The sharing of caches among Web proxies is an important technique to reduce Web traffic and alleviate network bottlenecks. Nevertheless it is not widely deployed due to the overhead of existing protocols. In this paper we demonstrate the benefits of cache sharing, measure the overhead of the existing protocols, and propose a new protocol called "summary cache". In this new protocol, each proxy keeps a summary of the cache directory of each participating proxy, and checks these summaries for potential hits before sending any queries. Two factors contribute to our protocol's low overhead: the summaries are updated only periodically, and the directory representations are very economical, as low as 8 bits per entry. Using trace-driven simulations and a prototype implementation, we show that, compared to existing protocols such as the Internet cache protocol (ICP), summary cache reduces the number of intercache protocol messages by a factor of 25 to 60, reduces the bandwidth consumption by over 50%, eliminates 30% to 95% of the protocol CPU overhead, all while maintaining almost the same cache hit ratios as ICP. Hence summary cache scales to a large number of proxies. (This paper is a revision of Fan et al. 1998; we add more data and analysis in this version.).

Summary cache: a scalable wide-area web cache sharing protocol

The invention provides a method and system for creating an innovative file system that separates its directory presentation from its data store. The method and system include processing, division, distribution, managing, synchronizing, and reassembling of file system objects that does not delay the presentation of the content to the user, but also uses a reduced amount of storage space. The invention includes the ability to manage and control the integrity of the files distributed across the network, and the ability to serve and reconstruct files in real time using a Virtual File Control System.

Method and system for managing distributed content and related metadata

Web caches can not only reduce network traffic and downloading latency, but can also affect the distribution of web traffic over the network through cost-aware caching. This paper introduces GreedyDual-Size, which incorporates locality with cost and size concerns in a simple and non-parameterized fashion for high performance. Trace-driven simulations show that with the appropriate cost definition, GreedyDual-Size outperforms existing web cache replacement algorithms in many aspects, including hit ratios, latency reduction and network cost reduction. In addition, GreedyDual-Size can potentially improve the performance of main-memory caching of Web documents.

/pdf/cost-aware-www-proxy-caching-algorithms-234kttt5bt.pdf

Cost-aware WWW proxy caching algorithms

In recent decades, health care costs have dramatically increased, while health care organisations have been under severe pressure to provide improved quality health care for their patients. Several health care administrators have used discrete-event simulation as an effective tool for allocating scarce resources to improve patient flow, while minimising health care delivery costs and increasing patient satisfaction. The rapid growth in simulation software technology has created numerous new application opportunities, including more sophisticated implementations, as well as combining optimisation and simulation for complex integrated facilities. This paper surveys the application of discrete-event simulation modeling to health care clinics and systems of clinics (for example, hospitals, outpatient clinics, emergency departments, and pharmacies). Future directions of research and applications are also discussed.

https://link.springer.com/content/pdf/10.1057%2Fpalgrave.jors.2600669.pdf

Application of discrete-event simulation in health care clinics: A survey

This paper presents a workload characterization study for Internet Web servers. Six different data sets are used in the study: three from academic environments, two from scientific research organizations, and one from a commercial Internet provider. These data sets represent three different orders of magnitude in server activity, and two different orders of magnitude in time duration, ranging from one week of activity to one year. The workload characterization focuses on the document type distribution, the document size distribution, the document referencing behavior, and the geographic distribution of server requests. Throughout the study, emphasis is placed on finding workload characteristics that are common to all the data sets studied. Ten such characteristics are identified. The paper concludes with a discussion of caching and performance issues, using the observed workload characteristics to suggest performance enhancements that seem promising for Internet Web servers.

