Analysis and control of correlated web server queues

Analysis of queueing model with processor sharing discipline and customers impatience

We propose an enhancement to the parametric-decomposition method for calculating approximate steady-state performance measures of open queueing networks with non-Poisson arrival processes and nonexponential service-time distributions. Instead of using a variability parameter ca2 for each arrival process, we suggest using a variability function ca2ρ, 0 < ρ < 1, for each arrival process i.e, the variability parameter should be regarded as a function of the traffic intensity ρ of a queue to which the arrival process might go. Variability functions provide a convenient representation of different levels of variability in different time scales for arrival processes that are not nearly renewal processes. Variability functions enable the approximations to account for long-range effects in queueing networks that cannot be addressed by variability parameters. For example, the variability functions provide a way to address the heavy-traffic bottleneck phenomenon, in which exceptional variability (either high or low) in the input has little impact in a series of queues with low-to-moderate traffic intensities, and then has a big impact when it reaches a later queue with a relatively high traffic intensity. The variability functions also enable the approximations to characterize irregular periodic deterministic external arrival processes in a reasonable way; i.e., if there are no batches, then ca2ρ should be 0 for ρ near 0 or 1, but ca2ρ can assume arbitrarily large values for appropriate intermediate ρ. We present a full network algorithm with variability functions, showing that the idea is implementable. We also show how simulations of single queues can be effectively exploited to determine variability functions for difficult external arrival processes.

short-paper Share on Tail asymptotics of the stationary distribution for a two-node generalized Jackson network Author: Masakiyo Miyazawa Tokyo University of Science, Noda, Chiba, Japan Tokyo University of Science, Noda, Chiba, JapanView Profile Authors Info & Claims ACM SIGMETRICS Performance Evaluation ReviewVolume 42Issue 2September 2014pp 70–72https://doi.org/10.1145/2667522.2667545Published:04 September 2014Publication History 1citation26DownloadsMetricsTotal Citations1Total Downloads26Last 12 Months0Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Anomaly detection in web server environments is essential for identifying early indicators of cyberattacks that arise from abnormal request behaviors. Traditional signature-based mechanisms often fail to detect emerging or obfuscated threats, requiring more adaptive analytical approaches. This study proposes an optimized anomaly detection model using K-Means clustering enhanced with engineered security-rule features and the Elbow Method. Two datasets were used: a small dataset of 3,399 log entries from one VPS and a large dataset of 223,554 entries collected from three VPS nodes, all sourced from local production servers of the Department of Computer and Business, Politeknik Negeri Cilacap. The preprocessing pipeline includes timestamp normalization, removal of non-informative static resources, numerical feature scaling, and TF-IDF encoding of URL paths. Domain-driven security features entropy scores, encoded-payload indicators, abnormal status-code ratios, and request-rate deviations were integrated to improve anomaly separability. Experiments across five model configurations show that combining larger datasets with rule-based features significantly enhances clustering performance, achieving a Silhouette Score of 0.9136 and a Davies–Bouldin Index of 0.4712. The results validate the effectiveness of incorporating security-rule engineering with unsupervised learning to support early-warning threat detection in web server environments.

Institutions such as banks, airlines, hospitals and telecommunication industries employ queuing theory to help in assisting the capacity levels needed to experience demand in a more optimized way for service improvement. In this article, we studied and employed the queuing theory activities of the Federal University Gusau Health Services Clinic. The distributions of patients’ arrival and service times were identified. The system was treated as a single, time-independent arrival with multiple service points. Based on the data obtained on the arrival and service processes, appropriate distributions were fitted and tested using the Chi-squared goodness of fit-test.

Motivated by a container storage problem at seaports, this paper examines the infinite-server queueing model with a (second order) stationary but arbitrarily correlated arrival process. It starts with a description of the application context, including an explanation of why non-standard inputs and service times arise in certain container storage problems. As further illustration, formulas characterizing the input and service processes for a particular situation are then presented and justified, together with the simple container accumulation variance formula that follows from the general results derived later. The paper then describes the general results. After reviewing the properties of a general arrival process, and based on minimal assumptions, it presents exact expressions for the variance of the number of customers in the system. (The expression for the mean is already well known.) Expressions are first derived for general independent service times and then for more general service processes that are of importance in port applications.

