QoS Prediction for Composite Web Services with Transactions

Quality of Service (QoS) has been widely used to support dynamic Web Service (WS) selection and composition. Due to the volatile nature of QoS parameters, QoS prediction has been put forward to understand the trend of QoS data volatility and estimate QoS values in dynamic environments. In order to provide adaptive and effective QoS prediction, we propose a WS QoS prediction approach, named WS-QoSP, based on the technique of forecast combination. Different from the existing QoS prediction approaches that choose a most feasible forecasting model and predict relying on this "best" model, WS-QoSP selects multiple potential forecasting models, combines the results of the selected models to optimize the overall forecast accuracy. Results of real data experiments demonstrate the diversified forecast accuracy gains by using WS-QoSP.

Web services QoS (Quality of Service) prediction in dynamic environment is a critical method to support service selection and service composition. The existing QoS prediction methods focus on the user-side QoS but not the server-side. However, the prediction accuracy of QoS prediction methods for user-side QoS are restricted by the subjectivity of user's feedback, while the server-side QoS prediction methods could get higher prediction accuracy with relying on objective QoS measured value. To this end, we purposed a server-side QoS prediction method for Web service dubbed QoSPAC. Based on Kalman Filter, QoSPAC generates the QoS predicted value and uses the QoS measured value to calibrate it. Furthermore, QoSPAC measures the prediction accuracy, which is also used to calibrate and optimize the prediction period. Experimental results demonstrate that QoSPAC can adapt to the noteworthy measurement error, and can significantly improve the prediction accuracy compared with the conventional technology.

More recently, with the increasing demand of web services on the World Wide Web used in the Internet of Things (IoTs), there has been a growing interest in the study of efficient web service quality evaluation approaches through the use of prediction strategies to obtain accurate quality-of-service (QoS) values. The unpredictable network environment imposes very challenging obstacles to web service QoS prediction. Most of the traditional web service QoS prediction approaches are implemented only using a set of static model parameters with the help of designer's priori knowledge. Unlike the traditional QoS prediction approaches, our algorithm in this paper is realized by incorporating approximate dynamic programming (ADP)-based online parameter tuning strategy into the QoS prediction approach. Through online learning and optimization, the proposed approach implements the QoS prediction with automatic parameter tuning capability, and the prior knowledge or identification of the prediction model is not required. The near-optimal performance of QoS prediction can therefore be achieved. Experiment studies are carried out to demonstrate the effectiveness of the proposed ADP-based prediction approach.

Quality of Service (QoS) prediction has played an important role in service computing. However, in the real-world scenario of Web service, many user-observed QoS values are unknown and vary over time. In order to provide high accurate and efficient QoS prediction performance for Web services, we propose a personalized and accurate QoS prediction approach namely PAOMF. Our prediction model is built by employing matrix factorization and online stochastic gradient descent algorithm. Extensive experiments are conducted on real world public datasets, which demonstrate the effectiveness and efficiency of our proposed approach.

With the rapid growth of Web services, recommending suitable services to users has become a big challenge. The existing service recommendation works by Quality of Service (QoS) prediction fail to fully consider the influence of situation information, such as time, location, and user relations thoroughly. Two issues must be resolved to consider situation information: issue one, rating scarcity, is that there are less data to learn when importing more situations; issue two is that an effective approach is needed to adapt many situational factors. Our solution is a two-phase method: first, to overcome rating scarcity, data is augmented with estimations of unknown QoS values by learning from observable factors. The augmented data is then used to learn the important latent factors associated with the situational factors for QoS prediction. Experiments on data of real service invocations in different situations show improvement of our method in terms of QoS prediction accuracy over several existing methods, especially in the severe rating scarcity condition. In addition, analysis on parameter selection of proposed method can further assist in obtaining better QoS prediction in practical use.

In the Web Service Composition (WSC) domain, Web Services (WSs) execute in a highly dynamic environment, as a result, the Quality of Service (QoS) of a WS is constantly evolving, and this requires tracking of the global optimization overtime to satisfy the users’ requirements. In order to make a WSC adapt to such QoS changes of WSs, we propose a self-healing model for WSC. Self-healing is the automatic discovery, and healing of the failure of a composite WS by itself due to QoS changes without interruption in the WSC and any human intervention. To the best of our knowledge, almost all the existing self-healing models in this domain substitute the faulty WS with an equivalent one without paying attention to the WS selection processes to achieve global optimization. They focus only on the WS substitution strategy. In this paper, we propose a self-healing model where we use our hybrid approach to find the optimal WSC by using Parallel Genetic Algorithm based on Q-learning, which we integrate with K-means clustering (PGAQK). The components of this model are organized according to IBM’s Monitor, Analyse, Plan, Execute, and Knowledge (MAPE-K) reference model. The PGAQK approach considers as a module in the Execute component. WS substitution strategy has also been applied in this model that substitutes the faulty WS with another equivalent one from a list of candidate WSs by using the K-means clustering technique. K-means clustering is used to prune the WSs in the search space to find the best WSs for the environment changes. We implemented this model over the NET Framework using C# programming language. A series of comparable experiments showed that the proposed model outperforms improved GA to achieve global optimization. Our proposed model also can dynamically substitute the faulty WSs with other equivalent ones in a time-efficient manner

