Data Providing Services Clustering and Management for Facilitating Service Discovery and Replacement

Abstract

In service-oriented computing, a user usually needs to locate a desired service for: (i) fulfilling her requirements or (ii) replacing a service, which disappears or is unavailable for some reasons, to perform an interaction. With the increasing number of services available within an enterprise and over the Internet, locating a service online may not be appropriate from the performance perspective, especially in large Internet-based service repositories. Instead, services usually need to be clustered according to their similarity. Thereafter, services in one or several clusters are necessary to be examined online during dynamic service discovery. In this paper, we propose to cluster data providing (DP) services using a refined fuzzy -means algorithm. We consider the composite relation between DP service elements (i.e., input, output, and semantic relation between them) when representing DP services in terms of vectors. A DP service vector is assigned to one or multiple clusters with certain degrees. In addition, we introduce some operations for managing service clusters, when new services emerge or existing services disappear or become unavailable. When grouping similar services into one cluster, while partitioning different services into different clusters, the capability of service search engine is improved significantly. We have prototyped our approach and the source code is freely available on the web. We have evaluated our clustering approach in different settings and the results are very promising.Note to Practitioners-DP services are common nowadays, and there are a huge number of DP services in the Internet-scale environment. Locating an appropriate DP service accurately and efficiently with respect to the requirements of a certain requestor is a challenging task. This work presents a novel clustering-oriented approach, which aims to group DP services into clusters offline leveraging the semantic description of these DP services, and provides operations for managing these clusters. The clustering procedure is conducted by means of a machine learning technique which is a refined fuzzy -means method. A DP service can be assigned to one or several clusters with certain degrees. DP service clusters constitute a cluster network. Operations are provided for facilitating the evolution of cluster network, when a DP service emerges or disappears sometime for some reason. A prototype has been implemented and the approach has been evaluated on two test collections of DP services considering factors impacting the efficiency. Our method can be readily used in industrial DP service repository for supporting DP service discovery and replacement.

An Approach for Content Retrieval from Web Pages Using Clustering Techniques

“…Li et al [14] proposed a concept to incorporate multidimensional clustering into a collaborative filtering recommendation model. In first stage, the user and item profiles were collected and clustered using the proposed algorithm.…”

“…Mostly the data set formed will not look in to the description value of the data instant it checks only for the migrant value of the data based on the usage of the data information. The data set recommended also will be maintained by user and not by the external affairs so that the data set recommended will give an enormous value accordingly to the different user for the same input of data the variation in the data and mismatch of the data content was formulated in the data set recommender system and also it will be avoided by the measures induced in the filtering phase used by the different collaborators [12] [14].…”

A noise- and size-insensitive integrity-based fuzzy c-means algorithm for image segmentation

“…x v (10) where N j is the neighborhood of data point x j and x r is the data point in the neighborhood N j , C i is cluster i. Thus, for data point x j with high purity neighborhood with respect to cluster i, fuzzy factor PG ij would be small; whereas data point x j with low purity neighborhood, PG ij would be larger.…”

“…Lately, it has even been applied to data providing service [10]. In [8], a fuzzy local information c-means clustering Phen-Lan Lin is with Department of Computer Science and Information Engineering, Providence University, Taiwan.…”

A dynamic assignment scheduling algorithm for big data stream processing in mobile Internet services

“…It features reading local history to keep adjusting the task graph so as to assign tasks to the proper nodes. Data providing (DP) services clustering using a refined fuzzy means algorithm [35] also processes big data stream in Internet services. Yang proposed a stream computing model which supports for execution of application and dynamic partitioning [36].…”