SEARCH · Engineering Papers

Results for “distributed scheduling”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6

All sources NASA NTRS DOE OSTI

NASA NTRS1994

Autonomous mission planning and scheduling: Innovative, integrated, responsive

Autonomous mission scheduling, a new concept for NASA ground data systems, is a decentralized and distributed approach to scientific spacecraft planning, scheduling, and command management. Systems and services are provided that enable investigators to operate their own instruments. In autonomous mission scheduling, separate nodes exist for each instrument and one or more operations nodes exist for the spacecraft. Each node is responsible for its own operations which include planning, scheduling, and commanding; and for resolving conflicts with other nodes. One or more database servers accessible to all nodes enable each to share mission and science planning, scheduling, and commanding information. The architecture for autonomous mission scheduling is based upon a realistic mix of state-of-the-art and emerging technology and services, e.g., high performance individual workstations, high speed communications, client-server computing, and relational databases. The concept is particularly suited to the smaller, less complex missions of the future.

Sary, Charisse↗

NASA NTRSDate not supplied

X-57 High-Lift Propeller Control Schedule Development

The NASA X-57 distributed electric propulsion flight demonstrator uses a high-lift propeller system to maintain low-speed capability with a highly loaded, cruise-efficient wing. Previous research showed that the control scheme for the high-lift propellers was a crucial factor to enable an adequate balance between stabilized glideslope control and appropriate lift margin during the approach-to-landing phase of flight. This paper expands the high-lift propeller control considerations to include all phases of low-speed flight, including preflight, taxi, takeoff, initial climb, approach, and landing. Two control modes, termed airspeed and fixed mode, are developed in this paper. The airspeed mode varies propeller torque based on equivalent airspeed to account for different phases of ground and flight operations. The fixed mode operates the high-lift propeller system at a fixed rotational speed to account for failures in the air data system, preflight checkout, and high-performance takeoff operations. Modeling of the high-lift propellers within the X-57 low-speed flight envelope shows that (1) the structural rotational speed limit of the propeller blades limits their effectiveness at higher altitudes and airspeeds, (2) the speed setting of the fixed mode is set by the maximum torque of the airspeed mode, and (3) minimizing the potential for windmilling in non-standard conditions sets the torque schedule at higher speeds. Additionally, the fixed mode is shown to provide an increased climb rate during normal takeoff operations.

Nicholas K. Borer↗

NASA NTRS1992

Autonomous power system: Integrated scheduling

The Autonomous Power System (APS) project at NASA Lewis Research Center is designed to demonstrate the abilities of integrated intelligent diagnosis, control and scheduling techniques to space power distribution hardware. The project consists of three elements: the Autonomous Power Expert System (APEX) for fault diagnosis, isolation, and recovery (FDIR), the Autonomous Intelligent Power Scheduler (AIPS) to determine system configuration, and power hardware (Brassboard) to simulate a space-based power system. Faults can be introduced into the Brassboard and in turn, be diagnosed and corrected by APEX and AIPS. The Autonomous Intelligent Power Scheduler controls the execution of loads attached to the Brassboard. Each load must be executed in a manner that efficiently utilizes available power and satisfies all load, resource, and temporal constraints. In the case of a fault situation on the Brassboard, AIPS dynamically modifies the existing schedule in order to resume efficient operation conditions. A database is kept of the power demand, temporal modifiers, priority of each load, and the power level of each source. AIPS uses a set of heuristic rules to assign start times and resources to each load based on load and resource constraints. A simple improvement engine based upon these heuristics is also available to improve the schedule efficiency. This paper describes the operation of the Autonomous Intelligent Power Scheduler as a single entity, as well as its integration with APEX and the Brassboard. Future plans are discussed for the growth of the Autonomous Intelligent Power Scheduler.

Ringer, Mark J.↗

NASA NTRS1992

Scheduling lessons learned from the Autonomous Power System

The Autonomous Power System (APS) project at NASA LeRC is designed to demonstrate the applications of integrated intelligent diagnosis, control, and scheduling techniques to space power distribution systems. The project consists of three elements: the Autonomous Power Expert System (APEX) for Fault Diagnosis, Isolation, and Recovery (FDIR); the Autonomous Intelligent Power Scheduler (AIPS) to efficiently assign activities start times and resources; and power hardware (Brassboard) to emulate a space-based power system. The AIPS scheduler was tested within the APS system. This scheduler is able to efficiently assign available power to the requesting activities and share this information with other software agents within the APS system in order to implement the generated schedule. The AIPS scheduler is also able to cooperatively recover from fault situations by rescheduling the affected loads on the Brassboard in conjunction with the APEX FDIR system. AIPS served as a learning tool and an initial scheduling testbed for the integration of FDIR and automated scheduling systems. Many lessons were learned from the AIPS scheduler and are now being integrated into a new scheduler called SCRAP (Scheduler for Continuous Resource Allocation and Planning). This paper will service three purposes: an overview of the AIPS implementation, lessons learned from the AIPS scheduler, and a brief section on how these lessons are being applied to the new SCRAP scheduler.