QoS prediction for service recommendations in mobile edge computing

With the development of web service, web service composition is used widely. How to guarantee the non-functional requirement of users under the precondition of satisfying functional requirement of users is an important problem in web service composition. To address this problem, this paper presents a web service composition selection approach based on multi-dimension quality of service(QoS) which introduces multi-dimension QoS to describe the QoS of web service composition and computes the QoS of web service composition according to the type of web service composition. Then the web service composition which can best satisfy the non-functional requirement of users can be found from the web service compositions which can satisfy functional requirement of users according to this approach. At last, an application example is used to explain this approach.

THE Internet, along with its related technologies, has created an interconnected world in which information flows easily and tasks are processed collaboratively. To make service-oriented applications more robust, Web services must be examined from a transactional perspective. By transactional, we mean first defining the actions that guide the execution of Web services when failures arise and then the states that permit claiming the success of this execution following the handling of these failures. A variety of transactional models are reported in the database community. Some of these models can be leveraged and enhanced in response to Web services characteristics while others are not suitable for Web services due to the dynamic nature of Web services, the long-running execution scenarios that Web services take part in, and the successful execution of Web services despite other peers’ failure. Today’s service-oriented applications require advanced transactional models that guarantee integrity and continuity of business processes despite the dynamic nature of the features of the environments hosting the execution of these applications. This special section sheds light on the latest advances in the fields of Web services and transactional models in order to better address advanced research on and experience with transactional Web services. Four papers out of 19 submissions were selected for inclusion in this special section. Each submission was subject to a double-review process by at least three peer reviewers. In the first paper, entitled “Event-Based Design and Runtime Verification of Composite Service Transactional Behavior,” Gaaloul et al. propose an event-driven approach to validate the transactional behavior of Web services taking part in compositions. A composition life cycle consists of four phases, namely, design, execution, monitoring, and reengineering. The verification of this behavior throughout this life cycle is done either at design time to validate recovery mechanisms’ consistency or after runtime to detect execution deviations and repair design errors, and, therefore, formally ensure the execution reliability of Web services. In addition, this verification is based on the Event Calculus formalism, which offers a sound definition for this reliability. In the second paper, entitled “FACTS: A Framework for Fault-Tolerant Composition of Transactional Web Services,” Liu et al. note that delivering reliable compositions over unreliable Web services is challenging. To address this challenge, Liu et al. identify a set of high-level exception handling strategies and a new taxonomy of transactional Web services to devise a fault-tolerant mechanism that combines exception handling and transaction techniques. In addition, Liu et al. devise two modules, known as specification and verification, to assist service designers in constructing fault handling logic conveniently and correctly. This logic is automatically injected into WS-BPEL. In the third paper, entitled “Rule-Based Coordination of Distributed Web Service Transactions,” von Riegen et al. study the distributed transactional activity control problem in the context of service choreographies. In such a context, many participants are allowed to work together to achieve a global, common goal, and the initiator of a process is not always the one who is able to commit or cancel a transaction. Von Riegen et al. introduce a framework that allows autonomous coordination of dynamic processes. This framework extends WSBusinessActivity to strengthen the role of the coordinator. Predicate rules are developed to let participants cancel or complete a process and help the coordinators decide on the completion processes and the confirmation or cancellation of the participants’ works. In the fourth paper, entitled “TQoS: Transactional and QoS-Aware Selection Algorithm for Automatic Web Service Composition,” El Haddad et al. focus on the issues of selecting and composing Web services. A design-time selection algorithm is proposed in which transactional and QoS requirements are both integrated into the selection process. This algorithm is based on the notion of risk that indicates if execution outcomes can either be compensated for or not. Two risk levels of execution in a transactional system are considered: Risk 0, meaning that if the execution is successful, the obtained outcomes can be compensated for by the user, and Risk 1, meaning that the system does not guarantee successful execution, but if it achieves it, the outcomes cannot be compensated for by the user. We hope this special section inspires researchers to develop new transactional models that would guarantee service-oriented applications integrity and continuity. 30 IEEE TRANSACTIONS ON SERVICES COMPUTING, VOL. 3, NO. 1, JANUARY-MARCH 2010

With the growing popularity of Service-Oriented-Computing (SOC) architecture, the number of Web services on the internet is increasing rapidly. When faced with a large number of candidate services with similar functionalities, personalized Web service recommendation is becoming an important issue. Quality-of-Service (QoS) is usually used to characterize the non-functional properties of Web services. Thus accurate QoS prediction is an important step in the service recommendation. In this paper, we propose a Cluster Feature based Latent Factor Model (CFLFM) for QoS prediction. First, we cluster users and services into several groups based on history records, respectively. We assume that users or services in the same cluster share some latent features. By incorporating this kind of information, we design an integrated latent factor model. Finally, we conduct comprehensive experiments on a real-world Web service dataset. The experimental results show that our approach can achieve higher QoS prediction accuracy than other competing approaches.

