Cloud Computing (CC) is considered the latest emerging computing paradigm and has brought revolutionary changes in computing technology. With the advancement in this field, the number of cloud users and service providers is increasing continuously with more diversified services. Consequently, the selection of appropriate cloud service has become a difficult task for a new cloud customer. In case of inappropriate selection of a cloud services, a cloud customer may face the vendor locked-in issue and data portability interoperability problems. These are the major obstacles in the adoption of cloud services. To avoid these complexities, a cloud customer needs to select an appropriate cloud service at the initial stage of the migration to the cloud. Many researches have been proposed to overcome the issues but problems still exist in intercommunication standards among clouds and vendor locked-in issues. This research proposed an IEEE multi-agent FIPA (Foundation for Intelligent Physical Agent) compliance multi-agent reference architecture for cloud discovery and selection using cloud ontology. The proposed approach will mitigate the prevailing vendor locked-in issue and also alleviate the portability and interoperability problems in Cloud Computing. To evaluate the proposed reference architecture and compare it with the state-of-the-art existing approaches, several experiments have been performed by utilizing the commonly used performance measures. Analysis indicates that the proposed approach enables significant improvements in cloud service discovery and selection in terms of search efficiency, execution and response time.