Real-world Quality Of Service Data Research Articles

A Personalized Federated Tensor Factorization Framework for Distributed IoT Services QoS Prediction From Heterogeneous Data

With a growing number of alternative Internet of Things (IoT) services that provide the same functionalities, Quality-of-Service (QoS) prediction has become an important research issue. Conventional central methods require that the historical QoS data is centralized. While the QoS data may be distributed in different edge servers. Due to privacy, these edge servers may not be willing to share their data with others for a better model representation. Besides, as each edge server is in charge of the collecting QoS data from the users in a specific area, the QoS data are likely to be heterogeneous. In this article, we propose a personalized federated tensor factorization framework for distributed privacy-preserving IoT services QoS prediction. We first adopt tensors to represent the QoS data with multidimensions and initialize a personalized model for each edge server. Then, each edge server performs local tensor factorization and exchanges the public component with a parameter master. By constraining the consistency of the global public component and the local personalized public components, the global model can learn information from edge servers during the training process. In addition, we conduct extensive experiments on a real-world QoS data set, the experimental results demonstrate that the proposed framework is efficient and effective.

BOOST: A novel algorithm Based On m Odified preference function and weight factor for ranking of cloud Services efficien Tly

In the present scenario, building the best quality cloud computing applications that fulfill demand services of customers is the toughest challenge for researchers. The services which perform the non-functional activities are considered as Quality of Service (QoS). Many sectors offer various cloud services such as Amazon, HP, and IBM to the customers. No technique is available to measure the real-world usage accurately and provide the efficient results for ranking the cloud services. Therefore, it is a very hard job for the client to select the optimal cloud service provider (CSP), which fulfills all the requirements of the customers. To avoid the conflict for selecting the right CSP, this paper proposes a novel QoS ranking prediction method called BOOST. Various experiments are done on the real-world QoS data by using EC2 services of Amazon. The results reveal that the proposed BOOST provides more efficient results than the competitor approaches.

An analysis of QoS ranking prediction framework techniques

In the real world, building the high quality cloud computing framework is the challenge for the researcher in the present scenario where on demand service is required. The services which are performing the non-functional activities are referred to as Quality-of Service (QoS). The experience of real-world usage services are generally required to obtain the QoS. Many organizations offer various cloud services, such as Amazon, HP and IBM, to the customers. No technique is available to measure the real-world usage and estimate the ranking of the cloud services. From the customer side, it is a very tough job to choose the right cloud service provider (SP), which fulfills all the requirements of the customers. To avoid the confusion to select the right CSP, this paper proposes QoS ranking prediction methods such as Cloud Rank1, Cloud Rank2 and Cloud Rank3. Various experiments are done on the real-world QoS data by using EC2 services of Amazon and providing healthy results and solutions.

A Factorization Machine-Based QoS Prediction Approach for Mobile Service Selection

Mobile services allow us to access the abundant and various resources (including data and services) on the Internet or devices in the physical world via wireless network technologies. It becomes increasingly popular to create mobile applications by combining existing mobile services. Mobile service selection is an important issue since different services with equivalent functions may have quite different qualities (e.g., performance). Even the same service may present different performances due to the volatility of mobile environments and move of users. Hence, getting aware of the quality of mobile services is a crucial need in service selection. To meet this need, a dozen of quality-of-service (QoS) prediction approaches have been proposed for traditional Web services and mobile services. However, their prediction accuracy and time efficiency still have plenty of room for improvement. This paper proposes a collaborative filtering approach to predict the QoS of mobile services based on factorization machines. Factorization machines significantly improve the traditional collaborative filtering techniques in both accuracy and time efficiency. The proposed approach revamps the classic factorization machine model by incorporating the locations of service users to better fit the mobile environments. The experimental results based on real-world QoS data show that the proposed approach outperforms the other collaborative filtering approaches.

Search based approach to forecasting QoS attributes of web services using genetic programming

ContextCurrently, many service operations performed in service-oriented software engineering (SOSE) such as service composition and discovery depend heavily on Quality of Service (QoS). Due to factors such as varying loads, the real value of some dynamic QoS attributes (e.g., response time and availability) changes over time. However, most of the existing QoS-based studies and approaches do not consider such changes; instead, they are assumed to rely on the unrealistic and static QoS information provided by service providers, which may seriously impair their outcomes. ObjectiveTo predict dynamic QoS values, the objective is to devise an approach that can generate a predictor to perform QoS forecasting based on past QoS observations. MethodWe use genetic programming (GP), which is a type of evolutionary computing used in search-based software engineering (SBSE), to forecast the QoS attributes of web services. In our proposed approach, GP is used to search and evolve expression-based, one-step-ahead QoS predictors. To evaluate the performance (accuracy) of our GP-based approach, we also implement most current time series forecasting methods; a comparison between our approach and these other methods is discussed in the context of real-world QoS data. ResultsCompared with common time series forecasting methods, our approach is found to be the most suitable and stable solution for the defined QoS forecasting problem. In addition to the numerical results of the experiments, we also analyze and provide detailed descriptions of the advantages and benefits of using GP to perform QoS forecasting. Additionally, possible validity threats using the GP approach and its validity for SBSE are discussed and evaluated. ConclusionsThis paper thoroughly and completely demonstrates that under a realistic situation (with real-world QoS data), the proposed GP-based QoS forecasting approach provides effective, efficient, and accurate forecasting and can be considered as an instance of SBSE.

