Parallel Cloud Computing Billing Model For Maximizing User’s Utility and Provider’s Cost-Efficiency

Presented cloud computing billing model is designed for maximizing value-adding throughput of a multiuser parallel computing platform across a set of users of the platform. The model enables maximally demand driven computing capacity allocation while guaranteeing each user application its contract-based assured minimum capacity access level whenever actually demanded. The billing model thus facilitates providing maximized application processing throughput per unit cost across the set of user applications dynamically sharing the platform. Technically, for any given user contract, on any given billing assessment period, the model determines a level of the given contract's demand for capacity that is met by the capacity allocated to it, and assess billables for the contract based on such met demand and the contract's assured access to the capacity, as well as billing rates on individual billing assessment periods for the met demand and the contract's assured access for the capacity.