Rob Minson

Large Scale Distributed Simulation on the Grid

The developmentof many complex siumulation applications requires collaborrrtive effortfrom reseachers with different domain knowledge and expertise,possibly at different locations. These simulations systems often require huge computing resources and data set, which may be geo- graphically distribyted, In ordr to support collaborative model development and to cater for the increasing comoplex- ity of such systems, it is necessary to harness distributed resources over the Internet. the emergence of Grid tech nologies provide exciting new opportunities for large scale distributed simulation, enabling collaboration and the use of distributed computing resources, while also facilitating access to geographically distributed data sets. This paper discusses the research challenges that must be addresses before these opportunities can be exploited and presents HLA-GRID_REPast, a system for executing large scale distributed simulations of agent based systems over the Grid.

Large Scale Distributed Simulation of p2p Networks

P2P systems have witnessed phenomenal development in recent years, evaluating and analysing new and existing new algorithms and techniques is a key issue for developers of p2p systems. In this context Simulation is an important tool for p2p developers. However, such systems are often very large and few existing simulators offer the ability to execute systems of real world size. In this paper we present a tool for executing large scale simulation of p2p systems which scale effectively, only limited by the amount of computational resource available (memory and CPU). This is achieved through the application of parallel discrete event simulation techniques to an existing, already scalable simulator, peersim. We show results from a case study using the chord p2p protocol, indicating good scalability both in terms of size (memory) and execution time (CPU).

Adaptive Interest Management via Push-Pull Algorithms

Interest management in large-scale distributed applications aims to reduce the amount of extraneous broadcast communication between nodes in the system with the aim of increasing responsiveness and scalability. We present a middleware-layer interest management framework based on pattern prediction to inform the oscillation of the systems protocol for the processing of state updates between two competing modes. This framework is transparent to the application itself. We discuss various algorithms for performing the prediction and experimentally evaluate the effectiveness of these algorithms against each other and a set of optimal and sub-optimal baselines

Evaluating Large Scale Distributed Simulation of P2P Networks

P2P systems have witnessed phenomenal development in recent years. Evaluating and analyzing new and existing algorithms and techniques is a key issue for developers of P2P systems. In this context, simulation is an important tool for P2P developers. However, such systems are often very large and few existing simulators offer the ability to execute simulations with an Internet scale. In this paper we utilize parallel discrete event simulation simulation techniques for executing large scale simulation of P2P systems which scale effectively, only limited by the amount of computational resource available (memory and CPU). We show results from a number of P2P protocols, indicating good scalability both in terms of size (memory) and execution time (CPU). The results demonstrate how the differences of these protocols and which of the underlying factors affect the performance of the distributed simulation infrastructure.

Synchronised Range Queries

In this paper, we present and evaluate a system for performing logical-time synchronised Range Queries over data in the context of parallel and distributed simulations of Multi-Agent Systems (MAS). MAS are often extremely complex and simulation is commonly used to understand their behaviour or investigate the implications of alternative agent architectures. Range Queries are widely used in various fields such as Peer to Peer systems, Wireless communications or Database systems. They are key to many MAS models as they are commonly used to represent the spatial perceptive abilities of the agents in the MAS. PDES-MAS (Parallel and Discrete Event Simulation for Multi-Agent Systems) is a decentralised, discrete event simulation (DES) system which can be used to distribute and run a large scale MAS simulation over a parallel computation architecture. This paper presents a design for Logical-Time synchronised Range Queries and the implementation and evaluation of this design within the PDES-MAS system.

Push-Pull Interest Management for Virtual Worlds

Several approaches for scalable interest management (IM) within real-time distributed virtual environments (DVEs) have been proposed based upon some division of the data-space in to disjoint volumes or cells. Any such approach, however, must implement some mechanism for propagating the query and update messages around the distributed system. The efficiency of this process can greatly effect the scalability of such systems. In this paper we evaluate an adaptive approach to this problem.

An Evaluation of Push-Pull Algorithms in Support of Cell-Based Interest Management

Several approaches for scalable interest management (IM) within real-time distributed virtual environments (DVEs) have been proposed based upon some division of the data-space in to disjoint volumes or cells. Responsibility for the entire space can then be distributed. Any such approach, however, must implement some mechanism for propagating the query and update messages around the distributed system. The efficiency of this process can greatly effect the scalability of such systems. In this paper we evaluate an adaptive approach to this problem, designed for use in cell-based systems in general.Several approaches for scalable interest management (IM) within real-time distributed virtual environments (DVEs) have been proposed based upon some division of the data-space in to disjoint volumes or cells. Responsibility for the entire space can then be distributed. Any such approach, however, must implement some mechanism for propagating the query and update messages around the distributed system. The efficiency of this process can greatly effect the scalability of such systems. In this paper we evaluate an adaptive approach to this problem, designed for use in cell-based systems in general.

Load Skew in Cell-Based Interest Management Systems

In large, real-time interactive distributed systems such as distributed simulations and multiplayer games, interest management (IM) is often implemented using a cell-based paradigm. In such a paradigm the subscription patterns of interactive clients are mapped on to some set of disjoint regions or cells which are typically hosted within a routing network made up either of dedicated machines or of the clients themselves. These systems often incorporate some mechanism for balancing the load placed on this routing network, on the assumption that interests over this population of cells will be non-uniform. Using a set of reference models for cell-based IM systems found in the research corpus, we evaluate the extent to which this phenomenon takes place. We also evaluate what effects an adaptive algorithm from previous work by Minson, R. and Theodoropoulos, G. (2007) has on this phenomenon.