No description available.

The MSU ERC UltraScope system consists of a distributed computing system, custom PCI cards, GPS receivers, and a re-radiation system. The UltraScope system allows precision timestamping of events in a distributed application on a system where the CPU and PCI clocks are phase-locked. The goal of this research is to expand the UltraScope system, using software routines and minimal hardware modifications, to allow precision timestamping of events on an asynchronous distributed system. The timestamp process is similar to the Network Time Protocol (NTP) in that it uses a series of timestamps to improve precision. As expected, the precision is less accurate on an asynchronous system than on a synchronous system. Results show that the precision is improved using this sequence of timestamps, and the major error component is due to operating system delays. The errors associated with this timestamping process are characterized using a synchronous system as a baseline.

Scientific applications are large, complex, irregular, and computationally intensive and are characterized by data parallel loops. The prevalence of independent iterations in these loops, makes parallel computing as the natural choice for solving these applications. The computational requirements of these problems vary due to variations in problem, algorithmic and systemic characteristics during parallelization, leading to performance degradation. Considerable amount of research has been dedicated to the development of dynamic scheduling techniques based on probabilistic analysis to address these predictable and unpredictable factors that lead to severe load imbalance. The mathematical foundations of these scheduling algorithms have been previously developed and published in the literature. These techniques have been successfully integrated into scientific applications as well as into runtime systems. Recently, efforts have also been directed to integrate these techniques into dynamic load balancing libraries for scientific applications. The optimal scheduling algorithm to load balance a specific scientific application in a dynamic parallel computing environment is very difficult without the exhaustive testing of all the scheduling techniques. This is a time consuming process, and therefore, there is a need for developing an automatic mechanism for the selection of dynamic scheduling algorithms. In recent years, extensive work has been dedicated to the development of reinforcement learning and some of its techniques have addressed load-balancing problems. However, they do not cover a number of aspects regarding the performance of scientific applications. First, these previously developed techniques address the load balancing problem only at a coarse granularity level (for example, job scheduling), and the reinforcement learning techniques used for load balancing are based on learning from trained datasets which are obtained prior to the execution of the application. Moreover, scientific applications contain parameters whose variations are so irregular that the use of training sets would not be able to accurately capture the entire spectrum of possible characteristics. Finally, algorithm selection using reinforcement learning has only been used for simple sequential problems. This thesis addresses these limitations and provides a novel integrated approach for automating the selection of dynamic scheduling algorithms at a finer granularity level to improve the performance of scientific applications using reinforcement learning. This integrated approach will experimentally be tested on a scientific application that involves a large number of time steps: The Quantum Trajectory Method (QTM). A qualitative and quantitative analysis of the effectiveness of this novel approach will be presented to underscore the significance of its use in improving the performance of large-scale scientific applications.

In recent years, Distributed Generators (DGs) and energy storage devices have gained more popularity due to growing energy and environmental concerns. Interconnection of DGs and storage devices in an electricity grid impacts its performance under steady state and transient conditions. This research aims at analyzing the impacts of distributed generators and energy storage devices on the transient stability of the grid. Battery and ultra-capacitor technologies have been taken as the two types of storage devices and their electrical characteristics have been modeled using Simulink. Impact of these devices has been analyzed by connecting them to the system by means of suitable power electronic converters. The developed methodology has been evaluated using small test systems in MATLAB/Simulink. Transient stability of the test systems has been assessed for different types and locations of faults as well as for different penetration levels of the DGs, with and without the energy storage devices. Impact on the system transient stability has been analyzed based on transient response of the generator rotor speed deviation, rotor angle and terminal voltage of the DGs. Finally, economic analyses have been carried out for different options of DGs, based on wind, diesel and biomass, along with the energy storage devices. Results indicate that the presence of DGs and storage devices enhances the transient stability of the system in most of the cases.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.