Scalable Capacity Research Articles

Modelling and analysis of dynamic capacity complexity in multi-stage production

The uncertainty associated with managing dynamic capacity problem is the main source of its complexity. This article presents a system dynamics approach to model and analyse operational complexity of dynamic capacity in multi-stage production. The unique feature of this approach is that it captures the stochastic nature of three main sources of complexity associated with dynamic capacity. These are the demand, internal manufacturing delay and capacity scalability delay. The developed model was demonstrated by an industrial case study of multi-stage printed circuit board assembly line. The analysis of simulation experiments showed that ignoring complexity sources can lead to wrong decisions concerning both scaling levels and backlog management decisions. In addition, a general trade-off between the controllability and complexity of the dynamic capacity was illustrated. Finally, comparative analysis of the effect of each of these sources on the complexity level revealed that internal delay has the highest impact on dynamic capacity efficiency. Guidelines and recommendations for better capacity management and reduction of its complexity are presented.

MODULAR RECONFIGURABLE MACHINE TOOLS: DESIGN, CONTROL AND EVALUATION

The reconfigurable manufacturing system (RMS) paradigm encapsulates methodologies that enable manufacturing systems to cope effectively with market and product changes. This research presents the design and evaluation of modular reconfigurable machine (MRM) tools as a novel machining solution within the scope of RMS. Mechanical and control designs are presented, outlining the development of this novel machining system. The property of hardware modularity displayed by MRMs enables an adjustment of system functionality and the synergistic redistribution of system resources between production streams, thus facilitating inter-process capacity scaling. Scalable production capacity and adjustable system functionality are the key objectives of reconfigurable manufacturing.

IBM Parallel Sysplex clustering: Technology options for continuous availability

IBM Parallel Sysplex® is a clustering technology that was designed to address specific client business objectives for IBM mainframe System z® servers. The nondisruptive addition of scalable processing capacity and improved application availability with respect to unplanned and planned outages were two key design objectives. This paper focuses on the evolving technology options that support the business objective of continuous availability. Key technology options are discussed relative to their importance to achieving continuous availability. Best practices for effectively using these technology options to improve availability, based on extensive client experiences, are recommended.

Assessing capacity scalability policies in RMS using system dynamics

This paper presents a model for assessing different capacity scalability policies in Reconfigurable Manufacturing System (RMS) for different changing demand scenarios. The novelty of this approach is two fold: (1) it is the first attempt to explore different capacity scalability policies in RMS based on multiple performance measures, mainly scaling rate, Work In Process level, inventory level and backlog level; and (2) the dynamic scalability process in RMS is modeled for the first time using System Dynamics. Different policies for capacity scalability for various demand scenarios were assessed. Numerical simulation results obtained using the developed capacity scalability model showed that the best capacity scalability policy to be adopted for RMS is dependent on the anticipated demand pattern as well as the various manufacturing objectives. The presented assessment results will help the capacity scalability planners better decide the different tradeoffs between the competing strategic and operational objectives of the manufacturing enterprise, before setting the suitable capacity scalability plan parameters.

Distributed inter-domain lightpath provisioning in the presence of wavelength conversion

Dense wavelength division multiplexing (DWDM) has become the dominant transport layer technology for next-generation backbone networks due to its unprecedented capacity scalability. As a result, there is a pressing need to investigate lightpath provisioning in multi-domain DWDM networks. Although inter-domain provisioning has been well-studied for packet/cell-switching networks, the wavelength dimension (along with wavelength conversion) presents many added challenges. To address these concerns, a detailed GMPLS-based hierarchical routing framework for provisioning transparent/translucent/opaque multi-domain DWDM networks is presented. The scheme adapts topology abstraction to hide internal domain state so as to resolve routing scalability and security issues. Specifically a novel full-mesh topology abstraction scheme is developed for full wavelength conversion domains, i.e., to disseminate additional wavelength converter state. Related inter-domain lightpath RWA and signaling schemes are also tabled. Performance analysis results are then presented to demonstrate the effectiveness of the proposed mechanisms along with directions for future research work.

