di erent security policies. A single software agent operating within such a system may nd itself interacting with, or even belonging to, several subsystems, and thus be subject to sev...