Jeffrey J. Evans

Predicting Ground Effects of Omnidirectional Antennas in Wireless Sensor Networks

Omnidirectional antennas are often used for radio frequency (RF) communication in wireless sensor networks (WSNs). Outside noise, electromagnetic interference (EMI), overloaded network traffic, large obstacles (vegetation and buildings), terrain and atmospheric composition, along with climate patterns can degrade signal quality in the form of data packet loss or reduced RF communication range. This paper explores the RF range reduction properties of a particular WSN designed to operate in agricultural crop fields to collect aggregate data composed of subsurface soil moisture and soil temperature. Our study, using simulation, anechoic and field measurements shows that the effect of antenna placement close to the ground (within 10 cm) signi?cantly changes the omnidirectional transmission pattern. We then develop and propose a prediction method that is more precise than current practices of using the Friis and Fresnel equations. Our prediction method takes into account environmental properties for RF communication range based on the height of nodes and gateways.

Wireless sensor networks in electrical manufacturing

Sensors along with processing and communication electronics are becoming small enough to be tightly integrated into a wide variety of systems from biological and environmental to manufacturing. Along with this miniaturization, wireless sensor networks have recently become an area of great interest to researchers and industry. They offer the promise of monitoring, data collection, and control of systems with unprecedented scale and spatial granularity. It is widely believed that wireless sensor network system design, installation, and maintenance are simplified due to the absence of physical wires. As with any emerging technology, pitfalls are as significant as the benefits. Today the performance of these networks is highly application dependent, with many different, yet tightly coupled challenges. This paper provides an overview and description of what wireless sensor networks are and are not. Challenges with their design and deployment in electrical manufacturing environments are also presented. The current wireless sensor network state of the art and obstacles to overcome are reviewed. Finally, a speculative view of future trends is offered

Network performance variability in NOW clusters

Performance management of clusters and grids poses many challenges. Sharing large distributed sets of resources can provide efficiencies, but it also introduces complexity in terms of providing and maintaining adequate performance. Current application requirements focus on the amount of resources needed without explicitly characterizing the performance required from those resources. In clusters and grids, inconsistent or highly variable application run-time is an indication of systemic inconsistency, with ramifications for those running the application and those managing the resources. We are focusing on the contribution of the interconnection network to application run-time variability. This work presents experimental results characterizing parallel application run-time sensitivity to communication performance variability using an application communication emulator (ACE).

Environment feature extraction and classification for Context aware Physical Activity monitoring

Context aware Physical Activity (PA) monitoring of humans is important for the study of diseases associated with obesity and lack of physical activity. This paper introduces a wearable context aware PA monitoring device which determines if the user is indoors or outside in situations of disrupted Global Positioning System (GPS) reception. In addition to a GPS sensor, multiple light and temperature sensors were added to our PA monitoring device. Differences in inside and outside temperature and the intensity of light are used to distinguish the context of location. Location, Light and temperature values were recorded using a controlled route during a period of 20 days in January and February. One of the non-parametric pattern recognition techniques (K-nearest neighbors) was used to classify indoor and outdoor conditions based on the combination of sensor values. Results show that the K-nearest neighbors algorithm could distinguish indoor and outdoor conditions during daytime and nighttime with the error of 0.003.

PARSE: a tool for parallel application run time sensitivity evaluation

Run time variability of parallel application codes continues to be a significant challenge in clusters. We are studying run time variability at the communication level from the perspective of the application, focusing on the network. To gain insight into this problem our earlier work developed a tool to emulate parallel applications and in particular their communication. This framework, called parallel application communication emulation (PACE) has produced interesting insights regarding network performance in NOW clusters. A parallel application run time sensitivity evaluation (PARSE) function has been added to the PACE framework to study the run time effects of controlled network performance degradation. This paper introduces PARSE and presents experimental results from tests conducted on several widely used parallel benchmarks and application code fragments. The results suggest that parallel applications can be classified in terms of their sensitivity to network performance variation

A network performance sensitivity metric for parallel applications

Excessive run time variability of parallel application codes on commodity clusters is a significant challenge. To gain insight into this problem, our earlier work developed tools to emulate parallel applications (PACE) by simulating computation and using the clusters interconnection network for communication, and further study parallel application run time sensitivity effects to controlled network performance degradation (PARSE). This work expands our previous efforts by presenting a metric derived from PARSE test results conducted on several widely used parallel benchmarks and application code fragments. The metric suggests that a parallel applications sensitivity to network performance variation can be quantified relative to its behaviour in optimal network performance conditions. Ideas on how this metric can be useful to parallel application development, cluster system performance management and system administration are also presented.

