English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Small devices are frequently used in IoT and smart-city applications toperform periodic dedicated tasks with soft deadlines. This work focuses ondeveloping methods to derive efficient power-management methods for periodictasks on small devices. We first study the limitations of the existing Linuxbuilt-in methods used in small devices. We illustrate three typicalworkload/system patterns that are challenging to manage with Linux's built-insolutions. We develop a reinforcement-learning-based technique with temporalencoding to derive an effective DVFS governor even with the presence of thethree system patterns. The derived governor uses only one performance counter,the same as the built-in Linux mechanism, and does not require an explicit taskmodel for the workload. We implemented a prototype system on the Nvidia JetsonNano Board and experimented with it with six applications, including twoself-designed and four benchmark applications. Under different deadlineconstraints, our approach can quickly derive a DVFS governor that can adapt toperformance requirements and outperform the built-in Linux approach in energysaving. On Mibench workloads, with performance slack ranging from 0.04 s to 0.4s, the proposed method can save 3% - 11% more energy compared to Ondemand.AudioReg and FaceReg applications tested have 5%- 14% energy-savingimprovement. We have open-sourced the implementation of our in-kernel quantizedneural network engine. The codebase can be found at:https://github.com/coladog/tinyagent.

CPU frequency scheduling of real-time applications on embedded devices with temporal encoding-based deep reinforcement learning