Integrating static and dynamic analysis in studying capacity scalability in RMS

The purpose of this paper is to provide a deeper understanding about the relation between management level and operational level in capacity scalability problem in Reconfigurable Manufacturing Systems (RMS). The approach presented in this paper integrates both static and dynamic analyses. A dynamic model for capacity scalability in RMS is developed and then a study of optimal capacity scalability by means of multi-objective optimisation is discussed. The dynamic model is based on control theory where the capacity scalability system is modelled using block diagram and a transfer function is derived. The capacity scalability controller's gain is determined using multi-objective optimisation. Simulation study of an industrial case for a scenario of exogenous disturbance to RMS is conducted. Results showed the impact of management strategies on the performance of capacity scalability systems in RMS and also the importance of dynamic control for capacity scalability management in modern system like RMS.

RETRACTED ARTICLE: Effect of reconfiguration costs on planning for capacity scalability in reconfigurable manufacturing systems

In a globally competitive market for products, manufacturers are faced with an increasing need to improve their flexibility, reliability, and responsiveness to meet the demands of their customers. Reconfigurable manufacturing systems (RMS) have become an important manufacturing paradigm, because they broadly encompass the ability to react efficiently to this environment by providing the exact capacity and functionality needed when needed. This paper studies how such new systems can manage their capacity scalability planning in a cost effective manner. An approach for modeling capacity scalability planning is proposed. The development of the model is based on set theory and the regeneration point theorem which is mapped to the reconfigurable manufacturing paradigm as the capacity scalability points of that system. The cost function of the model incorporates both the physical capacity cost based on capacity size and costs associated with the reconfiguration process which referred to as the scalability penalty cost and scalability effort cost. A dynamic programming (DP) approach is manipulated for the development of optimal capacity scalability plans. The effect of the reconfiguration costs on the capacity scalability planning horizon and overall cost is investigated. The results showed the relation between deciding on the optimal capacity scalability planning horizon and the different reconfiguration costs. Results also highlighted the fact that decreasing costs of reconfiguration will lead to cost effective implementation of reconfigurable manufacturing systems.

Research on Next-Generation Internet Architecture

The primary problem during the evolvement of next-generation Internet is the contradiction between growing requirements for Internet and the insufficient development of network theory and technology. As the fundamental principles to guide the developing direction of Internet, the study of Internet architecture is always a focus in the research community. To address the core issue of network scalability, we propose multi-dimension scalable architecture of next-generation Internet, the main idea of which is to extend the single-dimension scalability of traditional Internet on interconnection to multi-dimension scalability of next-generation Internet. The multi-dimension scalability is composed of scale-scalability, performance-scalability, security-scalability, function-scalability, and service-scalability. We suggest five elements, namely, IPv6, authentic IPv6 addressing, scalable processing capacity of routers, end-to-end connectionless Quality-of-Service control, and 4over6 mechanism to realize the multi-dimension scalability. The current research results show that the multi-dimension scalable architecture composed of these five elements will bring great influence on next-generation Internet.

Investigating optimal capacity scalability scheduling in a reconfigurable manufacturing system

Responsiveness to dynamic market changes in a cost-effective manner is becoming a key success factor for any manufacturing system in today’s global economy. Reconfigurable manufacturing systems (RMSs) have been introduced to react quickly and effectively to such competitive market demands through modular and scalable design of the manufacturing system on the system level, as well as on the machine components’ level. This paper investigates how RMSs can manage their capacity scalability on the system level in a cost-effective manner. An approach for modeling capacity scalability is proposed, which, unlike earlier approaches, does not assume that the capacity scalability is simply a function of fixed increments of capacity units. Based on the model, a computer tool that utilizes a genetic algorithm optimization technique is developed. The tool aids the systems’ designers in deciding when to reconfigure the system in order to scale the capacity and by how much to scale it in order to meet the market demand in a cost-effective way. The results showed that, in terms of cost, the optimal capacity scalability schedules in an RMS are superior to both the exact demand capacity scalability approach and the approach of supplying all required capacity at the beginning of the planning period, which is adopted by flexible manufacturing systems (FMSs). The results also suggest that the cost-effective implementation of an RMS can be realized through decreasing the cost of reconfiguration of these new systems.

A control approach to explore the dynamics of capacity scalability in reconfigurable manufacturing systems

This paper presents a dynamic model and analysis for one of the major characteristics of reconfigurable manufacturing systems (RMSs)—capacity Scalability. The dynamic model is analyzed using its transfer function. Dynamic characteristics associated with the delay in capacity Scalability and how to minimize this delay are discussed using control approaches. The problem of how to supply exact capacity in response to market changes is also examined by solving the dynamic problem of the production offset phenomenon in RMSs. The effect of work in process as a damping factor for production disturbances during capacity Scalability is addressed. Finally, a general capacity Scalability controller design is proposed to improve the dynamic performance of RMSs in response to sudden demand changes. The proposed controller considers the different activities associated with the capacity scalability process. A numerical example is also presented to highlight the applicability of the approach.

