Quality Of Service Prediction Research Articles

A location-aware hybrid web service QoS prediction algorithm

Quality-of-service (QoS) describes the non-functional characteristics of Web services. As such, the QoS is a critical parameter in service selection, composition and fault tolerance, and must be accurately determined by some type of QoS prediction method. However, with the dramatic increase in the number of Web services, the prediction failure caused by data sparseness has become a critical challenge. In this paper, a new hybrid user-location-aware prediction based on WAA (HUWAA) is proposed. The implicit neighbor search is optimized by incorporating location factors. Meanwhile, the ability of the improved algorithms to solve the data sparsity problem is validated in experiments on public real world datasets. The new algorithms outperform the existing IPCC, UPCC and WSRec algorithms.

Predicting Web Service QoS via Combining Matrix Factorization with Network Location

With the increasing abundance of Web Services across Internet, Quality of Service (QoS)based service recommendation has become a hot issue. It is necessary to predict the missing values of QoS for service recommendation. Because Web services run on the Internet, their network locations may be anther critical factor for QoS prediction. Although there have existed many works on QoS prediction, few consider the influence of the network locations of users or Web Services. In this paper, we propose a novel collaborative QoS prediction framework with network location-based regularization (NLBR). We first elaborate the popular Matrix Factorization (MF) model for missing values prediction. Then, by taking advantage of the local connectivity between Web services users, we incorporate network location information to identify the neighborhood. We conduct the experiments on a public large-scale real-world QoS dataset, Experiments show that our proposed approaches have the better prediction performance compared with the existed approaches.

A Novel Optimal Routing for Navigation Systems/Services Based on Global Navigation Satellite System Quality of Service

The positioning quality of global navigation satellite system (GNSS), or GNSS quality of service (QoS), is a major factor impacting real-time navigation performance. Commonly requested routes (i.e., shortest or fastest) may include areas with poor GNSS QoS, which can subsequently degrade navigation performance. To provide alternative routes with high or acceptable GNSS QoS along a route, a novel optimal routing for navigation systems/services based on GNSS QoS by utilizing integrated GNSS (iGNSS) QoS prediction is presented in this article. New routing criteria based on GNSS QoS are maximum availability, maximum accuracy, maximum continuity, and maximum reliability. Two experiments were conducted to compare GNSS QoS-based routes against shortest routes. In one experiment, routes were simulated, and in another, generated routes based on GNSS QoS were evaluated against GPS-based trajectories as ground truths. The results show that GNSS QoS-based routes provide routes with higher QoS, more than 50%, and longer, about 50%, than shortest routes.

CSCF: A Mashup Service Recommendation Approach based on Content Similarity and Collaborative Filtering

Lightweight Mashup service become very prevalent now since there are lots of advantages for them, such as easy use, short development time, and strong scalability. It is a challenge problem how to recommend user-interested, high-quality Mashup services to user with the rapid development of more and more Mashup service. In this paper, we propose CSCF (a Mashup service recommendation approach based on Content Similarity and Collaborative Filtering). CSCF firstly computes the content similarity between user history records and Mashup services and gets user interest value. Secondly, according to Mashup QoS(Quality of Service) invocation records of user, user similarity model and service similarity model are designed, and then get the QoS prediction value of active user to target service by using collaborative filtering. Finally, combining user interest value and QoS predictive value of Mashup service, CSCF ranks and recommends Mashup services to user. The experiments are performed with real Mashup services dataset, and the results of experiments show that CSCF can effectively recommends Mashup services to user with well-interesting, high-quality, better prediction precision.

QoS prediction for web service compositions using kernel-based quantile estimation with online adaptation of the constant offset

Services offered in a commercial context are expected to deliver certain levels of quality, typically contracted in a service level agreement (SLA) between the service provider and consumer. To prevent monetary penalties and loss of reputation by violating SLAs, it is important that the service provider can accurately estimate the Quality of Service (QoS) of all its provided (composite) services. This paper proposes a technique for predicting whether the execution of a service composition will be compliant with service level objectives (SLOs). We make three main contributions. First, we propose a simulation technique based on Petri nets to generate composite time series using monitored QoS data of its elementary services. This techniques preserves time related information and takes mutual dependencies between participating services into account. Second, we propose a kernel-based quantile estimator with online adaptation of the constant offset to predict future QoS values. The kernel-based quantile estimator is a powerful non-linear black-box regressor that (i) solves a convex optimization problem, (ii) is robust, and (iii) is consistent to the Bayes risk under rather weak assumptions. The online adaption guarantees that under certain assumptions the number of times the predicted value is worse than the actual value converges to the quantile value specified in the SLO. Third, we introduce two performance indicators for comparing different QoS prediction algorithms. Our validation in the context of two case studies shows that the proposed algorithms outperform existing approaches by drastically reducing the violation frequency of the SLA while maximizing the usage of the candidate services.