Ringer, Mark J.↗

NASA NTRS1992

Lessons learned from the Autonomous Power System

The Autonomous Power System (APS) project at the NASA Lewis Research Center is designed to demonstrate the applications of integrated intelligent diagnosis, control and scheduling techniques to space power distribution systems. The project consists of three elements: the Autonomous Power Expert System (APEX) for Fault Diagnosis, Isolation, and Recovery (FDIR); the Autonomous Intelligent Power Scheduler (AIPS) to efficiently assign activities start times and resources; and power hardware (Brassboard) to emulate a space-based power system. The APS project had been through one design iteration. Each of the three elements of the APS project has been designed, tested, and integrated into a complete working system. After these three portions were completed, an evaluation period was initiated. Each piece of the system was critiqued based on individual performance as well as the ability to interact with the other portions of the APS project. These critiques were then used to determine guidelines for new and improved components of the APS system.

Ringer, Mark J.↗

NASA NTRS2003

Job Superscheduler Architecture and Performance in Computational Grid Environments

Computational grids hold great promise in utilizing geographically separated heterogeneous resources to solve large-scale complex scientific problems. However, a number of major technical hurdles, including distributed resource management and effective job scheduling, stand in the way of realizing these gains. In this paper, we propose a novel grid superscheduler architecture and three distributed job migration algorithms. We also model the critical interaction between the superscheduler and autonomous local schedulers. Extensive performance comparisons with ideal, central, and local schemes using real workloads from leading computational centers are conducted in a simulation environment. Additionally, synthetic workloads are used to perform a detailed sensitivity analysis of our superscheduler. Several key metrics demonstrate that substantial performance gains can be achieved via smart superscheduling in distributed computational grids.

Shan, Hongzhang↗

NASA NTRS1989

Finding idle machines in a workstation-based distributed system

The authors describe the design and performance of scheduling facilities for finding idle hosts in a workstation-based distributed system. They focus on the tradeoffs between centralized and decentralized architectures with respect to scalability, fault tolerance, and simplicity of design, as well as several implementation issues of interest when multicast communication is used. They conclude that the principal tradeoff between the two approaches is that a centralized architecture can be scaled to a significantly greater degree and can more easily monitor global system statistics, whereas a decentralized architecture is simpler to implement.

Theimer, Marvin M.↗

NASA NTRS1997

Research in Distributed Real-Time Systems

This document summarizes the progress we have made on our study of issues concerning the schedulability of real-time systems. Our study has produced several results in the scalability issues of distributed real-time systems. In particular, we have used our techniques to resolve schedulability issues in distributed systems with end-to-end requirements. During the next year (1997-98), we propose to extend the current work to address the modeling and workload characterization issues in distributed real-time systems. In particular, we propose to investigate the effect of different workload models and component models on the design and the subsequent performance of distributed real-time systems.

Mukkamala, R.↗

NASA NTRS1987

Deep space network resource scheduling approach and application

Deep Space Network (DSN) resource scheduling is the process of distributing ground-based facilities to track multiple spacecraft. The Jet Propulsion Laboratory has carried out extensive research to find ways of automating this process in an effort to reduce time and manpower costs. This paper presents a resource-scheduling system entitled PLAN-IT with a description of its design philosophy. The PLAN-IT's current on-line usage and limitations in scheduling the resources of the DSN are discussed, along with potential enhancements for DSN application.

Eggemeyer, William C.↗

NASA NTRS1981

Project resource reallocation algorithm

A methodology for adjusting baseline cost estimates according to project schedule changes is described. An algorithm which performs a linear expansion or contraction of the baseline project resource distribution in proportion to the project schedule expansion or contraction is presented. Input to the algorithm consists of the deck of cards (PACE input data) prepared for the baseline project schedule as well as a specification of the nature of the baseline schedule change. Output of the algorithm is a new deck of cards with all work breakdown structure block and element of cost estimates redistributed for the new project schedule. This new deck can be processed through PACE to produce a detailed cost estimate for the new schedule.

Myers, J. E.↗

NASA NTRS1991

Autonomous power system intelligent diagnosis and control

The Autonomous Power System (APS) project at NASA Lewis Research Center is designed to demonstrate the abilities of integrated intelligent diagnosis, control, and scheduling techniques to space power distribution hardware. Knowledge-based software provides a robust method of control for highly complex space-based power systems that conventional methods do not allow. The project consists of three elements: the Autonomous Power Expert System (APEX) for fault diagnosis and control, the Autonomous Intelligent Power Scheduler (AIPS) to determine system configuration, and power hardware (Brassboard) to simulate a space based power system. The operation of the Autonomous Power System as a whole is described and the responsibilities of the three elements - APEX, AIPS, and Brassboard - are characterized. A discussion of the methodologies used in each element is provided. Future plans are discussed for the growth of the Autonomous Power System.

