•Proposing a novel deep learning based hybrid service recommendation approach.•Capturing non-linear interactions between mashups and their component services.•Evaluating pointwise and pairwise loss ...functions in the recommendation task.•The approach outperforms state-of-the-art methods on a real-world dataset.
With the rapid development of service-oriented computing and cloud computing, an increasing number of Web services have been published on the Internet, which makes it difficult to select relevant Web services manually to satisfy complex user requirements. Many machine learning methods, especially matrix factorization based collaborative filtering models, have been widely employed in Web service recommendation. However, as a linear model of latent factors, matrix factorization is challenging to capture complex interactions between Web applications (or mashups) and their component services within an extremely sparse interaction matrix, which will result in poor service recommendation performance. Towards this problem, in this paper, we propose a novel deep learning based hybrid approach for Web service recommendation by combining collaborative filtering and textual content. The invocation interactions between mashups and services as well as their functionalities are seamlessly integrated into a deep neural network, which can be used to characterize the complex relations between mashups and services. Experiments conducted on a real-world Web service dataset demonstrate that our approach can achieve better recommendation performance than several state-of-the-art methods, which indicates the effectiveness of our proposed approach in service recommendation.
Service-oriented architecture is becoming a major software framework for complex application and it can be dynamically and flexibly composed by integrating existing component web services provided by ...different providers with standard protocols. The rapid introduction of new web services into a dynamic business environment can adversely affect the service quality and user satisfaction. Therefore, how to leverage, aggregate and make use of individual component's quality of service (QoS) information to derive the optimal QoS of the composite service which meets the needs of users is still an ongoing hot research problem. This study aims at reviewing the advance of the current state-of-the-art in technologies and inspiring the possible new ideas for web service selection and composition, especially with nature-inspired computing approaches. Firstly, the background knowledge of web services is presented. Secondly, various nature-inspired web selection and composition approaches are systematically reviewed and analysed for QoS-aware web services. Finally, challenges, remarks and discussions about QoS-aware web service composition are presented.
•We propose an elite evolution strategy to be integrated with HHO.•The proposed modified HHO algorithm is named EESHHO.•We evaluate EESHHO by solving 29 mathematical optimization cases.•EESHHO is ...used to solve the QoS web service composition problem.
Harris hawks optimization (HHO) is one of the leading optimization approaches due to its efficacy and multi-choice structure with time-varying components. The HHO has been applied in various areas due to its simplicity and outstanding performance. However,the original HHO can be improved and evolved in terms of convergence trends, and it is prone to local optimization under certain circumstances. Therefore, the performance and robustness of the algorithm need to be further improved. In our research, based on the core principle of evolutionary methods, we first developed an elite evolutionary strategy (EES) and then utilized it to advance HHO’s convergence speed and ability to jump out of the local optimum. We named such an enhanced hybrid algorithm EESHHO in this paper. To verify the effectiveness and robustness of the EESHHO, we tested it on 29 numerical optimization test functions, including 23 classic basic test functions and 6 composite test functions from the IEEE CEC2017 special session. Moreover, we apply the EESHHO on resource-constrained project scheduling and QoS-aware web service composition problems to further validate the effectiveness of EESHHO. The experimental results show that proposed EESHHO has faster convergence speed and better optimization performance by comparing it with other mainstream algorithms. The supplementary info and answers to possible queries will be publicly available at https://aliasgharheidari.com/publications/EESHHO.html. Also, the codes and info of HHO are available at: https://aliasgharheidari.com/HHO.html.
In Web Service research, providing methods and tools to cater for automatic composition of services on the Web is still the object of ongoing research activity. Despite the proposed approaches, this ...issue remains open. Our current contribution deals with this topic and presents a Dynamic Web Service Composition Framework (DWSC). The DWSC behavior is based mainly on two components: service dynamic designer (WSDD) and service selection based on popularity (WSSP) to propose a composite service. The DWSC architecture, designed to automatically compose services based on popularity, has the advantage of proposing a list of suggested web services according the user request from a service repository and presenting a dynamic orchestration based on the selected web services. Further, we present a practical case study according the transportation process on supply chain, examples and experimental results that demonstrate the feasibility and effectiveness of our work.
Selection of an appropriate web service fulfilling the requirements of the end user is a challenging task. Most of the existing systems use Quality of Service (QoS) as predominant parameter for web ...service selection, without any preprocessing or filtering. These systems consider all of the candidate web services during selection process and require unnecessary processing of those web services which are far below the expectations of the end user. In this work, an approach for web service selection based on QoS parameters is proposed. The proposed method starts with prefiltering of candidate web services using classification technique. An improved PROMETHEE method, we call it as PROMETHEE Plus, is applied to most eligible web services and Maximizing Deviation Method based hybrid weight evaluation mechanism is adopted. Top-k web services matching closely with the QoS requirements of the end user are selected. Experiments on the dataset of real world web services are conducted. Experimental results show that our approach performs better in terms of end user satisfaction and efficiency with reference to the existing similar approaches.