A time series and reduction‐based model for modeling and QoS prediction of service compositions

SUMMARYWeb services are emerging as a major technology for deploying automated interactions between distributed and heterogeneous applications. The accurate prediction of their quality of service (QoS) is important because their users rely on it to decide whether they meet the QoS requirement. The existing studies of QoS prediction usually assume that QoS of service activities follows certain distributions. These distributions are used as static model inputs into stochastic process models to obtain analytical QoS results. Instead, we consider the QoS activities to be fluctuating and introduce a dynamic framework to predict the runtime QoS by employing an Autoregressive Moving Average Model and QoS reduction rules. In the case study of a real‐world composite service sample, a comparison between existing approaches and the proposed one is presented, and results suggest that the proposed one achieves higher prediction accuracy.Copyright © 2014 John Wiley & Sons, Ltd.

Colbar: A collaborative location-based regularization framework for QoS prediction

Quality-of-Service (QoS) is a fundamental element in Service-Oriented Computing (SOC) domain. At the ongoing age of Web 2.0, predicting the missing QoS values becomes more and more important since it is an indispensable preprocess of numerous service-oriented applications. Previous research works on this task underestimate the importance of users’ geographical information, which we argue would contribute to improving prediction accuracy in Web services invocation process. In this paper, we propose a novel collaborative location-based regularization framework (Colbar) to address the problem of personalized QoS prediction. We first leverage the personal geographical and QoS information to identify robust neighborhoods. And then, we collect the wisdom of crowds to construct two location-based regularization terms, which are integrated to build up an unified Matrix Factorization framework. Finally we make intermediate fusions to generate better prediction results. The experimental analysis on a large-scale real-world QoS dataset shows that the prediction accuracy of Colbar outperforms other state-of-the-art approaches in various criteria.

Joint delay and energy model for IEEE 802.11 networks

Popularity of IEEE 802.11 networks has increased dramatically over the past number of years. Nowadays audio/video conferencing, gaming and other quality of service (QoS) sensitive services are being delivered to the end users over wireless. Commonly probability for a packet to overstay a specific timeout serves as a QoS metric, and obtaining media access control layer packet delay distribution is highly important for this QoS prediction. Usually wireless devices are equipped with energy supplies of limited capacity, and accurate estimation of their energy expenditure is essential from the network design point of view. Meanwhile, as packets of longer delay normally have higher energy transmission cost, there is a certain dependency between the two metrics. This paper considers internal structure of the metrics and proposes a mathematical model that allows obtaining their individual distributions together with the joint distribution. The model presents a random sum, where the summand formation is determined by a Terminating Markov Process. The model has been validated through comparison with results of NS3 simulation.

Collaborative Web Service QoS Prediction via Neighborhood Integrated Matrix Factorization

With the increasing presence and adoption of web services on the World Wide Web, the demand of efficient web service quality evaluation approaches is becoming unprecedentedly strong. To avoid the expensive and time-consuming web service invocations, this paper proposes a collaborative quality-of-service (QoS) prediction approach for web services by taking advantages of the past web service usage experiences of service users. We first apply the concept of user-collaboration for the web service QoS information sharing. Then, based on the collected QoS data, a neighborhood-integrated approach is designed for personalized web service QoS value prediction. To validate our approach, large-scale real-world experiments are conducted, which include 1,974,675 web service invocations from 339 service users on 5,825 real-world web services. The comprehensive experimental studies show that our proposed approach achieves higher prediction accuracy than other approaches. The public release of our web service QoS data set provides valuable real-world data for future research.

The Influence of Service Quality on Satisfaction: A Gender Comparison

The purpose of this paper was to examine (1) the role of gender in predicting service quality perceptions and (2) the relationship between quality perceptions and satisfaction. The findings of this study were based on the empirical analysis of a sample of 234 respondents. Fifty three percent of the respondents (n = 124) were males while forty seven percent of the respondents were females (n = 110). The result generally support the hypothesis that gender affects service quality perceptions and the relative importance attached to dimensions of service quality. The study also revealed that that tangibles, reliability and responsiveness were critical service quality dimensions for determining satisfaction of both male and female customers.