Effect of Time-Based Parameters on the Agility of a Dynamic MPC System

This paper presents a dynamic manufacturing planning and control (MPC) system that can maintain agility through the ability to dynamically switch between different policies due to varying market strategies. The dynamic behavior of the developed system is investigated by studying the effect of the time based parameters on responsiveness and cost effectiveness of the system reflected in the natural frequency and the damping of its different configurations. Results showed that the agility requirements are directly affected by the time based parameters of the MPC system: production lead time, capacity scalability delay, and shipment time. This resulted in a better understanding of the requirements for a well designed agile MPC system.

Using Hardware to Configure a Load-Balanced Switch

Efficient router architectures should have predictable throughput and scalable capacity, as well as internal optical technology (such as optical switches and wavelength division multiplexing) that can increase capacity by reducing power consumption. The load-balanced switch is a promising way to scale router capacity. In this 100-terabit-per-second router, an optical switch spreads traffic evenly among linecards. When the network operator adds or removes linecards, reconfiguring the switch can be time consuming, but a polynomial-time algorithm drastically reduces the required memory-intensive operations, yielding a switch-reconfiguration time below 50 ms.

Memory-bandwidth performance of shared multibuffer switch versus sliding-window switch

Switching architectures with sharable parallel memory modules are known to provide scalable switch capacity with the advantage of complete sharing of memory resource. The router switches that belong in this class, namely the shared multibuffer switch and the sliding-window packet switch, are evaluated for comparing their memory-bandwidth requirement.

A high-speed and low-voltage associative co-processor with exact Hamming/Manhattan-distance estimation using word-parallel and hierarchical search architecture

A high-speed and low-voltage associative co-processor with exact Hamming or Manhattan distance estimation is presented. The word-parallel and hierarchical search architecture is achieved using a logic-in-memory digital implementation. In the bit-serial search architecture, it is important to shorten the search cycle time since the total search time generally increases in proportion to the bit length. The present hierarchical architecture achieves a high-speed operation with a large input number. Furthermore, it provides a result for the data close to the input with a fewer number of clocks. Therefore, it reduces the number of clocks required for nearest-match detection in practical use. The circuit implementation allows unlimited database capacity and achieves a low-voltage operation under 1.0 V for system-on-a-chip applications. The capacity scalability makes it easy to compute a function of Manhattan distance estimation using thermometer encoding. A 64-bit 32-word associative co-processor has been designed using a one-poly-Si five-metal 0.18-/spl mu/m CMOS process and has been successfully tested. The measurement results show that the operation achieves a speed of 411.5 MHz at a supply voltage of 1.8 V. The worst-case search time is 158.0 ns for a 64-bit 32-word database. In a low-voltage operation, the operation speed achieves 40.0 MHz at a supply voltage of 0.75 V.

IMPROVING BANDWIDTH EFFICIENCY IN DISTRIBUTED VIDEO-ON-DEMAND ARCHITECTURES

Distributed Video-on-Demand (DVoD) systems are proposed as a solution to the limited streaming capacity and null scalability of centralized systems. In a previous work, we proposed a fully distributed large-scale VoD architecture, called Double P-Tree, which has shown itself to be a good approach to the design of flexible and scalable DVoD systems. In this paper, we present relevant design aspects related to video mapping and traffic balancing in order to improve Double P-Tree architecture performance. Our simulation results demonstrate that these techniques yield a more efficient system and considerably increase its streaming capacity. The results also show the crucial importance of topology connectivity in improving multicasting performance in DVoD systems. Finally, a comparison among several DVoD architectures was performed using simulation, and the results show that the Double P-Tree architecture incorporating mapping and load balancing policies outperforms similar DVoD architectures.

