Multiple Workstations Research Articles

Temporal load balancing for distributed backup scheduling

The costs for building and using a data network typically depend on the carried load, and one of the primary challenges in managing such networks is the need to reduce peak traffic and achieve temporal load balancing. In this paper we focus on the portion of network traffic generated by the users’ backups, and we address the problem of shifting backup traffic to off-peak hours within the constraints imposed by user connectivity and the distributed nature of the backup protocol. Consider a group of users who need to regularly back up data to a central server. Users can only do a backup when connected to the network, and user connectivity may vary over time. The connectivity is typically correlated to the overall load, which creates a tradeoff between reducing peak load and ensuring regular backups. Backup attempts are initiated locally, without knowledge on the status of other users or the overall network load. The backup activity of connected users is governed by a probabilistic algorithm, characterized by backup probabilities that depend on the hour of the day and the time since the previous backup. This work is part of a joint project between IBM research and the IBM divisions Europe Innovations Team and Integrated Technology Delivery, and aims to design the backup probabilities that minimize the networking costs, while ensuring that the time between successive backups remains small. We have not found any study in the literature on temporal load balancing for distributed backup scheduling. The term load balancing often refers to the practice of distributing workload evenly across multiple workstations or servers to achieve optimal resource utilization. The most relevant study that we are aware of is by Sandnes and Huang [2], in which a temporal load balancing strategy for distributed web applications is proposed and analyzed. The problem of temporal load-balancing is also related to incentivizing commuters to travel at less congested times [1] and peak-shaving in power systems [3]. However, the distributed nature and high delay-tolerance of our setting create unique challenges. The remainder of this extended abstract is structured as follows. In Section 2 we present the model, and we describe our algorithm for deriving the optimal backup probabilities in Section 3. In Section 4 this approach is applied to balance traffic of the data network of an IBM location. We conclude by discussing future research directions in Section 5.

Optimal Buffer Allocation in Flexible Manufacturing Systems Using Genetic Algorithm and Simulation

Over the past few decades, buffer allocation problems have been investigated extensively. It is widely known that buffers play important roles in the manufacturing system, including preparing disruption and improving efficiency. However, due to a physical limit for buffer space and the related cost burden, optimal buffer allocation has become an important issue. In this paper, a solution for optimal buffer allocation in a flexible manufacturing system (FMS) with finite buffers is presented. Unlike most previous studies, which mainly focused on input buffers only and operation dispatching in simple production lines, this paper considers both input and output buffers together in complex production lines where multiple workstations, multiple automatic guided vehicles, and complicated paths exist. Also, we address a practical buffer allocation problem by increasing total number of buffers and changing a buffer profile (capacities of multiple input/output buffers). A simulation and a genetic algorithm are used to solve our problem. While the simulation models the process of the complex FMS, the genetic algorithm determines the optimal buffer allocation. The proposed solution performs better than the conventional heuristic used in practice.

Utilizing simulation to evaluate production line performance under varying demand conditions

Determining how a new production cell will function is problematic and can lead to disastrous results if done incorrectly. Discrete-event simulation can provide information on how a line will function before, during, and after the line is in operation. A simulation model can also provide a visual animation of the line to see how product will flow through the line. This paper discusses the development and analysis of a simulation model of a new manufacturing line. The manufacturing cell is a new motor assembly cell. An analysis of the capability of the line for varying demand levels was conducted for the two main motor types produced on the line. An ARENA ® simulation model was developed, verified, and validated to determine the daily production and potential problem areas for the various demand levels. The results show that at all but one demand level, the line is capable of producing to within one unit of customer demand if the required number of workers is present. At the highest demand level, the simulation results suggest that the line is not capable of meeting demand. Additional analysis indicates that multiple workstations could prove problematic with minor fluctuations in demand. Problematic workstations were identified for each assembly area and for the line as a whole.

Relations between volume flexibility and part cost in assembly lines

This paper presents a strategy for achieving volume flexibility in assembly lines, so that varying production demands can be met. The strategy involves providing assembly lines inherent cycle-time flexibility, through creating the possibility for operators to handle multiple work stations. A basic part-cost model serves as a basis for analyzing the cost effects of different staffing alternatives, its taking account of different performance parameters and numbers of operators. Use of the part-cost model is illustrated by analyzing two specific cases differing in the number of operators assigned to the assembly line, the operators being partly permanent and partly temporary workers. It is shown how the costs are affected by the production performance of the work force in question, temporary operators being expected to display a somewhat lower level of performance than permanent workers.

