Wilson Rivera

AppRAISE: application-level performance management in virtualized server environments

Managing application-level performance for multitier applications in virtualized server environments is challenging because the applications are distributed across multiple virtual machines, and workloads are dynamic in their intensity and transaction mix resulting in time-varying resource demands. In this paper, we present AppRAISE, a system that manages performance of multi-tier applications by dynamically resizing the virtual machines hosting the applications. We extend a traditional queuing model to represent application performance in virtualized server environments, where virtual machine capacity is dynamically tuned. Using this performance model, AppRAISE predicts the performance of the applications due to workload changes, and proactively resizes the virtual machines hosting the applications to meet performance thresholds. By integrating feedforward prediction and feedback reactive control, AppRAISE provides a robust and efficient performance management solution. We tested AppRAISE using Xen virtual machines and the RUBiS benchmark application. Our empirical results show that AppRAISE can effectively allocate CPU resources to application components of multiple applications to meet end-to-end mean response time targets in the presence of variable workloads, while maintaining reasonable trade-offs between application performance, resource efficiency, and transient behavior.

Wireless Sensor Networks for Environmental Monitoring Applications: A Design Framework

With the advances in wireless communication technologies, wireless sensor networks (WSNs) are becoming more and more attractive because they can provide services that are not possible or not feasible before. In this paper, we address the design issues of an important type of WSN, i.e., WSNs that enable environmental monitoring applications. We first provide an overview and analysis for our ongoing research project about the WSN for coastal area acoustic monitoring. Based on the analysis, we then propose a novel framework that can be used to guide the design of future WSNs that provide environmental monitoring services. The focus of the framework is the network layer design. In our framework, we consider that 1) the future WSN shall be heterogeneous, 2) the network layer design shall better meet the requirements of applications and services, 3) the network layer design shall be able to utilize advanced wireless communication technologies, and 4) the network layer can provide the monitoring functionality.

An Efficient Parallel Algorithm with Application to Computational Fluid Dynamics

Abstract When solving time-dependent partial differential equations on parallel computers using the nonoverlapping domain decomposition method, one often needs numerical boundary conditions on the boundaries between subdomains. These numerical boundary conditions can significantly affect the stability and accuracy of the final algorithm. In this paper, a stability and accuracy analysis of the existing methods for generating numerical boundary conditions will be presented, and a new approach based on explicit predictors and implicit correctors will be used to solve convection-diffusion equations on parallel computers, with application to aerospace engineering for the solution of Euler equations in computational fluid dynamics simulations. Both theoretical analyses and numerical results demonstrate significant improvement in stability and accuracy by using the new approach.

Sensitivity Analysis of a Hyperspectral Inversion Model for Remote Sensing of Shallow Coastal Ecosystems

This paper presents a sensitivity analysis of a semi-analytical inversion model for hyperspectral remote sensing of shallow coral ecosystems. Results consistently demonstrated that the estimates of water optical parameters, bottom albedo and bathymetry are most sensitive to values assigned for two of the fixed parameters: the spectral slope of the absorption coefficient for gelbstoff; and the spectral power coefficient for calculating the backscattering coefficient. This suggests that inversion model performance can be enhanced by incorporating improved estimates for these two fixed parameters, either through more explicit physical equations or through location-specific empirical relationships.

Parallel Implementation of an Inversion Model for Hyperspectral Remote Sensing

This paper describes the implementation of a semi-analytical inversion model within a parallel processing framework. The greater processing speed obtained with this parallel implementation is demonstrated. A reduction of 97% in the execution time is achieved. This approach enables real time processing capabilities and more complex analysis to simultaneously classify water properties, bathymetry and benthic composition associated with coral reefs and other shallow coastal subsurface environments.

A Sensor Grid Framework for Acoustic Surveillance Applications

This paper describes the design and implementation of a framework that integrates deployment, execution, and notification mechanisms for running surveillance monitoring applications on multi-purpose grids. The proposed framework employs statistical analysis over historical data along with self-adaptive mechanisms to allocate efficiently task to resources. This framework has been deployed on a set of computational resources pertaining to the Pacific Rim Applications and Grid Middleware Assembly (PRAGMA) infrastructure.

Grid Based Pervasive Distributed Storage

This paper describes a tool that implements a set of services to manipulate and store data from a sensor network in a transparent way to end users. A major requirement of this system is data availability and reliability. Consequently, we have implemented a replication schema based on the information dispersal algorithm (IDA). Preliminary results show that the IDA based replication provides better reliability and less storage spending than traditional replication. The storage scheme has been deployed on top of a Globus based infrastructure

Using Grid Computing to Enable Distributed Radar Data Retrieval and Processing

We describe a tool that implements a set of services to manipulate and store data from a radar network in a transparent way to end users. A major requirement of this system is data availability and reliability. Consequently, we have implemented a redundancy schema based on the information dispersal algorithm (IDA). Preliminary results show that the IDA based replication provides better reliability and less storage spending than traditional replication

A grid based weather radar data retrieval and processing framework.

In this paper, we describe the implementation of a distributed data retrieval and processing strategy enabled by using grid computing technologies and applied to distributed collaborative adaptive sensing environments. Underlying the grid computing and storage infrastructure there is a data dispersion algorithm to guarantee pervasive data management. Experimental results show that the proposed framework integrates successfully radar networks to grid infrastructures, while providing higher resources utilization than typical storage strategies.

An efficient parallel algorithm for solving unsteady nonlinear equations

This paper discusses the application of a new parallel non-overlapping domain decomposition algorithm, based on explicit predictors and implicit correctors, to the solution of nonlinear equations. The results demonstrate significant improvement in accuracy for calculating transient solutions using the new approach. In addition, the parallel algorithm scales well as the number of processors increases for large scale problems.