Workload uncertainty characterization and adaptive frequency scaling for energy minimization of embedded systems

A primary design optimization objective for battery-operated embedded systems is to minimize the energy consumption of applications while satisfying their performance requirement. A system-level approach to this problem is to scale the frequency of the hardware based on the readings obtained from the hardware performance monitors. We show that the performance monitor readings contain uncertainty, which becomes prominent when applications are executed in a multicore environment. These uncertainties (termed as "noise") are attributed to factors such as cache contention and DRAM access time, that are very difficult to predict dynamically. In this paper, we propose a multinomial logistic regression model, which combines probabilistic interpretation with maximum likelihood (ML) estimation to classify an incoming noisy workload, at run-time, into a finite set of classes. Every workload class corresponds to a frequency pre-determined using an appropriate training set and results in minimum energy consumption. The classifier incorporates (1) "noise" with arbitrary probability distribution to estimate the actual frame workload; and (2) the frequency switching overhead, neither of which are considered in any of the existing approaches. The classified frequency is applied on the processing cores to execute the workload. The proposed approach is engineered into an embedded multicore system and is validated with a set of standard multimedia applications. Results demonstrate that the proposed approach minimizes energy consumption by an average 20% as compared to the existing techniques