Zengxiang Li

Adaptive Resource Provisioning Mechanism in VEEs for Improving Performance of HLA-Based Simulations

Parallel and distributed simulations (or High-Level Architecture (HLA)-based simulations) employing optimistic synchronization allow federates to advance simulation time freely at the risk of overoptimistic executions and execution rollbacks. As a result, the simulation performance may degrade significantly due to the simulation workload imbalance among federates. In this article, we investigate the execution of parallel and distributed simulations on Cloud and data centers with Virtual Execution Environments (VEEs). In order to speed up simulation execution, an Adaptive Resource Provisioning Mechanism in Virtual Execution Environments (ArmVee) is proposed. It is composed of a performance monitor and a resource manager. The former measures federate performance transparently to the simulation application. The latter distributes available resources among federates based on the measured federate performance. Federates with different simulation workloads are thus able to advance their simulation times with comparable speeds, thus are able to avoid wasting time and resources on overoptimistic executions and execution rollbacks. ArmVee is evaluated using a real-world simulation model with various simulation workload inputs and different parameter settings. The experimental results show that ArmVee is able to speed up the simulation execution significantly. In addition, it also greatly reduces memory usage and is scalable.

Accelerating optimistic HLA-based simulations in virtual execution environments

High Level Architecture (HLA)-based simulations employing optimistic synchronization allows federates to process event and to advance simulation time freely at the risk of over-optimistic execution and execution rollbacks. In this paper, an adaptive resource provisioning system is proposed to accelerate optimistic HLA-based simulations in Virtual Execution Environment (VEE). A performance monitor is introduced using a middleware approach to measure the performance of individual federates transparently to the simulation application. Based on the performance measurements, a resource manager distributes the available computational resources to the federates, making them advance simulation time with comparable speeds. Our proposed approach is evaluated using a real-world simulation model with various workload inputs and different parameter settings. The experimental results show that, compared with distributing resources evenly among federates, our proposed approach can accelerate the simulation execution significantly using the same amount of computational resources.

Hierarchical resource management for enhancing performance of large-scale simulations on data centers

More and more interests have been shown to move large-scale simulations on modern data centers composed of a large number of virtualized multi-core computers. However, the simulation components (Federates) consolidated in the same computer may have imbalanced simulation workloads. Similarly, the computers involved in the same simulation execution (Federation) may also have imbalanced simulation workloads. Hence, federates may waste a lot of computer resources on time synchronization with each other. In this paper, a hierarchical resource management system is proposed to enhance simulation execution performance. Federates in the federation are enraptured in their individual Virtual Machines (VMs), which are consolidated on a group of virtualized multi-core computers. On the computer level, multiple VMs share the resource of the computer according to the simulation workloads of their corresponding federates. On the federation level, some VMs are migrated for workload balance purpose. Therefore, computer resources are fully utilized to conduct useful simulation workloads, avoiding the synchronization overheads. Experiments using synthetic and real simulation workloads have verified that the hierarchical resource management system enhances simulation performance significantly.

Compensatory dead-reckoning-based update scheduling for distributed virtual environments

In a distributed virtual environment (DVE), participants located in different places may observe inconsistent views of the simulated virtual world due to message delay and loss in the network. This paper investigates how to compensate for the impact of message delay and loss on consistency in the DVE. We focus on dead reckoning (DR)-based update mechanisms and measure inconsistency by the time–space inconsistency (TSI) metric. We theoretically analyze the TSI of an entity and derive the condition under which the impact of message delay and loss on consistency can be fully compensated for by reducing the DR threshold. Based on the analysis, a compensatory update scheduling algorithm is proposed. Experiments using real traces of a racing car game are conducted to evaluate the compensatory algorithm. The results confirm that if the condition derived in our theoretical analysis is fulfilled, the compensatory algorithm can decrease the TSI of a racing car to the level of the case without message delay and loss when there is sufficient network bandwidth available. Under severe bandwidth constraints, the compensatory algorithm still leads to comparable TSIs of the racing car among the participants regardless of their network conditions so as to enable fair competition.

Hierarchical Parallelization and Runtime Scheduling for Pregel-Like Graph Processing Systems

Graph processing has become popular for various big data analytic applications. Googles Pregel framework enables vertex-centric graph processing in distributed environment based on Bulk Synchronous Parallel (BSP) model. However, the BSP model is inefficient for many complex graph algorithms requiring graph traversals, as only a small number of vertices really update states in each super step. In this paper, we propose an hierarchical parallelization mechanism, taking the advantages of both synchronous (warp-level) and asynchronous (task-level) parallelization approaches. In addition, a runtime task scheduling mechanism is proposed, relying on real-time monitoring or prediction of resource utilization. Experiments have verified that the hierarchical parallelization mechanism can expose greater parallelism, and thus, increase resource utilization significantly. Moreover, the runtime scheduling mechanism can avoid aggressive resource competition, and thus, further enhance the performance of the parallelized graph processing.