Application of a hybrid MPI/OpenMP approach for parallel groundwater model calibration using multi-core computers

Calibration of groundwater models involves hundreds to thousands of forward solutions, each of which may solve many transient coupled nonlinear partial differential equations, resulting in a computationally intensive problem. We describe a hybrid MPI/OpenMP approach to exploit two levels of parallelisms in software and hardware to reduce calibration time on multi-core computers. HydroGeoChem 5.0 (HGC5) is parallelized using OpenMP for direct solutions for a reactive transport model application, and a field-scale coupled flow and transport model application. In the reactive transport model, a single parallelizable loop is identified to account for over 97% of the total computational time using GPROF. Addition of a few lines of OpenMP compiler directives to the loop yields a speedup of about 10 on a 16-core compute node. For the field-scale model, parallelizable loops in 14 of 174 HGC5 subroutines that require 99% of the execution time are identified. As these loops are parallelized incrementally, the scalability is found to be limited by a loop where Cray PAT detects over 90% cache missing rates. With this loop rewritten, similar speedup as the first application is achieved. The OpenMP-parallelized code can be run efficiently on multiple workstations in a network or multiple compute nodes on a cluster as slaves using parallel PEST to speedup model calibration. To run calibration on clusters as a single task, the Levenberg–Marquardt algorithm is added to HGC5 with the Jacobian calculation and lambda search parallelized using MPI. With this hybrid approach, 100–200 compute cores are used to reduce the calibration time from weeks to a few hours for these two applications. This approach is applicable to most of the existing groundwater model codes for many applications.

Visual Alerting in Complex Command and Control Environments

A study was conducted to investigate automated visual alerting in complex environments where operators rely on multiple display workstations to perform high-intensity tasks. Two forms of alerts - a short red sidebar and a red border around the perimeter of the workstation display - were examined, as well as two forms of alert state - static and flashing. Results showed that the sidebar alert was detected faster than the border alert regardless of whether it was flashing or static, and in general, sidebar alerts were detected faster when they appeared on all three displays as compared to one display. Future work will focus on examining the association between the display an alert appears on and the spatial location of operator attention.

Dynamic decentralised balancing of CONWIP production systems

This paper presents a non-linear programming model for online balancing of the work-in-queue (WIQ) of a fast response production system that consists of multiple workstations and diverse part mix. The model resembles a multiple product CONWIP system with a variety of products’ routings and bottlenecks. It maximises a global benefit of the production system subject to delay and loading rate bounds. The upper bounds on the delay symbolise the desired level of WIQ. The approach relies on the delay of the authorisation cards as a measure of the actual system WIQ. A real-time primal-dual algorithm associated with each part type is used to solve the optimisation problem in a decentralised manner. The algorithm solves for the optimal rates in a timely decentralised iterative way without the access to the global information of the production system. Each part route calculates its loading rate according to the arrival of the authorisation cards. Extensive simulation experiments were conducted to demonstrate the reliability of the algorithm. The calculated rates were found to be proportional to the level of WIQ at each workstation with reasonable resource allocation achieved between the different routes.

Radar image processing with clusters of computers

Some radar image processing algorithms such as shape-from-shading are particularly compute-intensive and time-consuming. If, in addition, a data set to be processed is large, then it may make sense to perform the processing of images on multiple workstations or parallel processing systems. We have implemented shape-from-shading, stereo matching, resampling, gridding, and visualization of terrain models in such a manner that they execute either on parallel machines or on clusters of workstations. We were motivated by the large image data set from NASA's Magellan mission to planet Venus, but received additional inspiration from the European Union's Center for Earth Observation program (CEO) and Austria's MISSION initiative for distributed processing of remote sensing images on remote workstations, using publicly-accessible algorithms. We developed a multi-processor approach that we denote as CDIP for Concurrent and Distributed Image Processing. The speedup for image processing tasks increases nearly linearly with the number of processors, be they on a parallel machine or arranged in a cluster of distributed workstations. Our approach adds benefits for users of complex image processing algorithms: the efforts for code porting and code maintenance are reduced and the necessity for specialized parallel processing hardware is eliminated.

