Along with the progress of Internet and information technology, distributed systems have been widely utilized by various businesses. In a distributed system, task scheduling and resource allocation plays a key role in determining the overall efficiency. In this research, we designed evaluation software for carrying out performance evaluation of a distributed real-time job scheduling and resource management method. In addition, we designed evaluation software of other distributed job scheduling methods based on traditional scheduling methods. We also planned evaluation metrics for performance comparison to verify effectiveness of our scheduling method

This article points out the importance of discussions about distance-learning quality, formats, and appropriate usage. It addresses some elementary issues, trying to bring up questions and to answer them. Particularly, this article talks how modern technologies play important roles in the design of distance education.

This is a grant proposal by the OSPI, a community of individuals and organizations dedicated to the creation of open source software for (learning) electonic portfolios. Formed in January 2003, the Open Source Portfolio Initiative (OSPI) is a collaborative, open-source, software development project based on the University of Minnesota Enterprise System's electronic portfolio software. The University of Minnesota (U of MN), University of Delaware, and the r-smart group, founded this collaborative to open the evolution of the U of MN ePortfolio to diverse input, rapid development, and widespread use. Mission Create and sustain leading production ePortfolio software. Build a software platform to accelerate ePortfolio innovation for teaching and learning. Influence and reflect best practices in portfolio thinking. Influence the movement of open source in education. Source: http://www.theospi.org/

Over the last two decades, information technology has been moving towards distributed computing to host their applications and services. These systems can process more data more reliably than their central processing counterparts; however, distributed applications are more complex to design and develop because they require additional properties like replication and fault tolerance to work effectively. These complexities translate to the educational setting, where schools need to invest in additional infrastructure, knowledge, and technologies to teach distributed concepts to students. This project presents the design and implementation of a complete educational framework for the teaching of distributed computing concepts at Cal Poly. The framework consists of three components: a Raspberry Pi cluster, a custom distributed file system (DecaFS), and a set of labs that can be used to support coursework in a distributed computing class. Each cluster is composed of five networked Raspberry Pi computers. The DecaFS distributed file system runs on the Raspberry Pi cluster. DecaFS provides the base functionality of a distributed file system with a design that allows for easy modification of sections of the implementation. The lab exercises focus on important distributed computing concepts that represent a variety of problems encountered in distributed systems including distribution, replication, fault tolerance, recovery, rebalancing, and efficiency. Isolation of the lab related modules allows students to focus on the learning objectives of the labs without needing to set up network and file system infrastructure to support the distributed aspects. The complexities of teaching distributed computing concepts in a classroom setting at Cal Poly have been addressed with this project's framework. The solution overcomes key educational challenges as it is portable, modular, scalable and affordable. The framework provides the ability to offer courses in distributed computing to better prepare students for the challenges presented in industry today. Through the use of a modular distributed file system and computing cluster that were created for this project, students are able to solve complex distributed problems, in the form of labs, in an isolated environment that is conducive to quarter long learning objectives. This work is a major step to bringing distributed computing into the classrooms at Cal Poly and classes are currently being designed around this curriculum. Cal Poly can evolve the framework to keep pace with the ever advancing information technology world so that it may continue to serve the needs of the faculty and students of Cal Poly.

The simulation of power system behavior, especially transient behavior, helps us in the analysis and planning of various power systems. However, power systems are usually highly complex and geographically distributed. Therefore system partitioning can be used to allow for sharing resources in simulation. In this work, distributed simulations of power system models have been developed using an electromagnetic transient simulator, namely Real Time Digital Simulator (RTDS). The goal is to demonstrate and assess the feasibility of both non-real-time and real-time simulations using the RTDS in a geographically distributed scenario. Different protocols and options used in the communication between power systems have been studied and analyzed. In this work, a test bed has been developed for data transfer between a power system simulated in RTDS at Mississippi State University and the power system simulated in RTDS at Texas A&M University. Different protocols, available for the interface and communication in the RTDS, have been studied and applied in this work. Finally, a locally distributed wide area control test bed was developed and simulated.

Systems operating in a medical environment need to maintain high standards regarding availability and performance. Large amounts of images are stored and studied to determine what is wrong with a patient. This puts hard requirements on the storage of the images. In this thesis, ways of incorporating distributed storage into a medical system are explored. Products, inspired by the success of Google, Amazon and others, are experimented with and compared to the current storage solutions. Several “non-relational databases” (NoSQL) are investigated for storing medically relevant metadata of images, while a set of distributed file systems are considered for storing the actual images. Distributed processing of the stored data is investigated by using Hadoop MapReduce to generate a useful model of the images' metadata.

