A Bayesian Business Model for Video-Call Billing for End-to-End QoS Provision

Wireless communications and IP networks will evolve into a new converged vision, which is called "beyond the third generation," where charging and billing will be essential tools for customer care to fight competition and to assure operator's revenue. This contribution proposes a business model for video-call billing founded on Bayes' decision testing. It is based on the end-to-end Quality of Service (QoS) estimated by exploiting the tracing watermarking procedure, which has recently been introduced into the literature. In particular, we employ the watermark embedded in each transmitted video sequence to monitor the QoS of the communication link and adequately charge the calling user, depending on the received video quality. Adopting such a Bayesian business model, we translate the network operator's paradigm of "pay as you talk (and watch)" to "pay how you talk (and watch)," maximizing the operator's profit under a constrained video quality for end users. Wide simulation trials are conducted to characterize the effectiveness of the proposed method, using different business scenarios, confirming the validity of such an approach.