Contractor Prebid Planning Principles

Planning is an essential function of project management. Yet, many small- and medium-sized contractors do a relatively poor job of operational planning. Better prebid plans will reduce costs, shorten schedules, and improve labor productivity. Unfortunately, the published literature offers little guidance for smaller contractors on what constitutes effective planning. Most papers describe planning as a macrolevel process for owners. Most emphasize scope definition for industrial projects. This paper describes a microlevel planning process for contractors. It consists of eight steps which are: (1) assess contract risks; (2) develop a preliminary execution plan; (3) develop site layout plans; (4) identify the sequences that are essential-to-success; (5) develop detailed operational plans; (6) develop proactive strategies to assure construction input into design; (7) revise the preliminary plan; and (8) communicate and enforce the plan. The entire process is illustrated with a case study project and is fully illustrated with figures which show how to integrate the work of multiple contractors, keep key resources (crews or equipment) fully engaged with no downtime, provide time buffers so the work of follow on crews can be efficiently done, expedite the schedule using multiple work stations and concurrent work, ways to communicate the work plan to the superintendent and foremen, and how to assess the feasibility of various work methods. The steps are easy to understand and implement. They will yield immediate positive results.

Using simulation and multi-criteria methods to provide robust solutions to dispatching problems in a flow shop with multiple processors

Dispatching rules are important to the performance of a manufacturing system. Selective applications of different priority rules at different processing stages in a multiple workstation manufacturing system have a positive impact on shop performance. This type of problem is a combinatorial dispatching decision. However, no dispatching rule can consistently produce better performance than all other rules under a variety of operating conditions and criteria. It is the purpose of this study to provide a robust solution for a dispatching decision that will have ‘good’ performance under different operating scenarios. In this paper a simulation case of a flow shop with multiple processors is proposed, specifically a multi-layer ceramic capacitor manufacturing system. Two multiple criteria decision-making methods – techniques for order preference by similarity to ideal solution (TOPSIS) and an analytic hierarchy process (AHP) – in combination with Taguchi orthogonal array are used to find the most suitable dispatching rule for every workstation. The results show that for 15 production scenarios and 4 criteria this combinatorial dispatching rule is robust, in the sense that it outperforms other commonly employed strategies.

Design of a flexible platform for execution of medical decision support agents in the intensive care unit

This paper addresses the design of a generic and scalable platform for the execution of medical decision support agents in the intensive care unit (ICU). As will be motivated, medical decision support agents can impose high computational load and in practical setups a large amount of such agents are typically running in parallel. Future ICU systems will rely on extensive medical decision support. However, in current systems only one workstation is typically dedicated for the execution of medical decision support agents. Therefore, we propose an architecture based on middleware technology to allow for easy distribution of the agents along multiple workstations. The architecture allows for easy integration with a general ICU data flow management architecture.

Resource scheduling and load balancing in distributed robotic control systems

This paper describes the latest advances made to a software architecture designed to control multiple miniature robots. As the robots themselves have very limited computational capabilities, a distributed control system is needed to coordinate tasks among a large number of robots. Two of the major challenges facing such a system are the scheduling of access to system resources and the distribution of work across multiple workstations. This paper discusses solutions to these problems in the context of a distributed surveillance task.

Time-based goal chasing method for mixed-model assembly line problem with multiple work stations

In sequencing problems for mixed-model assembly line in JIT production system, the Goal Chasing method (GC) is widely used for parts used leveling goal. The difference in assembly time of each product is not taken into consideration in the Goal Chasing method. Assembly time usually varies with product types. In recent years, the Time-Based Goal Chasing method (TBGC) has been proposed. The advantage of TBGC is to consider the influence of different assembly time of each product and idle time in production period. TBGC, however, has been only applied to single work station problems. In this paper, TBGC is applied to an assembly line problem with multiple work stations. Furthermore, the sequencing method and use of Simulated Annealing (SA) or Local Search (LS) for this problem are proposed.

Blood Centers Adopt Manufacturing Practices To Ensure Quality, Consistency

Blood Centers Adopt Manufacturing Practices To Ensure Quality, Consistency

Steps Towards Advanced Cell Control Systems: An Application in Flexible Assembly Systems

Abstract This paper presents an advanced cell control system which integrates design, modelling, control and monitoring capabilities and demonstrates its use in a class of Flexible Assembly System (FAS). From this research work, a Timed Colour Petri Net (TCPN) based model for the design and modelling of FAS is proposed. Furthermore, through the adoption of a Manufacturing Message Specifications (MMS) based open network communication scheme, a real-time distributed client/server control methodology is formulated. These techniques are integrated within an advanced cell control architecture which is demonstrated through the implementation of a class of FAS using multiple robotic workstations and a conveyor based materials handling system for concurrent manufacture of products in small batch quantities. Operational flexibility is enhanced by the introduction of a flexible process planning scheme and a genetic algorithm for real-time searching of near-optimal production sequences and operation assignments. Suc...