This paper investigates a queuing system with infinite number of servers where the arrival process is given by a Markov Arrival Process (MAP) and the service time follows a Phase-type (PH) distribution. They were chosen since they are simple enough to describe the model by exact methods. Moreover, highly correlated arrival processes and heavy-tailed service time distributions can be approximated by these tools on a wide range of time-scales. The transient behaviour of the system is analysed and the time-dependent moments of the queue length is computed explicitly by solving a set of differential equations. The results can be applied to models where performance of parallel processing is important. The applicability of the model is illustrated by dimensioning a WEB-based content provider.

Average waiting times in queuing models are generally computed with the assumption that the arrival and service processes are independent and not related. In many applications and especially in queues with scheduled batch service times, this assumption is not valid and a formulation which relates the two processes is required. This paper proposes a model aimed at analyzing and exploiting the relationship between the arrival and service processes with emphasis on the impact of this relationship on average waiting times. The presentation is made in the context of a transportation model to motivate and validate the basic assumptions.

A new timeliness metric, called Age-of-Information (AoI), has recently attracted a lot of research interests for real-time applications with information updates. It has been extensively studied for various queueing models based on the probabilistic approaches, where the analyses heavily depend on the properties of specific distributions (e.g., the memoryless property of the exponential distribution or the i.i.d. assumption). In this work, we take an alternative new approach, the robust queueing approach, to analyze the Peak Age-of-Information (PAoI). Specifically, we first model the uncertainty in the stochastic arrival and service processes using uncertainty sets. This enables us to approximate the expected PAoI performance for very general arrival and service processes, including those exhibiting heavy-tailed behaviors or correlations, where traditional probabilistic approaches cannot be applied. We then derive a new bound on the PAoI in the single-source single-server setting. Furthermore, we generalize our analysis to two-source single-server systems with symmetric arrivals, which involves new challenges (e.g., the service times of the updates from two sources are coupled in one single uncertainty set). Finally, through numerical experiments, we show that our new bounds provide a good approximation for the expected PAoI. Compared to some well-known bounds in the literature (e.g., one based on Kingman's bound under the i.i.d. assumption) that tends to be inaccurate under light load, our new approximation is accurate under both light and high loads, both of which are critical scenarios for the AoI performance.

We propose an alternative approach for studying queues based on robust optimization. We model the uncertainty in the arrivals and services via polyhedral uncertainty sets, which are inspired from the limit laws of probability. Using the generalized central limit theorem, this framework allows us to model heavy-tailed behavior characterized by bursts of rapidly occurring arrivals and long service times. We take a worst-case approach and obtain closed-form upper bounds on the system time in a multi-server queue. These expressions provide qualitative insights that mirror the conclusions obtained in the probabilistic setting for light-tailed arrivals and services and generalize them to the case of heavy-tailed behavior. We also develop a calculus for analyzing a network of queues based on the following key principles: (a) the departure from a queue, (b) the superposition, and (c) the thinning of arrival processes have the same uncertainty set representation as the original arrival processes. The proposed approach (a) yields results with error percentages in single digits relative to simulation, and (b) is to a large extent insensitive to the number of servers per queue, network size, degree of feedback, and traffic intensity; it is somewhat sensitive to the degree of diversity of external arrival distributions in the network.

Users of Web and grid services often must temporarily delegate some or all of their rights to a software entity to perform actions on their behalf. The problem with the typical grid services approach (X. 509 proxy certificates) is that commercial Web services tooling fails to recognize these certificates or process them properly. The security assertion markup language (SAML) is a standardized XML-based framework for exchanging authentication, authorization and attribute information. SAML has broadening commercial support but lacks delegation capabilities. To address this shortcoming, we exploit SAML's inherent extensibility to create a delegation framework for Web and grid services that supports both direct and indirect delegation. We develop a set of verification rules for delegation tokens that rely on WS-Security X.509 signatures, but do not force any trust relationship between the delegatee and the target service. We have implemented the framework on two common Web service hosting environments: Java/Tomcat and .NET. By leveraging existing Web services standards, we make it easier for Grid practitioners to build and consume Web and grid services without resorting to grid-specific protocols.