•Study the mapping relationship between the similarity and the geographical distance.•Propose two novel context-aware QoS prediction models and an ensemble model.•Our models can save much ...computation, and are suitable for the cold-start scenario.
QoS prediction is one of the key problems in Web service recommendation and selection. The context information is a dominant factor affecting QoS, but is ignored by most of existing works. In this paper, we employ the context information, from both the user side and service side, to achieve superior QoS prediction accuracy. We propose two novel prediction models, which are capable of using the context information of users and services respectively. In the user side, we use the geographical information as the user context, and identify similar neighbors for each user based on the similarity of their context. We study the mapping relationship between the similarity value and the geographical distance. In the service side, we use the affiliation information as the service context, including the company affiliation and country affiliation. In the two models, the prediction value is learned by the QoS records of a user (or a service) and the neighbors. Also, we propose an ensemble model to combine the results of the two models. We conduct comprehensive experiments in two real-world datasets, and the experimental results demonstrate the effectiveness of our models.
We introduce molecularevolution. org, a publicly available gateway for high-throughput, maximum-likelihood phylogenetic analysis powered by grid computing. The gateway features a GARLI 2.0 web ...service that enables a user to quickly and easily submit thousands of maximum likelihood tree searches or bootstrap searches that are executed in parallel on distributed computing resources. The garli web service allows one to easily specify partitioned substitution models using a graphical interface, and it performs sophisticated post-processing of phylogenetic results. Although the garli web service has been used by the research community for over three years, here we formally announce the availability of the service, describe its capabilities, highlight new features and recent improvements, and provide details about how the grid system efficiently delivers high-quality phylogenetic results.
With the rapid development of electronic business, Web services have attracted much attention in recent years. Enterprises can combine individual Web services to provide new value-added services. An ...emerging challenge is the timely discovery of close matches to service requests among large service pools. In this study, we first define a new semantic similarity measure combining functional similarity and process similarity. We then present a service discovery mechanism that utilises the new semantic similarity measure for service matching. All the published Web services are pre-grouped into functional clusters prior to the matching process. For a user's service request, the discovery mechanism first identifies matching services clusters and then identifies the best matching Web services within these matching clusters. Experimental results show that the proposed semantic discovery mechanism performs better than a conventional lexical similarity-based mechanism.
•Proposing a new similarity measure integrating multiple conceptual relationships.•Utilizing is-a, has-a and antinomy conceptual relationships.•Weighted combination of interface similarity and ...description similarity.•Comparing with state-of-the-art similarity-based Web service discovery methods.
The process of Web service discovery identifies the most relevant services to requesters’ service queries. We propose a new measure of semantic similarity integrating multiple conceptual relationships (SIMCR) for Web service discovery. The new measure enables more accurate service-request comparison by treating different conceptual relationships in ontologies such as is-a, has-a and antonomy differently. Each service or request is represented by vectors of terms (or words) that characterize both the interface signature and textual description. The overall semantic similarity is computed as a weighted aggregation of interface similarity and description similarity. The experimental results confirm the effectiveness of the proposed semantic similarity measure. As demonstrated in this study, the semantic Web service discovery method based on the proposed similarity measure outperforms existing state-of-the-art discovery methods in terms of precision, recall and F-measure. The proposed semantic similarity measure has wider applications such as to improve document classification or clustering, and to more accurately represent and apply knowledge in expert and intelligent systems.
Service-Oriented Computing (SOC) is a new paradigm that replaces the traditional way to develop distributed software with a combination of discovery, engagement and reuse of third-party services. Web ...Service technologies are currently the most adopted alternative for implementing the SOC paradigm. However, Web Service discovery presents many challenges that, in the end, hinder service reuse. This paper reports frequent practices present in a body of public services that attempt to prevent the discovery of any service. In addition, we have studied how to solve the discoverability problems that these bad practices cause. Accordingly, this paper presents a novel catalog of eight Web Service discoverability anti-patterns. We conducted a comparative analysis of the retrieval effectiveness of three discovery systems by using the original body of Web Services versus their corrected version. This experiment shows that the removal of the identified anti-patterns eases the discovery process by allowing the employed discovery systems to rank more relevant services before non-relevant ones, with the same queries. Moreover, we conducted a survey to collect the opinions from 26 individuals about whether the improved descriptions are more intelligible than the original ones. This experiment provides more evidence of the importance of correcting the observed problems.