Radio Resource Management of Composite Wireless Networks: Predictive and Reactive Approaches

Recently, the IEEE 1900.4 standard specified a policy-based radio resource management (RRM) framework in which the decision making process is distributed between network-terminal entities. The standard facilitates the optimization of radio resource usage to improve the overall composite capacity and quality of service (QoS) of heterogeneous wireless access networks within a composite wireless network (CWN). Hence, the study of different RRM techniques to maintain either a load- or QoS-balanced system through dynamic load distribution across a CWN is pivotal. In this paper, we present and evaluate three primary RRM techniques from different aspects, spanning across predictive versus reactive to model-based versus measurement-based approaches. The first technique is a measurement-based predictive approach, known as predictive load balancing (PLB), commonly employed in the network-distributed RRM framework. The second technique is a model-based predictive approach, known as predictive QoS balancing (PQB), typically implemented in the network-centralized RRM framework. The third technique is a measurement-based reactive approach, known as reactive QoS balancing (RQB), anchored in the IEEE 1900.4 network-terminal distributed RRM framework. Comprehensive performance analysis between these three techniques shows that the IEEE 1900.4-based RQB algorithm yields the best improvement in QoS fairness and aggregate end-user throughput while preserving an attractive baseline QoS property.

Formal QoS Policy Based Grid Resource Provisioning Framework

Grid resource provisioning is a complex task that is often compromised due to non-availability of the desired resources. The heterogeneous and dynamic nature of the Grid resources depends on the Quality of Service (QoS) based resource provisioning for allocation of appropriate resources to Grid applications. Until resource provisioning is considered a fundamental capability, predictable QoS cannot be delivered to the Grid consumers. A resource provisioning policy based on QoS parameters is required for efficient Grid resource provisioning. In this paper a resource provisioning framework has been proposed. This framework offers resource provisioning policy that caters to provisioned resource allocation and resource scheduling. The policy rules have been specified in XML schema. The policy has been validated by Z Formal specification language and implementation has been demonstrated through a case study. The experimental results demonstrate that QoS based provisioned approach is effective in minimizing cost and submission burst time of applications in comparison to the existing approaches.

QoS Routing in Mobile Ad-hoc Networks using Agents

Quality of Service (QoS) provisioning in a Mobile Ad-hoc Network (MANETs) routing for multimedia traffic is a challenging task due to dynamic topology of such networks. Fuzzy Logic (FL) were used for QoS prediction from current uncertain QoS constraints in the network for particular applications, from these uncertain constraints there is an error at the QoS prediction. To overcome this error, we proposed an intelligent system called ”Neuro-Fuzzy” (NF) system. Our proposed scheme optimizes the uncertain weights before QoS prediction using Error Back Propagation (EBP) algorithm, this optimization is done till to get acceptable error limit. From these optimized weights we can predict more accurately and hence, we can provide the well quality of service to the user. And also to provide real-time communication in MANETs, we used software agents.

A QoS-enabled resource management scheme for F-HMIPv6 micro mobility approach

In the near future, wireless networks will certainly run real-time applications with special Quality of Service (QoS) requirements. In this context micro mobility management schemes such as Fast Handovers over Hierarchical Mobile IPv6 (F-HMIPv6) will be a useful tool in reducing Mobile IPv6 (MIPv6) handover disruption and thereby to improve delay and losses. However, F-HMIPv6 alone does not support QoS requirements for real-time applications. Therefore, in order to accomplish this goal, a novel resource management scheme for the Differentiated Services (DiffServ) QoS model is proposed to be used as an add-on to F-HMIPv6. The new resource management scheme combines the F-HMIPv6 functionalities with the DiffServ QoS model and with network congestion control and dynamic reallocation mechanisms in order to accommodate different QoS traffic requirements. This new scheme based on a Measurement-Based Admission Control (MBAC) algorithm is effective, simple, scalable and avoids the well known traditional resource reservation issues such as state maintenance, signaling overhead and processing load. By means of the admission evaluation of new flows and handover flows, it is able to provide the desired QoS requirements for new flows while preserving the QoS of existing ones. The evaluated results show that all QoS metrics analyzed were significantly improved with the new architecture indicating that it is able to provide a highly predictive QoS support to F-HMIPv6.

A tractable approximation approach to improving hotel service quality

Typically, the service quality in the hotel industry is analyzed using cross-sectional empirical studies. For example, to examine current causal relationships among various latent and manifest variables using structural equation modeling plays a key role in understanding how services are provided at a given hotel. Note that accurate prediction of service quality certainly helps decision-makers better manage their services operations to sustain quality services to meet the ever-changing needs of customers. In this paper, by integrating continued fraction interpolation theory and genetic algorithms, an innovative service quality prediction model in the hotel industry is presented. An illustrative example is provided, which essentially shows the applicability of this proposed innovative methodology.