Ringer, Mark J.↗

NASA NTRS1991

Autonomous Power System intelligent diagnosis and control

Ringer, Mark J.↗

NASA NTRS2005

ROBUS-2: A Fault-Tolerant Broadcast Communication System

The Reliable Optical Bus (ROBUS) is the core communication system of the Scalable Processor-Independent Design for Enhanced Reliability (SPIDER), a general-purpose fault-tolerant integrated modular architecture currently under development at NASA Langley Research Center. The ROBUS is a time-division multiple access (TDMA) broadcast communication system with medium access control by means of time-indexed communication schedule. ROBUS-2 is a developmental version of the ROBUS providing guaranteed fault-tolerant services to the attached processing elements (PEs), in the presence of a bounded number of faults. These services include message broadcast (Byzantine Agreement), dynamic communication schedule update, clock synchronization, and distributed diagnosis (group membership). The ROBUS also features fault-tolerant startup and restart capabilities. ROBUS-2 is tolerant to internal as well as PE faults, and incorporates a dynamic self-reconfiguration capability driven by the internal diagnostic system. This version of the ROBUS is intended for laboratory experimentation and demonstrations of the capability to reintegrate failed nodes, dynamically update the communication schedule, and tolerate and recover from correlated transient faults.

Torres-Pomales, Wilfredo↗

NASA NTRSDate not supplied

The Influence of Heat Treatments on the Microstructure and Tensile Properties of Additively Manufactured Inconel 939

This study investigated the effect of heat treatment variations on the microstructure and tensile properties of laser powder bed fused Inconel 939 manufactured via laser powder bed fusion. Three different heat treatment schedules, all of which comprise stress relief, hot isostatic pressing, solution annealing, and aging, were followed, and resulting changes in microstructure were analyzed using scanning electron microscopy. Tensile tests were conducted on specimens subjected to different heat treatments to evaluate the mechanical properties at room temperature. Microstructural results showed that solution treatment at 1190 °C for 4 h led to better removal of dendritic microstructure, while second-step aging at 850 °C resulted in monomodal distribution of precipitates. However, the second-step aging temperatures from 750 to 800 °C resulted in bi-modal distribution. The optimal heat treatment schedule, which yielded a superior combination of strength and ductility, involved solution treatment at 1190 °C for 4 h and two-step aging at 1000 °C for 6 h and 800 °C for 4 h.

Laser powder bed fusion (L-PBF)↗

NASA NTRS1991

Measuring the effects of heterogeneity on distributed systems

Distributed computer systems in daily use are becoming more and more heterogeneous. Currently, much of the design and analysis studies of such systems assume homogeneity. This assumption of homogeneity has been mainly driven by the resulting simplicity in modeling and analysis. A simulation study is presented which investigated the effects of heterogeneity on scheduling algorithms for hard real time distributed systems. In contrast to previous results which indicate that random scheduling may be as good as a more complex scheduler, this algorithm is shown to be consistently better than a random scheduler. This conclusion is more prevalent at high workloads as well as at high levels of heterogeneity.

El-Toweissy, Mohamed↗

NASA NTRS1990

A curriculum for real-time computer and control systems engineering

An outline of a syllabus for the education of real-time-systems engineers is given. This comprises the treatment of basic concepts, real-time software engineering, and programming in high-level real-time languages, real-time operating systems with special emphasis on such topics as task scheduling, hardware architectures, and especially distributed automation structures, process interfacing, system reliability and fault-tolerance, and integrated project development support systems. Accompanying course material and laboratory work are outlined, and suggestions for establishing a laboratory with advanced, but low-cost, hardware and software are provided. How the curriculum can be extended into a second semester is discussed, and areas for possible graduate research are listed. The suitable selection of a high-level real-time language and supporting operating system for teaching purposes is considered.

Halang, Wolfgang A.↗

NASA NTRS1994

ATAMM enhancement and multiprocessing performance evaluation

The algorithm to architecture mapping model (ATAAM) is a Petri net based model which provides a strategy for periodic execution of a class of real-time algorithms on multicomputer dataflow architecture. The execution of large-grained, decision-free algorithms on homogeneous processing elements is studied. The ATAAM provides an analytical basis for calculating performance bounds on throughput characteristics. Extension of the ATAMM as a strategy for cyclo-static scheduling provides for a truly distributed ATAMM multicomputer operating system. An ATAAM testbed consisting of a centralized graph manager and three processors is described using embedded firmware on 68HC11 microcontrollers.

Stoughton, John W.↗

NASA NTRS2001

Reasoning abstractly about resources

r describes a way to schedule high level activities before distributing them across multiple rovers in order to coordinate the resultant use of shared resources regardless of how each rover decides how to perform its activities. We present an algorithm for summarizing the metric resource requirements of an abstract activity based n the resource usages of its potential refinements.

abstraction planning rovers multiple agents↗