A Trust-Based Agent Learning Model for Service Composition in Mobile Cloud Computing Environments

Mobile cloud computing has the options of resource constraints, openness, and uncertainty that ends up in the high uncertainty on its quality of service (QoS) provision and heavy security risks. Therefore, once faced with advanced service necessities, associate economical and reliable service composition approach is extraordinarily necessary. additionally, preference learning is additionally a key issue to boost user experiences. so as to handle them, this paper introduces a three-layered trust-enabled service composition model for the mobile cloud computing systems. 

supported the fuzzy comprehensive analysis technique, we have a tendency to style unique and integrated trust management model. Service brokers area unit equipped with a learning module sanctioning them to raised analyze customers’ service preferences, particularly in cases once the small print of a service request is not entirely disclosed. as a result, of ancient ways cannot entirely mirror the autonomous collaboration between the mobile cloud entities, an imaging system supported the multi-agent platform JADE is enforced to gauge the potency of the projected methods. The experimental results show that our approach improves the dealing success rate and user satisfaction.