AI Planning and Combinatorial Optimization for Web Service Composition in Cloud Computing

Abstract

In recent years, there has been an increasing interest in web service composition due to its importance in practical applications. At the same time, cloud computing is gradually evolving as a widely used computing platform where many different web services are published and available in cloud data centers. The issue is that traditional service composition methods mainly focus on how to find service composition sequence in a single cloud, but not from a multi-cloud service base. It is challenging to efficiently find a composition solution in a multiple cloud base because it involves not only service composition but also combinatorial optimization. In this paper, we first propose a framework of service composition in multi-cloud base environments. Next, three different cloud combination methods are presented to select a cloud combination subject to not only finding feasible composition sequence, but also containing minimum clouds. Experimental results show that a proposed method based on artificial intelligence (AI) planning and combinatorial optimization can more effectively and efficiently find sub-optimal cloud combinations.

Agent-based Cloud service composition

“…In addition, both [55] and [56] are centralized approaches. Moreover, inherent features of Cloud-computing environments are ignored, such as: (i) service fees associated to Cloud services, nor dynamic selection of services based on fees, (ii) service contract management, and (iii) updating Cloud service compositions.…”

“…Although [55] and [56] are focused on different aspects of Cloud service compositions, they share some strong assumptions, such as: complete knowledge of the Cloudcomputing environments, and that all the web services are atomic. In addition, both [55] and [56] are centralized approaches.…”

“…In [56], Cloud service composition is achieved in multiple Cloud-computing environments. From the service directories of each Cloud, a search tree is created to which artificial intelligence planning techniques are applied to obtain service compositions that involve the minimum number of Clouds.…”

Self-Organization Mechanisms for Service Composition in Cloud Computing

“…Therefore, the problem of how to effectively and efficiently compose existing services has attracted a lot of research interests and is an important open problem [3].…”

Scaling Up Web Service Composition with the Skyline Operator

“…Many inmemory approaches based on different techniques have been successfully employed in solving service composition problem. These include Integer Linear programming [1], beam-stack search [2] and the planning model [3]- [5]. For each user request, in-memory approaches construct a search graph and search this graph for a solution.…”