Cloud Service Composition Using Genetic Algorithm and Particle Swarm Optimization

Cloud computing indicates the on-demand accessibility of computer system resources, especially data storage and computing capabilities that users manage without direct intervention. One of the benefits of using cloud computing services is that companies can use the computing resources they need. Cloud service composition with service quality awareness is a crucial requirement in service-oriented computing, as it enables users to perform complex operations while meeting service quality constraints. Since there are multiple services in the distributed cloud space, the problem space is enormous and choosing the optimal composition is often very complex, which is considered NP-hard. In this paper, a new method using a combination of genetic algorithm and particle swarm optimization algorithm is presented for cloud services composition, which uses exploration and exploitation of these algorithms simultaneously. Our proposed method aims to establish a proper balance between different performance goals to composition these services. We evaluated our approach on the QWS real dataset and compared the results with multiple baseline methods. Based on the number of different generations and services, the proposed method outperforms the basic algorithms and two previous studies and delivers 5% to 15% improvement compared to baseline methods in terms of different criteria.