The advent of Web services has made automated workflow composition relevant to web based applications. One technique, that has received some attention, for automatically composing workflows is AI-based classical planning. However, classical planning suffers from the paradox of first assuming deterministic behavior of Web services, then requiring the additional overhead of execution monitoring to recover from unexpected behavior of services. To address these concerns, we propose using Markov decision processes (MDPs), to model workflow composition. Our method models both, the inherent stochastic nature of Web services, and the dynamic nature of the environment. The resulting workflows are robust to non-deterministic behaviors of Web services and adaptive to a changing environment. Using an example scenario, we demonstrate our method and provide empirical results in its support. 1.

Web services are fast emerging as the dominant means for connecting remotely executing programs via well established internet protocols and commonly used machine readable representations. Software agents are now increasingly used in commercial applications to solve complex engineering problems, and these applications often expose or make use of Web services. As such,

Abstract not found

We propose a framework and polynomial algorithms for semantic-based automated Web service composition, fully compliant with Semantic Web technologies. The approach exploits the recently proposed Concept Abduction inference service in Description Logics to extend Concept covering definition to expressive logics and to solve Concept Covering problems in a significant subset of OWL-DL. We show how the proposed approach also deals with not-exact solutions, computing an approximate composition and providing an explanation of which part of the request is not covered by the composite service. We present the formalization of the approach, the proposed algorithms, a prototype system implementing the approach, and illustrate experiments carried out with it. KEY WORDS:

Abstract. Recently, Web services have generated great interests in both vendors and researchers. Web services, based on existing Internet protocols and open standards, can provide a flexible solution to the problem of application integration. With the help of WSDL, SOAP, and UDDI, Web services are becoming popular in Web applications. However, the current Web services architectures are confronted with a few stubborn problems, for instance, security. In this paper, we shall give an overview of these problems. We believe that solving these problems will become crucial to success of Web services. In the end, we predict distinct advances in semantic Grid services.

There is little doubt that Web services are becoming a part of the essential fabric enabling machine-to-machine information exchange across the Web. However, there is also a perceptible progression toward the realisation that this principal means of invoking operations on remote hosts will become insufficient to their task almost as quickly as they rose to prominence. Already emerging amongst the community of adopters is a recognition that richer semantics are required to express any truly useful information about the nature of business processes and the way in which they interoperate. But ultimately, as the power to meaningfully express information improves, so does the need for automatic processes (i.e. agents), that are capable of interpreting, processing and deciding about this information. Given this, a means of connecting the realms of agents and Web services is required and so this paper reports on a proposed design for a Service Integration Gateway for seamlessly connecting Web services to agents and their services. The Gateway is a progressive work evolving from existing approaches, yet taking an innovative approach encapsulating fully transparent and automatic operation in a simple and scalable solution.

In realistic settings, service descriptions will never be precise reflections of the services really offered. An online seller of notebooks, for instance, will most certainly not describe each and every notebook offered in his service description. This imprecision causes poor quality in discovery results. A matcher will be able to find potentially matching services but can give no guarantees that the concrete service needed will really be provided. To alleviate this problem, a contract agreement phase between service provider and requester following the discovery has been suggested in the literature. In this paper, we present an approach to the automation of this contracting. At the heart of our solution is the possibility to extend service descriptions with dynamically changing information and to provide several means tailored to the abilities of the service provider to obtain this information at discovery time.

Abstract. Web services are functionalities that can be engaged over the Internet. A workflow is a set of Web services that are executed by carrying out specified control and data flows among these services to address some business needs. We believe that commitments among agents can be used to model a workflow and coordinate several self-interested parties to execute a workflow. This paper presents a methodology to infer commitments and causal relationships from a workflow by utilizing semantic descriptions of Web services. We provide an example scenario to show how commitments of a workflow can be inferred. In addition, we use the Petri net representation of a workflow to describe our algorithm. With this technology, agents (service requestors and providers) engaged in a workflow can negotiate with multiple agents to reach favorable agreements and then coordinate their behaviors through the commitment operations in the context of service-oriented environment, where one or more self-interested parties can provide services to one or more other parties. 1

Abstract –Technological advancements in the Web services standards have lead to the development and deployment of broad applications in open and dynamic environment. These standards enable the services to be discovered and invoked dynamically. In current web, due to lack of semantics, agents cannot understand services that radically influence the negotiation, coordination and cooperation among the heterogeneous environments. Hence semantics play a vital role to bring automation in the current web and are highly desirable to enhance the capabilities of Web services. We believe that the vision of the semantic web can be realized if the agents are intelligent enough to process and interpret the semantic content based on the understanding which they have developed about the contents through the use of attached ontologies, since the agents have well defined reasoning, decision making, and interaction mechanisms. Our research objective is to propose new paradigm for interactions among semantic web services and software agents for problem solving. In this paper, our focus is to address the issue of negotiation between agents and semantic web services and present our initial work towards the solution, by presenting how the agents can discover, invoke and negotiate with the Semantic Web services for the autonomous service provisioning and consumption. We have achieved this interoperability, where the agents can efficiently communicate with the Web services in the dynamic and heterogeneous environments.