A signaling game-based approach for Data-as-a-Service provisioning in IoT-Cloud

The impressive progress in sensing technology over the last few years has contributed to the proliferation and popularity of the Internet of Things (IoT) paradigm and to the adoption of Sensor Clouds for provisioning smart ubiquitous services. Also, the massive amount of data generated by sensors and smart objects led to a new kind of services known as Data-as-a-Service (DaaS). The quality of these services is highly dependent on the quality of sensed data (QoD), which is characterized by a number of quality attributes. DaaS provisioning is typically governed by a Service Level Agreement (SLA) between data consumers and DaaS providers. In this work, we propose a game-based approach for DaaS Provisioning, which relies on signaling based model for the negotiation of several QoD attributes between DaaS providers and data consumers. We consider that these entities are adaptive, rational, and able to negotiate the QoD offering even in the case of incomplete information about the other party. We use in the negotiation between the two parties a Q-learning algorithm for the signaling model and a Multi Attributes Decision Making (MADM) model to select the best signal. Moreover, we empirically validate the MADM model using Shannon's entropy. The results obtained in the case of a multi-stages negotiation scenario show the convergence towards the pooling equilibrium.