Gabriele D'Angelo

Parallel and distributed simulation from many cores to the public cloud

In this tutorial paper, we will firstly review some basic simulation concepts and then introduce the parallel and distributed simulation techniques in view of some new challenges of today and tomorrow. More in particular, in the last years there has been a wide diffusion of many cores architectures and we can expect this trend to continue. On the other hand, the success of cloud computing is strongly promoting the “everything as a service” paradigm. Is parallel and distributed simulation ready for these new challenges? The current approaches present many limitations in terms of usability and adaptivity: there is a strong need for new evaluation metrics and for revising the currently implemented mechanisms. In the last part of the paper, we propose a new approach based on multi-agent systems for the simulation of complex systems. It is possible to implement advanced techniques such as the migration of simulated entities in order to build mechanisms that are both adaptive and very easy to use. Adaptive mechanisms are able to significantly reduce the communication cost in the parallel/distributed architectures, to implement load-balance techniques and to cope with execution environments that are both variable and dynamic.

Simulation of scale-free networks

In this paper, we present a new simulation tool for scale-free networks composed of a high number of nodes. The tool, based on discrete-event simulation, enables the definition of scale-free networks composed of heterogeneous nodes and complex application-level protocols. To satisfy the performance and scalability requirements, the simulator supports both sequential (i.e. monolithic) and parallel/distributed (i.e. PADS) approaches. Furthermore, appropriate mechanisms for the communication overhead-reduction are implemented. To demonstrate the efficiency of the tool, we experiment with gossip protocols on top of scale-free networks generated by our simulator. Results of the simulations demonstrate the feasibility of our approach. The proposed tool is able to generate and manage large scale-free networks composed of thousands of nodes interacting following real-world dissemination protocols.

Dynamic resource provisioning for cloud-based gaming infrastructures

Modern massively multiplayer online games (MMOGs) allow hundreds of thousands of players to interact with a large, dynamic virtual world. Implementing a scalable MMOG service is challenging because the system is subject to high workload variability, but nevertheless must always operate under very strict quality of service (QoS) requirements. Traditionally, MMOG services are implemented as large dedicated IT infrastructures with aggressive over-provisioning of resources in order to cope with the worst-case workload scenario. In this article we address the problem of building a large-scale, multitier MMOG service using resources provided by a Cloud computing infrastructure. The Cloud paradigm allows customers to request as many resources as they need using a pay-as-you-go model. We harness this paradigm by proposing a dynamic provisioning algorithm, which can resize the resource pool of a MMOG service to adapt to workload variability and maintain a response time below a given threshold. We use a queuing network performance model to quickly estimate the system response time for different configurations. The performance model is used within a greedy algorithm to compute the minimum number of servers to be allocated on each tier in order to satisfy the system response time constraint. Numerical experiments are used to validate the effectiveness of the proposed approach.

New trends in parallel and distributed simulation: From many-cores to Cloud Computing

Abstract Recent advances in computing architectures and networking are bringing parallel computing systems to the masses so increasing the number of potential users of these kinds of systems. In particular, two important technological evolutions are happening at the ends of the computing spectrum: at the “small” scale, processors now include an increasing number of independent execution units (cores), at the point that a mere CPU can be considered a parallel shared-memory computer; at the “large” scale, the Cloud Computing paradigm allows applications to scale by offering resources from a large pool on a pay-as-you-go model. Multi-core processors and Clouds both require applications to be suitably modified to take advantage of the features they provide. Despite laying at the extreme of the computing architecture spectrum – multi-core processors being at the small scale, and Clouds being at the large scale – they share an important common trait: both are specific forms of parallel/distributed architectures. As such, they present to the developers well known problems of synchronization, communication, workload distribution, and so on. Is parallel and distributed simulation ready for these challenges? In this paper, we analyze the state of the art of parallel and distributed simulation techniques, and assess their applicability to multi-core architectures or Clouds. It turns out that most of the current approaches exhibit limitations in terms of usability and adaptivity which may hinder their application to these new computing architectures. We propose an adaptive simulation mechanism, based on the multi-agent system paradigm, to partially address some of those limitations. While it is unlikely that a single approach will work well on both settings above, we argue that the proposed adaptive mechanism has useful features which make it attractive both in a multi-core processor and in a Cloud system. These features include the ability to reduce communication costs by migrating simulation components, and the support for adding (or removing) nodes to the execution architecture at runtime. We will also show that, with the help of an additional support layer, parallel and distributed simulations can be executed on top of unreliable resources.

MoVES: A framework for parallel and distributed simulation of wireless vehicular ad hoc networks

In this paper, we illustrate a Mobile Wireless Vehicular Environment Simulation (MoVES) framework for the parallel and distributed simulation of vehicular wireless ad hoc networks (VANETs). The proposed framework supports extensible, module-based and layered modeling, and scalable, accurate and efficient simulation of vehicular scenarios integrated with wireless communication and mobile services/applications. The vehicular layer includes models for vehicles, synthetic and trace-driven mobility, driver behavior, GPS-based street maps, intersection policies and traffic lights. The wireless communication layer currently includes models for physical propagation, and a network protocol stack including IEEE 802.11 Medium Access Control, up to the Application layer. MoVES provides a platform for microscopic modeling and simulation-based analysis of wireless vehicular scenarios and communication-based services and applications, like Intelligent Transportation Systems, communication-based monitoring/control and info-mobility services. The framework includes design solutions for scalable, accurate and efficient parallel and distributed simulation of complex, vehicular communication scenarios executed over cost-effective, commercial-off-the-shelf (COTS) simulation architectures. Dynamic model partition and adaptation-based load balancing solutions have been designed by exploiting common assumptions and model characteristics, in a user-transparent way. Test-bed performance evaluation for realistic scenarios has shown the effectiveness of MoVES in terms of simulation efficiency, scalability, adaptation and simulation accuracy.