/pdf/internet-web-servers-workload-characterization-and-3i6ufipgvw.pdf

Internet Web servers: workload characterization and performance implications

The authors describe an integrated simulation modeling environment (ISME) which utilizes an information-based approach for the description of manufacturing systems. Manufacturing systems are described as a higher level aggregation of the objects in the system. Such a description is stored in a relational database. Models are later synthesized from the description of the system. Experimental conditions are input to guide the analysis. >

Modeling manufacturing systems: an information-based approach

A combined discrete/continuous simulation model of the primary health care system of Indiana has been developed and implemented in the GASP IV simulation language. The purpose of this model is to project the supply of and demand for primary health care in Indiana from 1970 through 2000. The model has been developed to evaluate the need for additional primary care supply in Indiana, and to assess the effect of exogenous policy changes on performance measures of the Indiana primary health care system. This paper describes the model and its use, however, an emphasis is placed on the data collection aspects of model building.The data to support the model was obtained from many sources. Extensive problems existed in converting the data to a consistent basis. A description of the data sources, the data reduction requirements and the parameter estimation procedures are included in the paper.The primary health care system of Indiana is modeled as having four major components: 1. the providers of primary care; 2. the volume of services of the providers; 3. the population of Indiana; and 4. the volume of services the population demands.Model outputs involved the projection of the four components over time. In working with health man-power policy-makers, it was determined that the following two performance measures were of significant interest:1. Ratio of the supply of visits to the demand for visits.2. A normalized difference between the supply of visits and the demand for visits.

A simulation model of the primary health care system of Indiana

New tools simplify the development and simulation of models as well as the analysis and presentation of simulation results. The SLAM language allows the modeler to use network, dis crete event and continuous modeling prospectives in any combination to describe the different parts of a system. The SDL database management system allows the modeler to col lect simulation results, and at the same time to analyze and present these results independent of the simulation run.We applied SLAM and SDL in analyzing a package of experi ments for the Space Shuttle. The SLAM model of the experi mental package shows the utility of a combined network, discrete event, and continuous model. The SDL database illustrates the advantages of storing model run results, using the computer in comparing alternatives, defining and comput ing performance measures after simulation results are made, and generating reports and plots of model results in the data base.The results of our analysis were also of interest. Only a limited amount...

Using SLAM and SDL to assess space shuttle experiments

This paper discusses the effect of the use of SDLTM database management capabilities on the modeling and analysis procedures employed in studying two health care delivery systems: the use of capitation reimbursement in the Iowa Medicaid drug program and the availability of primary care in Indiana. Emphasis is placed on the construction and organization of databases from data produced by running simulation models. This data can then be used to compute measures of performance independently of the running of models. Furthermore, the decomposition of a large, complex model into a set of smaller, less complex component models is discussed. In addition, the assessment of alternatives and the iterative definition and computation of performance measures are described.

Enhancing simulation analyses of health care delivery policies using SDLTM database capabilities

Purpose: Few studies comparing manufacturing control systems as they relate to high-mix, low-volume applications have been reported. This paper compares two strategies, constant work in process (CONWIP) and Paired-cell Overlapping Loops of Cards with Authorization (POLCA), for controlling work in process (WIP) in such a manufacturing environment. Characteristics of each control method are explained in regards to lead time impact and thus, why one may be advantageous over the other. Design/methodology/approach: An industrial system in the Photonics industry is studied. Discrete event simulation is used as the primary tool to compare performance of CONWIP and POLCA controls for the same WIP level with respect to lead time. Model verification and validation are accomplished by comparing historic data to simulation generated data including utilizations. Both deterministic and Poisson distributed order arrivals are considered.  Findings: For the system considered in this case study, including order arrival patterns, a POLCA control can outperform a CONWIP parameter in terms of average lead time for a given level of WIP. At higher levels of WIP, the performance of POLCA and CONWIP is equivalent.  Practical Implications: The POLCA control helps limit WIP in specific areas of the system where the CONWIP control only limits the overall WIP in the system. Thus, POLCA can generate acceptably low lead times at lower levels of WIP for conditions equivalent to the HMLV manufacturing systems studied. Originality/value: The study compliments and extends previous studies of  CONWIP and POLCA performance to a HMLV manufacturing environment. It demonstrates the utility of discrete event simulation in that regard. It shows that proper inventory controls in bottleneck areas of a system can reduce average lead time.

/pdf/conwip-versus-polca-a-comparative-analysis-in-a-high-mix-low-1yfj0qv62y.pdf

Charles R. Standridge

Papers

Modeling manufacturing systems: an information-based approach

A simulation model of the primary health care system of Indiana

Using SLAM and SDL to assess space shuttle experiments

Enhancing simulation analyses of health care delivery policies using SDLTM database capabilities

CONWIP versus POLCA: A comparative analysis in a high-mix, low-volume (HMLV) manufacturing environment