The design and regulation of power equipments which installed in distribution system are based on single direction power flow. When distributed generators (DG) are added into distribution system, it may cause some technical problems such as two-way current, fault capacity and power quality. In general, the utility should make sure that its power system could be operated safely and reliably before integrating DG into the system. If there are no complete measurements for DG, the capacity of DG would be restricted by fault current, short circuit capacity, feeder voltage or other problems. In this research, the focus is on the influence of DG operations in distribution system and the increase of DG integration capacity. The impacts of different combinations of DG generation profiles and control strategies are first analyzed, followed by the use of particle swarm optimization (PSO) technique to search for better feeder reconfigurations in order to increase DG integration capacity.

Networked multi-agent systems have attracted lots of researchers to develop algorithms, techniques, and applications.A multi-agent networked system consists of more than one subsystem (agent) to cooperately solve a global problem with only local computations and communications in a fully distributed manner. These networked systems have been investigated in various different areas including signal processing, control system, and machine learning. We can see massive applications using networked systems in reality, for example, persistent surveillance, healthcare, factory manufacturing, data mining, machine learning, power system, transportation system, and many other areas. Considering the nature of those mentioned applications, traditional centralized control and optimization algorithms which require both higher communication and computational capacities are not suitable. Additionally, compared to distributed control and optimization approaches, centralized control, and optimization algorithms cannot be scaled into systems with a large number of agents, or guarantee performance and security. All of the limitations of centralized control and optimization algorithms motivate us to investigate and develop new distributed control and optimization algorithms in networked systems. Moreover, convergence rate and analysis are crucial in control and optimization literature, which motivates us to investigate how to analyze and accerlate the convergence of distributed optimization algorithms.

The main objective of this study is to analyze the impact of the stochastic renewable distributed generation (DG) system on the urban distribution network. Renewable DG systems, particularly photovoltaic (PV) systems, dispersed on the distribution network may, in spite of their relatively small individual capacities, change the behavior of such a network. Therefore, this study (1) developed tools and algorithms useful for planning, designing, and operating such a network, (2) addressed some of the issues in the analysis of the impact of renewable DG systems on such a network, and (3) designed a framework for streamlining the future development and the smooth integration of renewable DG systems into the urban distribution network. For this purpose, in Task 1, using the backward and forward sweep method implemented in MATLAB, this study developed an algorithm for three-phase power flow that models power system components, including distribution systems, transformers, and PV systems. To model the influence of the inherent uncertainty of the input, the location, and the capacity of the PV system, this study implemented a stochastic simulation algorithm combined with the power-flow algorithm. It also accelerated the stochastic algorithm using a method of variance reduction, including importance sampling, and the sampling of representative clusters and extreme points, which reduced the extremely heavy computational burden that the stochastic simulation inevitably imposed. Then this study analyzed inherent uncertainties such as the inputs, the locations, and the capacities of residential PV systems stochastically installed on urban distribution networks by performing several stochastic simulations. In Task 2, this study developed a genetic algorithm in MATLAB that solves an optimization problem that maximizes the reliability (or minimizes the frequency and the duration of failure) of urban distribution networks enhanced by protection devices (i.e., the recloser, the fuse, and the switch) and renewable DG. Using the backward and forward method, this study implemented an analytical method that simulates all possible permanent and transient faults and evaluated the reliability of an urban distribution network housing a combination of fuses, switches, reclosers, and DG systems. Then it analyzed the impact of both the DG system, including the effect of the islanded operation of the DG system, and the protection device, on the reliability of the urban distribution network. The objective of Task 3 of this study was to present a useful method for analyzing the impact of geographically dispersed DG systems, particularly PV systems, on statewide and nationwide power grids. Using the methods of Lagrangian optimization and hydrothermal coordination, this study developed an algorithm for environmentally constrained generation resource allocation that minimizes both fuel costs and ecological impact, including the cost and the impact of water consumption. Then, this study (1) analyzed, as an example of the statewide power grid of the future, the power system of the state of Georgia in 2010, (2) modeled the load consumption and the water inflow of the power system, (3) synthesized third-order power output functions for costs, emissions, and water consumption from actual heat-rate data, and (4) estimated the power output of PV systems geographically dispersed throughout the state and hydroelectric resources of the state in hourly intervals. Lastly, it performed simulations for the generation resource allocation of the power system in hourly and minute intervals.

Concurrent computations have been modeled using partial orders in both event based and state based domains. We give necessary and sufficient conditions on partial orders for them to be valid state based or event based models of concurrent computations. In particular, we define notions of width-extensibility and interleaving-consistency of partial orders, and show that a partial order can be valid state based model of a concurrent computation iff it is width-extensible. Distributed computations that involve asynchronous message passing are a subset of concurrent computations. For asynchronous distributed computations, a partial order can be a valid state based model iff it is width-extensible and interleaving-consistent. We show a duality between the event based and state based models of concurrent computations, and give algorithms to convert partial orders from the event based domain to state based domain and vice-versa. / text