AWPP: A New Scheme for Wireless Access Control Proportional to Traffic Priority and Rate

Cutting-edge wireless networking approaches are required to efficiently differentiate traffic and handle it according to its special characteristics. The current Medium Access Control (MAC) scheme which is expected to be sufficiently supported by well-known networking vendors comes from the IEEE 802.11e workgroup. The standardized solution is the Hybrid Coordination Function (HCF), that includes the mandatory Enhanced Distributed Channel Access (EDCA) protocol and the optional Hybrid Control Channel Access (HCCA) protocol. These two protocols greatly differ in nature and they both have significant limitations. The objective of this work is the development of a high-performance MAC scheme for wireless networks, capable of providing predictable Quality of Service (QoS) via an efficient traffic differentiation algorithm in proportion to the traffic priority and generation rate. The proposed Adaptive Weighted and Prioritized Polling (AWPP) protocol is analyzed, and its superior deterministic operation is revealed.

A heuristic adaptive QoS prediction scheme in single-hop passive star coupled WDM optical networks

In this paper, a novel quality of service (QoS) prediction framework is proposed to accommodate different applications with various QoS requirements. The purpose of the proposed structure is to estimate, given the QoS requirements of different applications, the number of them can be satisfied according to the predefined QoS level and the number of them have to be rejected or accepted under lower level. Moreover, this structure is able to control the network behavior when the new application with certain QoS requirements requesting for the connection. The framework consists of four modules. QoS Requirements Monitoring detects the changes in the supplied QoS. QoS Prediction performs at real-time to estimate whether the new QoS can be adapted to the current QoS. QoS Violation is dedicated to detect the violation. And a module of QoS Estimation is used to make the decision whether the hopeless new traffic is refused or accepted with acceptable QoS requirements. Therefore, this structure is able to control network behavior when the surrounding environment changes. Numerical and simulation results obtained suggest that the proposed predictive scheme is a promising approach for real time QoS prediction.

Web Service QoS Prediction Approach

服务消费者在选择服务之前,通常需要基于其他消费者的经验对未使用过的服务的质量进行预测.考虑到不同服务消费者对同一服务的服务质量的感受之间可能存在较大的差别,提出了一种QoS(quality of service)预测方法.该方法以消费者的历史经验为基础,计算消费者之间以及服务之间的相似程度,并以此相似度为基础对消费者并未使用过的服务的QoS进行预测.实验结果表明,这种方法可以显著提高Web服务质量预测的准确性.;Consumers need to make prediction on the quality of unused Web services before selecting. Usually, this prediction is made based on other consumers’ experiences. Being aware of different QoS (quality of service) experiences of consumers, this paper proposes a QoS prediction approach. This approach makes similarity mining among consumers and QoS data, and then predicts the QoS of the unused Web services from other consumers’ experiences. Experimental results show that with this approach the preciseness of QoS prediction for Web services can be improved significantly.

DRACON: QoS Management for Large-Scale Distributed Real-Time Databases

The demand for real-time data services is increasing in many large-scale distributed real-time applications including advanced traffic control, global environment control, and the nation-wide electric power grid control. However, providing quality-of-service (QoS) for data services in such large-scale and geographically distributed environment is a challenging task. In particular, both unpredictable communicational delays and computational workloads of large-scale distributed systems can lead to large number of deadline misses. We have designed a distributed real-time database architecture called DRACON (Decentralized data Replication And CONtrol), which enables QoS guarantees for large-scale distributed real-time applications. DRACON couples cluster-based replica-sharing and a decentralized control structure to address communication and computational unpredictability, simultaneously. The cluster-based replica-sharing mechanism not only enables scalable and bounded-delay access to remote data with high probability, but also decouples clusters to have less interaction, allowing a decentralized, thus scalable, QoS control structure. The simulation study demonstrates that DRACON’s decentralized QoS control structure combined with a decentralized replica-sharing structure provides robust and predictable QoS guarantees in a highly scalable manner.

A predictive admission control algorithm for user advance reservation in equipment grid

In a service computing world, a user submits job requests to an equipment grid which often has quality of service (QoS) requirements. The advance reservations of equipment grid are used to satisfy such requirements. Due to the dynamic behaviours and fluctuations of resources in equipment grid, some accepted advance reservations are not able to be fulfilled in different contexts. Therefore, we propose a predictive admission control algorithm to decide whether the new advance reservation requests can be accepted according to their QoS requirements and prediction of future resource utilisation. Historical data are used in this algorithm to predict future status of resources in the equipment grid. The simulation experiments demonstrate that our algorithm can reduce the number of accepted advance reservations that fail to be fulfilled, and can keep the resource utilisation ratio at an acceptable level.