RA2: Predicting Simulation Execution Time for Cloud-Based Design Space Explorations

Design space exploration refers to the evaluation of implementation alternatives for many engineering and design problems. A popular exploration approach is to run a large number of simulations of the actual system with varying sets of configuration parameters to search for the optimal ones. Due to the potentially huge resource requirements, cloud-based simulation execution strategies should be considered in many cases. In this paper, we look at the issue of running large-scale simulation-based design space exploration problems on commercial Infrastructure-as-a-Service clouds, namely Amazon EC2, Microsoft Azure and Google Compute Engine. To efficiently manage cloud resources used for execution, the key problem would be to accurately predict the running time for each simulation instance in advance. This is not trivial due to the currently wide range of cloud resource types which offer varying levels of performance. In addition, the widespread use of virtualization techniques in most cloud providers often introduces unpredictable performance interference. In this paper, we propose a resource and application-aware (RA2) prediction approach to combat performance variability on clouds. In particular, we employ neural network based techniques coupled with non-intrusive monitoring of resource availability to obtain more accurate predictions. We conducted extensive experiments on commercial cloud platforms using an evacuation planning design problem over a month-long period. The results demonstrate that it is possible to predict simulation execution times in most cases with high accuracy. The experiments also provide some interesting insights on how we should run similar simulation problems on various commercially available clouds.

Transparent three-phase Byzantine fault tolerance for parallel and distributed simulations

Abstract A parallel and distributed simulation (federation) is composed of a number of simulation components (federates). Since the federates may be developed by different participants and executed on different platforms, they are subject to Byzantine failures. Moreover, the failure may propagate in the federation, resulting in epidemic effect. In this article, a three-phase (i.e., detection, location, and recovery) Byzantine Fault Tolerance (BFT) mechanism is proposed based on a transparent middleware approach. The replication, checkpointing and message logging techniques are integrated in the mechanism for the purpose of enhancing simulation performance and reducing fault tolerance cost. In addition, mechanisms are provided to remove the epidemic effects of Byzantine failures. Our experiments have verified the correctness of the three-phase BFT mechanism and illustrated its high efficiency and good scalability. For some simulation executions, the BFT mechanism may even achieve performance enhancement and Byzantine fault tolerance simultaneously.

Two-Level Storage QoS to Manage Performance for Multiple Tenants with Multiple Workloads

With more applications moving to cloud, scalable storage systems, composed of a cluster of storage servers and gateways, are deployed as the back-end infrastructure to accommodate high-volume data. In such an environment, it is a challenge to provide predictable and controllable storage performance for multitenanted users with multiple applications, due to performance violation from misbehaving applications. In this paper, we propose a two-level QoS controller over scalable storage system. On the higher level, I/O throughput rented by each tenant is guaranteed and strictly limited by a CAP value. On the lower level, this rented service can be on-demand served among multiple applications under the same tenant. Thus our distributed controller not only shields performance violation from noisy tenants but also allows tenants to fully utilizing the rented I/O throughput. Furthermore, the QoS controller is implemented in an efficient manner, by reusing the communication channels among gateways and storage servers and piggybacking control signals on data communications. The experimental results have shown that the two-level QoS controller can guarantee I/O throughput at tenant level by controlling the CAP value while accelerating applications by on-demand serving at a very little computation cost.

Un-identical federate replication structure for improving performance of HLA-based simulations

Abstract The execution of an HLA-based simulation (federation) is usually time consuming, as it usually involves a number of compute-intensive simulation components (federates). To improve simulation performance, an un-identical federate replication structure is proposed in this article. For the same federate, multiple replicas are developed in software diversity manner by employing different synchronization approaches. The simulation performance is improved by always choosing the fastest replica to represent the federate in the federation. The replication structure is implemented in a transparent manner without increasing federation scale. Message exchange and time management mechanisms are developed to handle the different behaviors of those un-identical replicas. Correctness of the replication structure is proved in theory and verified by experiments. The experimental results have also shown that the un-identical federate replication structure achieves significant performance enhancement with good scalability and marginal overhead.

Equality of public transit connectivity: the influence of mass rapid transit services on individual buildings for Singapore

ABSTRACT Accessibility and its equality are key factors for land-use and transport planning in city developments. In this paper, we propose a graph-based Public Transit Connectivity (PTC) index to measure the accessibility of individual buildings focusing on transportation factors. A large-scale graph is created to connect all buildings in the city through multi-modal public transit services. The PTC index of each building is calculated based on the door-to-door travel distance/time from the building to all others using a parallel graph closeness centrality algorithm. In addition, the PTC index is verified from an economic perspective, as it is highly correlative to house resale price and thus enable accurate price prediction using machine learning models. Consequently, the PTC index and its equality are used to evaluate the influence of existing and future Mass Rapid Transit (MRT) services in Singapore as a case study. As experimental results show, MRT services significantly enhance PTC indices of individual buildings. However, they could not improve PTC equality in city scale due to their conflicting effects, i.e. (1) shrinking the difference between central and peripheral regions and (2) enlarging the difference among buildings with different distances to the nearest MRT stations.