On the construction of a powerful distributed authentication server without additional key management

The extensive use of networks and distributed systems has increased the need for authentication and digital signatures. In performing authentication on a massive scale, authentication servers that use multiple workstations or PCs are more economical than servers that use one minicomputer or mainframe. However, the establishment of authentication servers with multiple platforms can cause some security problems and increase the cost of key management because all platforms within the server must have the private key of the authentication server. We propose a model for a distributed authentication server, in which one platform keeps the secret information, while the other platforms just do calculations (therefore, no additional key management).

Measurements and calculations of thermal neutron fluence rate and neutron energy spectra resulting from moderation of 252Cf fast neutrons: applications for neutron capture therapy.

252Cf is a neutron emitting radioisotope which has promise for both standard brachytherapy and neutron capture enhanced brachytherapy. In this study, experimental measurements and calculations were used to determine the thermal neutron fluence rate, phi(th) [n cm(-2) s(-1) mg(-1)], in the vicinity of 252Cf applicator tube (AT) type sources. Results of these measurements were confirmed with Monte Carlo calculations performed in a distributed manner on multiple workstations using MCNP. Three studies were executed: (1) relative phi(th) as a function of distance from a 252Cf AT source in an A-150 tissue equivalent plastic phantom using thermoluminescent dosimeters (TLDs) of varying 6Li/Li enrichment, (2) phi(th) measured with gold foils in a 114 liter water phantom 5 cm from two 252Cf AT sources, and (3) calculations of the impact of phantom material composition (e.g., A-150, water, brain, muscle) on phi(th) from moderated 252Cf fast neutrons. TLD results and Monte Carlo calculations in A-150 of relative phi(th) typically agreed within 1% and at most differed by 3% for distances from 1 to 6 cm. Foil measurements followed the ASTM E 262-86e protocol, and the ratio of activated plain and Cd encased gold foils (7.31) agreed well with the calculated ratio (7.26). Measured phi(th) at 5 cm (1.70+/-0.10 x 10(7) n cm(-2) s(-1) mg(-1)) was 10% greater than that determined using MCNP (1.55+/-0.12 x 10(7) n cm(-2) s(-1) mg(-1)), but was within the combined uncertainties. Compared with A-150 at a distance of 1 cm, phi(th) was 20%, 22%, and 32% less for water, brain, and muscle, respectively; these ratios decreased to 16%, 16%, and 24% less, respectively, at a distance of 5 cm from the source in a 15 cm diameter phantom. Comparisons of these results generally agreed with those in the literature for a value of 2 x 10(7) n cm(-2) s(-1) mg(-1) in water at 3 cm.

Configuration and evaluation of an emulator for telecommunication service specification including screening service

There is a need for technologies that can rapidly and accurately acquire the request specifications for telecommunication services and that can mechanically support specification verification in the upper-level process of the upstream processes of telecommunication service software development. In this paper, we propose an emulator for telecommunication service specifications that supports improved understanding of a specification's operation by testing the operation based on the telecommunication service specification described by state transition rules (STRs), which constitute a declarative telecommunication service specification description language, and can verify the validity of the telecommunication service specification and check for contention between multiple services. Specifically, network functions and terminal functions are set up in multiple work stations connected over a LAN. The service scenario described by the STRs is saved on the network function side. Then based on the scenario, the operations are executed sequentially. We propose a system extension method corresponding to a screening service that selects a service provided with specific conditions in a customized service that is specified to match the user's preferences. This extension makes available an emulator of the comprehensive telecommunication service specifications, which include the screening conditions specified by the user. Thus, further improvement in the user's satisfaction with the requests in the telecommunication service specification can be expected. The effectiveness of the system configured on the LAN was evaluated. © 2000 Scripta Technica, Electron Comm Jpn Pt 1, 84(4): 11–21, 2001

Algorithms for Toyota's goal of sequencing mixed models on an assembly line with multiple workstations

Toyota's goal of sequencing mixed models on an assembly line is to keep the constant usage rate of every part used in the assembly line. This paper deals with Toyota's goal of sequencing mixed models on an assembly line with multiple workstations. A sequencing problem with Toyota's goal is formulated. Two algorithms based on different mechanisms, respectively modified goal chasing and simulated annealing, are developed for solving the sequencing problem. A number of numerical experiments are carried out for evaluating the efficiency of the algorithms. Computational results show that one of the algorithms generates good sub-optimal solutions with very short CPU times, while the other can reach optimal solutions with longer, but acceptable, CPU times.

Algorithms for Toyota's Goal of Sequencing Mixed Models on an Assembly Line with Multiple Workstations

Algorithms for Toyota's Goal of Sequencing Mixed Models on an Assembly Line with Multiple Workstations