The purpose of this paper is to present a framework from which Automated Test Equipment (ATE) manufacturers can use to help them develop, integrate, and deliver ATE cloud-based applications to the consumers of their products. In order to create these applications, the developer can utilize Commercial Web Services (CWS) as a means to help access compute power, storage devices, and other services that provide the flexibility to choose a development platform or programming model that makes the most sense in trying to resolve the problem at hand. CWS provides a flexible environment from which to choose various programming models, operating systems, databases, and architectures to serve the consumers needs. CWS is highly cost-effective in that the developers and consumers pay only for what they use. Using CWS makes it extremely easy to create scalable and elastic systems as the developers can quickly add and subtract resources to their applications in order to meet current or future consumer needs. Furthermore, security is always a concern so CWS builds services in accordance with security best practices by providing the appropriate security features in those services. Using a CWS provides a level of scale, security, reliability, and privacy that are often cost prohibitive for most organizations to meet. This paper will examine available CWS cloud service platforms that organizations can potentially use to help deploy applications and services in a cost effective manner. The CWS platform consists of the following six main services, which will be discussed in more detail in this paper - (1) Computational/Networking, (2) Storage/Content Delivery, (3) Databases, (4) Analytics, (5) Applications, and (6) Deployment and Management services. One or more of these services may be utilized to help develop, integrate, and deliver ATE cloud-based applications to the consumer. The goals of ATE are to (1) quickly and accurately detect and isolate each fault, (2) provide software tools for analyzing historical data, (3) gather, manage, and distribute accurate and reliable maintenance information for the failed Unit Under Test (UUT). The CWS cloud platform will aid in the development of cloud based tools and applications that are cost effective, flexible, scalable, and secure that can be used by multiple end users to aid in the development of ATE system software tool sets. One example of a cloud-based application is a diagnostic reasoner that could be used to aid in diagnosing UUT repair actions. This paper will show how developers can use CWS to develop ATE cloud-based applications and tools that will help improve the overall ATE testing throughput, thus resulting in bottom line improvements to ATE life cycle costs.

This paper presents a more general class of MAP/MAP/1 exhaustive vacation queue, in which the Markov modulated arrival and service processes are dependent. This model class requires the evaluation of the busy period of quasi birth death process with arbitrary initial level, which is a new analysis element.

The analysis of system performance measures is fairly simple if there is only one or several channels with identical service times and arranged in parallel with exponentially distributed inter arrival time of packets and service time. However, heterogeneous multiple channels often occur in practice and here the channels have different service times. It is therefore useful to be able to calculate the performance measures of such systems. We shall take an exact analytical model of the asymmetric data network node and assume that the arrival process is Poisson of two priority flows with different rates and two channels with different service times distributed exponentially and in case with determine service time. In symmetric queuing systems, the response time depends only on whether an arrival message finds some free channel. An asymmetric multiple channel system differs since which of the channels processes the message. It is very important to take analysis of different strategies for selecting a free channel. In a system with heavy traffic there is usually all channels are occupied and therefore a channel selection strategy is not so efficient. The transmission order is from high-priority packet to low-priority packet. Two priority packets queues share a limited size single buffer. The each priority packet is dropped if the queue length exceeds a capacity of buffer. Network node performance measures such as packet losses, packet delay, channel utilization are evaluated by means of analytical and simulation models. Some calculated system performance measures results are presented in figures.

This paper considers a single server queue in which the service time is exponentially distributed and the service station may breakdown according to a Poisson process with the rates γ and γ' in busy period and idle period respectively. Repair will be performed immediately following a breakdown. The repair time is assumed to have an exponential distribution. Let g(t) and G(t) be the probability density function and the cumulative distribution function of the interarrival time respectively. When t tends to infinity, the rate of g(t)/[1 – G(t)] will tend to a constant. A set of equations will be derived for the probabilities of the queue length and the states of the arrival, repair and service processes when the queue is in a stationary state. By solving these equations, numerical results for the stationary queue length distribution can be obtained.