Web service QoS prediction by neighbor information combined non-negative matrix factorization

Strongly promoted by the development of Service-Oriented Computing and Cloud Computing technologies, a large number of functionally equivalent web services emerge on the Internet. Quality of Service (QoS) is becoming a key factor to distinguish different web services. Although many Collaborative Filtering (CF) based approaches are recently proposed to predict the QoS of web services, the prediction accuracy are not satisfactory, since they rarely take full use of the neighbor information and latent feature information contained in the historical QoS data. Especially when the realworld QoS data is highly sparse, the previous works fail to detect the actual relationships between services. In this paper, we present a novel hybrid web service QoS prediction approach that systematically combines the memory-based CF and model-based CF. Firstly a non-negative matrix factorization model for web service QoS prediction is presented. Then an Expectation-Maximization (EM) based approach is designed to learn the model for making further prediction. The service neighbor information, which integrates the direct similarity and transitive indirect similarity of services to handle the data sparsity problem, is introduced into EM based learning process to make the prediction results more accurate. Large-scale real-world experiments are conducted using the WSDREAM QoS dataset. The experimental results demonstrate that our approach can achieve better prediction accuracy than other state-of-the-art approaches.

Search-based QoS ranking prediction for web services in cloud environments

Unlike traditional quality of service (QoS) value prediction, QoS ranking prediction examines the order of services under consideration for a particular user. To address this NP-Complete problem, greedy strategy-based solutions, such as CloudRank algorithm, have been widely adopted. However, they can only produce locally approximate solutions. In this paper, we propose a search-based prediction framework to address the QoS ranking problem. The traditional particle swarm optimization (PSO) algorithm has been adapted to optimize the order of services according to their QoS records. In real situations, QoS records for a given consumer are often incomplete, so the related data from close neighbour users is often used to determine preference relations among services. In order to filter the neighbours for a specific user, we present an improved method for measuring the similarity between two users by considering the occurrence probability of service pairs. Based on the similarity computation, the top-k neighbours are selected to provide QoS information support for evaluation of the service ranking. A fitness function for an ordered service sequence is defined to guide search algorithm to find high-quality ranking results, and some additional strategies, such as initial solution selection and trap escaping, are also presented. To validate the effectiveness of our proposed solution, experimental studies have been performed on real-world QoS data, the results from which show that our PSO-based approach has a better ranking for services than that computed by the existing CloudRank algorithm, and that the improvement is statistically significant, in most cases.

Efficient web service QoS prediction using local neighborhood matrix factorization

In the era of Big Data, companies worldwide are actively deploying web services in both intranet and internet environments. Quality-of-Service (QoS), the fundamental aspect of web service has thus attracted numerous attention in industry and academia. The study on sufficient QoS data keeps advancing the state in Service-Oriented Computing (SOC) area. To collect a large amount of resource in practice, QoS prediction applications are designed and built. Nevertheless, how to generate accurate results in high productivity is still a main challenge to existing frameworks. In this paper, we propose LoNMF, a Local Neighborhood Matrix Factorization application that incorporates domain knowledge in modern Artificial Intelligence (AI) technique to tackle this challenge. LoNMF first proposes a two-level selection mechanism that can identify a set of highly relevant local neighbors for target user. And then, it integrates the geographical information to build up an extended Matrix Factorization (MF) approach for personalized QoS prediction. Finally, it iteratively generates results by utilizing hints from previous round computations, a gradient boosting strategy that directly accelerates solving process. Experimental evidence on large-scale real-world QoS data shows that LoNMF is scalable, and consistently outperforming other state-of-the-art applications in prediction accuracy and efficiency.

PHAT: A Preference and Honesty Aware Trust Model for Web Services

Trust is one of the most critical factors for a service requestor when selecting a service from a large pool of candidate services. However, existing web service trust models either do not consider users' preferences for different quality of service (QoS) attributes, or ignore the impact of vicious ratings on trust evaluation. To address these gaps, PHAT, a dynamic trust evaluation model with dual consideration of users' preferences and false ratings, is proposed in this paper. The model introduces an approach to automatically mine users' preferences from their requirements. The preferences are then used to determine the weight of each QoS attribute when integrating trust into multi-dimensional QoS attributes. The “local” trust on a service is derived by combining the trust on QoS attributes and the user's subjective ratings. Then, the users are divided into different groups according to their QoS preferences, and the honesty of each group is assessed by filtering out dishonest users based on a hybrid approach combining rating consistency clustering with an average method. Finally, the weight on ratings is dynamically adjusted according to the results of honesty assessment when calculating the global trustworthiness, namely, the reputation of a service. The proposed model is evaluated with real-world QoS data, and the results indicate that PHAT works well on personalized evaluation of trust, and can effectively dilute the influence of malicious ratings.