Name
Abstract | ||
|---|---|---|
While Dynamic Voltage Scaling (DVS) and Dynamic Power Management (DPM) techniques are widely used in real-time embedded applications, their complex interaction is not fully understood. In this research effort, we consider the problem of minimizing the expected energy consumption on settings where the workload is known only probabilistically. By adopting a system-level power model, we formally show how the optimal processing frequency can be computed efficiently for a real-time embedded application that can use multiple devices during its execution, while still meeting the timing constraints. Our evaluations indicate that the new technique provides clear (up to 35%) energy gains over the existing solutions that are proposed for deterministic workloads. Moreover, in a non-negligible part of the parameter spectrum, the algorithm's performance is shown to be close to that of a clairvoyant algorithm that can minimize the energy consumption with the advance knowledge about the exact workload. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1145/1687399.1687484 | ICCAD |
Keywords | Field | DocType |
energy gain,advance knowledge,clairvoyant algorithm,real-time embedded application,energy consumption,complex interaction,optimal integration,expected energy consumption,dynamic voltage scaling,exact workload,dynamic power management,bismuth,real time systems,probabilistic logic,data mining,spectrum,reliability | Dynamic voltage scaling,Dynamic power management,Computer science,Workload,Voltage control,Embedded applications,Power model,Real-time computing,Probabilistic logic,Energy consumption | Conference |
Citations | PageRank | References |
16 | 0.69 | 19 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Baoxian Zhao | 1 | 211 | 7.69 |
| Hakan Aydin | 2 | 1218 | 61.97 |