The sliding-window packet switch: a new class of packet switch architecture with plural memory modules and decentralized control

Shared-memory based packet switches are known to provide the best possible throughput performance for bursty data traffic in high-speed packet networks and internets compared with other buffering strategies under conditions of identical memory resources deployed in the switch. However, scaling of shared-memory packet switches to a larger size has been restricted mainly due to the physical limitations imposed by the memory-access speed and the centralized control for switching functions in shared-memory switches. A new scalable architecture for a shared-memory packet switch, called the sliding-window (SW) switch, is proposed to overcome these limitations. The SW switch introduces a new class of switching architecture, where physically separate multiple memory modules are logically shared among all the ports of the switch, and the control is decentralized. The SW switch alleviates the bottleneck caused by the centralized control of switching functions in large shared-memory switches. Decentralized switching functions enable the SW switch to operate in a pipeline fashion to enhance scalability and switching capacity compared with that of previously known classes of shared-memory switch architecture.

Technical note—The IBM TotalStorage Enterprise Storage Server: Testing for general availability and beyond

The IBM TotalStorage™ Enterprise Storage Server® (ESS) is a powerful and versatile storage subsystem that can respond well to the explosion in demand for on-line data storage. ESS provides unique features in the areas of connectivity, capacity and performance scalability, data integrity, reliability, availability, and serviceability. This technical note discusses the stages of ESS hardware and software testing. Focus is then given to the collaboration, tools, and techniques needed for testing ESS software support provided specifically for the System/390® platform.

The WaveStar™ BandWidth Manager: The key building block in the next-generation transport network

The WaveStar™ BandWidth Manager (BWM) is Lucent Technologies' flagship product platform for providing bandwidth management within network nodes. It provides broadband (OC-3/12/48/192 and STM-1/4/16/64), asynchronous transfer mode (ATM), and Internet protocol (IP) bandwidth management within a highly-integrated, scalable, single network element. The WaveStar BWM's broadband synchronous transfer mode (STM) fabric scales from 1152 STS-1/384 STM-1 (60 Gb/s) to 9216 STS-1/3072 STM-1 (480 Gb/s) port capacity. With such a high range in capacity scalability across the broadband STM fabric, the BWM can be sized to meet most carriers' growth projections while protecting them from unforeseen growth within network nodes. The WaveStar BWM also addresses the growing need for enhanced bandwidth management capabilities within central offices. It integrates all access and transport facilities within a network node and efficiently manages bandwidth among these facilities via a cost-effective, scalable, multiservice switching architecture. The BWM facility interfaces, which feature integrated self-healing rings, eliminate the need for stand-alone add/drop multiplexer (ADM) ring terminals in the central office. Furthermore, the switching architecture, which includes an STM fabric as well as ATM and IP functionality, replaces the need for stand-alone broadband digital cross-connect systems (BDCSs) and ATM and IP core switches/routers. The WaveStar BWM also supports direct integration of Lucent's dense wavelength division multiplexing (DWDM) systems — the WaveStar optical line system (OLS) 400G and the WaveStar OLS 40G.

Design Principles for Machining System Configurations

Until recently, mass producers have relied on long serial lines of dedicated machines in order to machine products at high volumes. Today, as the cost of CNC machining centers decreases, more and more high-volume manufacturers are examining the alternative of shorter lines with more machines configured in parallel. This paper presents the main principles for selecting the right machining system configurations. We propose a system classification and show that only symmetric configurations are of interest to industry. We compare four classes of systems: pure serial lines, pure parallel lines, short serial lines arranged in parallel, and short serial lines arranged in parallel with the ability to move products between the lines (i.e., with crossover). Specifically, we compare the different configurations in terms of throughput, line balancing, machine investment cost, and capacity scalability. Finally, we introduce an upgradable multi-spindle reconfigurable machine as a cost-effective alternative for system scalability.

Failure-Atomic File Access in the Slice Interposed Network Storage System

This paper presents a recovery protocol for block I/O operations in Slice, a storage system architecture for high-speed LANs incorporating network-attached block storage. The goal of the Slice architecture is to provide a network file service with scalable bandwidth and capacity while preserving compatibility with off-the-shelf clients and file server appliances. The Slice prototype virtualizes the Network File System (NFS) protocol by interposing a request switching filter at the client's interface to the network storage system. The distributed Slice architecture separates functions typically combined in central file servers, introducing new challenges for failure atomicity. This paper presents a protocol for atomic file operations and recovery in the Slice architecture, and related support for reliable file storage using mirrored striping. Experimental results from the Slice prototype show that the protocol has low cost in the common case, allowing the system to deliver client file access bandwidths approaching gigabit-per-second network speeds.