Online Optimization of Collaborative Web Service QoS Prediction Based on Approximate Dynamic Programming

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.

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.

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.

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.

Prediction of the Quality of Service (QoS) of Composite Web Services (CWS) makes it possible to tell whether the CWS meets the non-function requirements, and to choose the CWS with better QoS from those with similar function. QoS prediction is based on the estimation of the execution process of CWS. For the reliability of CWS executions, Web service transaction has been proposed, which will affect the execution process. However, the existing approaches have not considered the effect. Thus they have limited accuracy when predicting the CWS with transactions. The paper proposes an approach for QoS prediction of CWS with transactions. A specification model is defined to specify execution processes of CWS according to the exception handling policies of transactions. Based on the model, an algorithm is proposed. The experiment proves that the algorithm has much lower error rate and better feasibility than the previous approaches when predicting CWS with transactions.KeywordsComposite Web ServiceQoS predictionTransaction

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.

QoS prediction for service recommendations in mobile edge computing

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.

Predicting the Quality of Service (QoS) values is important since they are widely applied to Service-Oriented Computing (SOC) research domain. Previous research works on this problem do not consider the influence of user location information carefully, which we argue would contribute to improving prediction accuracy due to the nature of Web services invocation process. In this paper, we propose a novel collaborative QoS prediction framework with location-based regularization (LBR). 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 geographical information to identify the neighborhood. Different neighborhood situations are considered to systematically design two location-based regularization terms, i.e. LBR1 and LBR2. Finally we combine these regularization terms in classic MF framework to build two unified models. The experimental analysis on a large-scale real-world QoS dataset shows that our methods improve 23.7% in prediction accuracy compared with other state-of-the-art algorithms in general cases.

Efficient web service QoS prediction using local neighborhood matrix factorization

With the great development of mobile services, the Quality of Services (QoS) becomes an essential factor to meet end users’ personalized requirement on the nonfunctional performance of mobile services. However, most of the QoS values in real cases are unattainable because a service user would only invoke some specific mobile services. Therefore, how to predict the missing QoS values and recommend high-quality services to end users becomes a significant challenge in mobile service recommendation research. Previous QoS prediction researches demonstrate that the nonfunctional performance of mobile services is closely related to users’ location information. However, most location-aware QoS prediction methods ignore the premise that the obtainable QoS values observed by different users in same location region would probably be untrustworthy, which will lead to inaccurate and unreliable prediction results. To make credible location-aware QoS prediction, we propose a hybrid matrix factorization method integrated location and reputation information (LRMF) to predict the unattainable QoS values. Our approach firstly cluster users into different locational region based on their geographical distribution, and then we compute users’ reputation to identify untrustworthy users in every locational region. Finally, the unknown QoS values can be predicted by integrating locational cluster information and users’ reputation into a hybrid matrix factorization model. Comprehensive experiments are conducted on a public QoS dataset which contains sufficient real-world service invocation records. The evaluation results indicate that our LRMF method can effectively reduce the impact of unreliable users on QoS prediction and make credible mobile service recommendation.

Service-oriented computing (SOC) promises a world of cooperating services loosely connected, constructing agile Web applications in heterogeneous environments conveniently. Web application interface (API) as an emerging technique attracts more and more enterprises and organizations to publish their deep computing functionalities and big data on the Internet, Web API has become the backbone to promote the development of SOC, thus forming the prosperous Web API economy. However, the number of available Web APIs on the Internet is massive and growing constantly, which causes the Web API overload problem. Quality of service (QoS) as an indicator is able to well differentiate the quality of Web APIs and has been widely applied for high quality Web API selection. Since testing QoS for massive Web APIs is resource-consuming, and the QoS performance depends on contextual information such as network and location, hence accurate QoS prediction has become very crucial for personalized Web API recommendation and high quality Web application construction. To address the above issue, this paper presents a context aware deep factorization machine model (CADFM for short) for accurate Web API QoS prediction. Specifically, we first carry out detailed data analysis using real-world QoS dataset and discover a positive relationship between QoS and contextual information, which motivates us to incorporate beneficial contexts for enhancing QoS prediction accuracy. Then, we treat QoS prediction as a regression problem and propose a context aware CADFM framework that integrates the contextual information via embedding technique. Particularly, we adopt MF and MLP for high-order and nonlinear interaction modeling, so as to learn the complex interaction between users and Web APIs accurately. Finally, the experimental results on real-world QoS dataset demonstrate that CADFM outperforms the classic and the state-of-the-art baselines, thereby generating the most accurate QoS predictions and increasing the revenue of Web APIs recommendation.

The internet currently hosts a large number of web services with highly volatile quality of service (QoS), which makes it difficult for users to quickly access highly reliable online services. Hence, the selection of the optimal service composition based on fast and reliable QoS has emerged as a challenging and popular problem in the field of service computing. In this paper, we propose a service selection approach based on QoS prediction. We consider historical QoS information as time series and predict QoS values using the autoregressive integrated moving average model, which can provide more accurate QoS attribute values. We then calculate the uncertainty in the prediction results using an improved coefficient of variation to prune redundant services. In order to downsize the search space, we employ Skyline computing to prune redundant services and perform Skyline service selection using 0-1 mixed-integer programming. Experimental results based on real-world dataset showed that our approach yields satisfactory performance in terms of reliability and efficiency.

With the fast-developing domain of cyber-physical systems (CPS), constructing the CPS with high-quality services becomes an imperative task. As one of the effective solutions for information overload in CPS construction, quality of service (QoS)-aware service recommendation has drawn much attention in academia and industry. However, the lack of most QoS values limits the recommendation performance and it is time-consuming for users to get the QoS values by invoking all the services. Therefore, a powerful prediction model is required to predict the unobserved QoS values. Considering the fact that most existing QoS prediction models are unable to effectively address the data-sparsity problem, a novel two-stage framework called AgQ is proposed for QoS prediction. Specifically, a data augmentation strategy is designed in the first stage to enlarge the training set by drawing additional virtual instances. In the second stage, a prediction model is applied that considers both virtual and factual instances during the training procedure. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the our QoS prediction framework and verify that the data augmentation strategy can indeed alleviate the data-sparsity problem. In terms of mean absolute error, taking the Multilayer Perceptron model as an example, the maximum improvement achieves 5% under 5% sparsity.