A Computer Engineering Technology Body of Knowledge

Educational programs in engineering and engineering technology have been developed to address many technical aspects associated with computers. Computer Engineering programs typically focus on the theoretical foundations related to machine and algorithm designs used to develop computers, producing highly skilled design and research engineers. Computer Engineering Technology (CpET) programs span a wide range of focus, from hardware and software development principles and practices to the latest advances in “applications”. Other programs tend to focus on Information Technology concepts and practices for the enterprise. This paper compares and contrasts CpET to other forms of computer, information, and network technology academic disciplines. We identify educational gaps that can be filled by 4-year CpET programs using the 2004 IEEE and ACM Joint Task Force on Computing Curricula “Body of Knowledge” for computer engineering, industry input, and institutional factors. This work also captures situations where combining CET and IT-centric disciplines can be useful to academic institutions, students and employers.

Toward understanding soft faults in high performance cluster networks

Fault management in high performance cluster networks has been focused on the notion of hard faults (i.e., link or node failures). Network degradations that negatively impact performance but do not result in failures often go unnoticed. In this paper, we classify such degradations as soft faults. In addition, we identify consistent performance as an important requirement in cluster networks. Using this service requirement, we describe a comprehensive strategy for cluster fault management.

Parallel application-level behavioral attributes for performance and energy management of high-performance computing systems

Run time variability of parallel applications continues to present significant challenges to their performance and energy efficiency in high-performance computing (HPC) systems. When run times are extended and unpredictable, application developers perceive this as a degradation of system (or subsystem) performance. Extended run times directly contribute to proportionally higher energy consumption, potentially negating efforts by applications, or the HPC system, to optimize energy consumption using low-level control techniques, such as dynamic voltage and frequency scaling (DVFS). Therefore, successful systemic management of application run time performance can result in less wasted energy, or even energy savings.We have been studying run time variability in terms of communication time, from the perspective of the application, focusing on the interconnection network. More recently, our focus has shifted to developing a more complete understanding of the effects of HPC subsystem interactions on parallel applications. In this context, the set of executing applications on the HPC system is treated as a subsystem, along with more traditional subsystems like the communication subsystem, storage subsystem, etc.To gain insight into the run time variability problem, our earlier work developed a framework to emulate parallel applications (PACE) that stresses the communication subsystem. Evaluation of run time sensitivity to network performance of real applications is performed with a tool called PARSE, which uses PACE. In this paper, we propose a model defining application-level behavioral attributes, that collectively describes how applications behave in terms of their run time performance, as functions of their process distribution on the system (spacial locality), and subsystem interactions (communication subsystem degradation). These subsystem interactions are produced when multiple applications execute concurrently on the same HPC system. We also revisit our evaluation framework and tools to demonstrate the flexibility of our application characterization techniques, and the ease with which attributes can be quantified. The validity of the model is demonstrated using our tools with several parallel benchmarks and application fragments. Results suggest that it is possible to articulate application-level behavioral attributes as a tuple of numeric values that describe course-grained performance behavior.

On Performance and Energy Management in High Performance Computing Systems

Large-scale High Performance Computing (HPC) systems continue to be designed and constructed to extend performance beyond Petascales using monolithic, cluster, and distributed architectures and emerging multi-core Central Processing Unit (CPU) technologies. As these machines grow so too does the size and variety of applications that run on them. Yet power management and interconnection performance are of great and mounting concern, and to date, the understanding of HPC subsystem interactions and their relationships to power efficiency remains less than desirable. Furthermore, Executive Order 13423 was issued in January of 2007 in an effort to ensure that Federal agencies operate in an environmentally, economically, and fiscally sound manner. It mandates a 30% reduction in energy intensity (MBTUs per square foot) of government facilities in the FY06-15 timeframe using FY03 as a baseline. Two major drawbacks hinder their ability to sustain consistent run time and energy efficient performance: (1) major subsystems interact with each other, often at the expense of unpredictable application run time and energy consumption, and (2) increased power density of these machines complicates the space, power, and cooling problem, resulting in partial or full system down time, further exacerbating run time unpredictability. We believe that one fundamental reason for the above limitations is the operational isolation of loosely coupled subsystems. While the development of subsystems in isolation has been the dominant model for decades, it is inherently unsuitable for ensuring consistent and sustainable systemic performance. We propose that the collection of HPC sub-systems, including the set of running applications must be collaborative in nature, and as such the HPC systems full potential is limited by subsystem isolation and autonomous actions to improve their individual subsystem performance. This paper describes an approach for using “Application-Level Behavioral Attribute Driven Techniques” to characterize HPC subsystem interactions into meaningful metrics and correlates that can be used as inputs to algorithms to control large-scale behaviors (job schedulers, routers, and HVAC systems) as well as smaller-scale behaviors such as CPU frequency and voltage scaling to achieve improved run time and energy efficiency to help satisfy Executive Order 13423.