To deal with the problems such as Web Services selection algorithm, availability of Web Services composition and QoS(Quality of Service) guarantee, presents a model for Web Services composition based on QoS and providers' benefit. In this model, the traditional UDDI is expanded to describe the QoS attributes of Web Services. A Service Proxy role is added into this model. All Web Services compositions requested by service consumers are fond, bound and invoked by the Service Proxy role. In order to maximize services providers' benefit, presents a Service Request Queue Scheduling algorithm in the Service Proxy role. This model meets the QOS requirements of service consumers, guarantees the availability of Web Services composition and maximizes service providers' benefit. Experimental results confirm the efforts of this model.

With the rapid growth of web services on the Internet, it becomes more difficult for users who want to choose the high-quality web services from a large number of functionally equivalent candidate services. Therefore, the prediction of quality of service (QoS) values according to the history of web services has received extensive attention. In recent years, deep learning has achieved great success in speech recognition, image processing, and natural language understanding. However, it is rarely applied to the service recommendation field. Therefore, a novel approach for QoS prediction named NDL (neighborhood-aware deep learning) is proposed. NDL first gets the Top-k neighbors of the user and the service through the Pearson correlation coefficient according to the service QoS information. Then, it extracts the potential features of the user neighbor and the service neighbor; after that, it inputs the QoS values of the user and the user neighbor as well as the QoS values of the service and service neighbors as a convolutional neural network. The results of experiments conducted on a real-world dataset demonstrate that the NDL significantly outperforms the current QoS prediction method in prediction accuracy.

With the widespread adoption of cloud computing, large-scale online applications composed of services have been deployed in many critical areas. In order to ensure the performance of cloud applications, Quality of Service (QoS) is a key indicator commonly used for service selection and adaptation. Previous studies have proposed collaborative QoS prediction approaches to estimate personalized QoS values. However, collaborative QoS prediction encounters privacy problems in practice. As a result, privacy threat has become a key challenge to make QoS prediction approaches practical. In this paper, we proposed a privacy-preserving QoS prediction approach employing federated learning techniques to tackle this grand challenge. We further improve the prediction efficiency by reducing system overhead and make the federated privacy-preserving QoS prediction approach feasible. The proposed approach is evaluated on a large-scale real-world QoS dataset, and the experimental results confirm its effectiveness and efficiency.

Virtual enterprise is a temporary network of independent companies or enterprises that can quickly bring together to fulfill a value-added task. With the development of Web service technologies, the enterprise business systems can be encapsulated as Web services. Establishing a virtual enterprise is actually a process of Web services composition. As more and more Web services are available, many Web services with different quality of service (QoS) can be found for tasks of the composite Web service. Thus, a significant research problem in Web service composition is how to select the correct Web services for tasks such that the composite Web service gives the best overall quality. In this paper, we propose an approach to achieve Web services selection efficiently with excellent comprehensive quality. Firstly, a comprehensive evaluation model based on generic QoS (GQoS) and domain QoS (DQoS) of composite Web service is established. Secondly, a novel optimization algorithm named culture max–min ant system (C-MMAS) is constructed to solve the problem of Web service selection based on DGQoS. Simulations show that when used in Web service selection, C-MMAS is better than ant colony optimization algorithm and MMAS in efficiency.

Aiming at the hot and difficult issues in Web services and service composition, this paper analyzes and studies the selection of Web services and service composition from the functional and non functional attributes of Web services, and mainly makes the following work and innovation. First of all, the functional attributes of Web services are studied, Web services on various service provision platforms are collected, and Web services are classified. Secondly, aiming at the shortcomings of existing Web service QoS attribute evaluation models, an improved method is proposed, which introduces a comprehensive evaluation mechanism of variable weight vector. Based on the constant weight comprehensive evaluation method, the state variable weight vector is established to dynamically adjust the attribute weights of various service QoS indicators, so as to improve the accuracy and objectivity of the Web service QoS attribute evaluation. Finally, in view of the defects and deficiencies of traditional algorithms in the selection of Web service composition, the particle swarm optimization algorithm with linearly decreasing inertia weight and learning factor is introduced, which better balances the self cognition and social learning ability of particles, and improves the search speed and global search ability of particles. And a large number of experiments are carried out to compare it with the traditional algorithm, which verifies the effectiveness and superiority of the improved particle swarm optimization algorithm.