Concurrent Replication of Parallel and Distributed Simulations

Parallel and distributed simulations enable the analysis of complex systems by concurrently exploiting the aggregate computation power and memory of clusters of execution units. In this paper we investigate a new direction for increasing both the speedup of a simulation process and the utilization of computation and communication resources. Many simulation-based investigations require to collect independent observations for a correct and significant statistical analysis of results. The execution of many independent parallel or distributed simulation runs may suffer the speedup reduction due to rollbacks under the optimistic approach, and due to idle CPU times originated by synchronization and communication bottlenecks under the conservative approach. We present a parallel and distributed simulation framework supporting concurrent replication of parallel and distributed simulations (CR-PADS), as an alternative to the execution of a linear sequence of multiple parallel or distributed simulation runs. Results obtained from tests executed under variable scenarios show that speedup and resource utilization gains could be obtained by adopting the proposed replication approach in addition to the pure parallel and distributed simulation.

A New Adaptive Middleware for Parallel and Distributed Simulation of Dynamically Interacting Systems

In this work we define and test a new framework obtained as the integration of two recently developed middlewares defined to support the parallel and distributed simulation of large scale, complex and dynamically interacting system models (like wireless and mobile network systems). In a distributed simulation of highly interacting system models, the main bottleneck may become the communication and synchronization required to maintain the causality constrains between distributed model components. We designed and implemented the ARTÌS middleware as a new framework incorporating a set of features that allow an adaptive optimization of the communication layer management in a distributed simulation scenario. ARTÌS has been integrated with GAIA, a dynamic mechanism for the runtime management and adaptive allocation of model entities in a distributed simulation. By adopting a runtime evaluation of causal bindings between model entities GAIA adapts the dynamic and time-persistent causal effects of model interactions to dynamic migration of model entities. Preliminary results demonstrate that the combined effect of ARTÌS management and GAIA heuristics leads to a significant reduction in the communication and synchronization overheads between the physical execution units. Simulation performance enhancements have been obtained also in worst-case modelling assumptions and simulation scenarios.

Distributed simulation of large-scale and detailed models

We present a new approach for the distributed simulation of large-scale and detailed models. Our approach increases the simulator speed jointly addressing two main problems of distributed simulation: the reduction of the communication overhead and the load-balancing in the execution cluster. The proposed method dynamically reconfigures the simulation, considering the performance of each part of the execution architecture. In this way, commercial-off-the-shelf hardware can be used for fast and cost-effective simulations. The performance evaluation, based on the 802.11 DCF protocol, demonstrates that this approach is feasible for the detailed simulation of very large-scale models such as wireless networks.

An adaptive load balancing middleware for distributed simulation

The simulation is useful to support the design and performance evaluation of complex systems, possibly composed by a massive number of interacting entities. For this reason, the simulation of such systems may need aggregate computation and memory resources obtained by clusters of parallel and distributed execution units. Shared computer clusters composed of available Commercial-Off-the-Shelf hardware are preferable to dedicated systems, mainly for cost reasons. The performance of distributed simulations is influenced by the heterogeneity of execution units and by their respective CPU load in background. Adaptive load balancing mechanisms could improve the resources utilization and the simulation process execution, by dynamically tuning the simulation load with an eye to the synchronization and communication overheads reduction. In this work it will be presented the GAIA+ framework: a new load balancing mechanism for distributed simulation. The framework has been evaluated by performing testbed simulations of a wireless ad hoc network model. Results confirm the effectiveness of the proposed solutions.

Multiplayer Online Games over scale-free networks: a viable solution?

In this paper we discuss the viability of deploying Multiplayer Online Games (MOGs) over scale-free networks. We employ a general peer-to-peer overlay network; nodes have a number of neighbors which follows a power law distribution, pk ~ k-α, the usual degree distribution that characterizes scale-free nets. Game events generated by nodes during the game evolution are disseminated through the network, based on some (push) gossip protocols run over the created overlay. We experiment with different gossip protocols. Results demonstrate that the employed gossip protocol may greatly influence the ability of disseminating the game data through the scale-free network. In particular, when gossip is performed using a small dissemination probability, a non-negligible percentage of the network is not able to receive the message. This implies that not all players might be able to perceive the game event. Hence, parameters of gossip protocols must be properly tuned to guarantee a full network coverage. Concurrently, it is shown that, due to their low diameter, the use of scale-free networks allows to disseminate game events in very few steps. This could ensure a high level of responsiveness on the dissemination of game events, which is the main objective to pursue when dealing with MOGs.