Abstract: One embodiment of the present invention provides a system that models customer behavior in a multi-choice service environment. The system constructs a probability density function f to represent probabilities of service-level choices made by customers, wherein the probability density function is a function of functional variables u?(d) and p(d); u?(d) is a utility function for a specific customer type indexed by vector ?; p(d) is a given price curve which specifies a relationship between service levels offered by a service provider and corresponding prices for the offered service levels; and u?(d) and p(d) are both functions of the offered service levels d. The system then obtains a distribution function ?(?) which specifies a probability distribution of different customer types ?. Next, the system obtains a service level-choice distribution for a population of customers as a function of a given price curve based on the probability density function f and ?(?).

Abstract: One embodiment of the present invention provides a system that assigns jobs to a system containing a number of central processing units (CPUs). During operation, the system captures a current state of the system, which describes available resources on the system, characteristics of jobs currently being processed, and characteristics of new jobs waiting to be assigned. The system then uses the system state to estimate a long-term benefit to the system of not oversubscribing the system. If the benefit from oversubscribing the system with a new job exceeds the benefit from not oversubscribing the system, the system oversubscribes the system with the new job.

Abstract: A method for maximizing revenue generated from a plurality of service level agreements (SLAs) that includes receiving a first subset of the plurality of SLAs for executing a first plurality of jobs, wherein each SLA in the first subset specifies a first maximum requested delay that is greater than an initial minimum offered delay, and wherein a price of each SLA in the first subset is defined by the maximum requested delay and a price/delay function, calculating a first expected revenue from executing the first subset, and optimizing a second subset of the plurality of SLAs by replacing the initial minimum offered delay on the initial price/delay function with a new minimum offered delay based on the expected revenue, wherein each SLA in the second subset specifies a second maximum requested delay that is greater than the new minimum offered delay.

Abstract: One embodiment of the present invention provides a system that selects bases to form a regression model for cache performance. During operation, the system receives empirical data for a cache rate. The system also receives derivative constraints for the cache rate. Next, the system obtains candidate bases that satisfy the derivative constraints. For each of these candidate bases, the system: (1) computes an aggregate error E incurred using the candidate basis over the empirical data; (2) computes an instability measure I of an extrapolation fit for using the candidate basis over an extrapolation region; and then (3) computes a selection criterion F for the candidate basis, wherein F is a function of E and I. Finally, the system minimizes the selection criterion F across the candidate bases to select the basis used for the regression model.

Abstract: One embodiment of the present invention provides a system that tunes state-based scheduling policies, wherein the system contains a number of central processing units (CPUs). During operation, the system recurrently estimates a long-term benefit to the system by feeding a system state as input to a parametric value function and computing an output from the parametric value function. The system makes scheduling decisions for the CPUs based on the estimated long-term benefit to the system. The system also tunes a parameter of the parametric value function based on current and previously estimated long-term benefit to the system, thereby facilitating more effective scheduling policies.