Deep Reinforcement Learning for Energy-Efficient on the Heterogeneous Computing Architecture
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929609758474240 |
|---|---|
| author | Yu, Zheqi Zhang, Chao Machado, Pedro Zahid, Adnan Fernandez-Hart, Tim. Imran, Muhammad A. Abbasi, Qammer H. |
| author_facet | Yu, Zheqi Zhang, Chao Machado, Pedro Zahid, Adnan Fernandez-Hart, Tim. Imran, Muhammad A. Abbasi, Qammer H. |
| contents | The growing demand for optimal and low-power energy consumption paradigms for IOT devices has garnered significant attention due to their cost-effectiveness, simplicity, and intelligibility. In this article, an AI hardware energy-efficient framework to achieve optimal energy savings in heterogeneous computing through appropriate power consumption management is proposed. The deep reinforcement learning framework is employed, utilising the Actor-Critic architecture to provide a simple and precise method for power saving. The results of the study demonstrate the proposed approach's suitability for different hardware configurations, achieving notable energy consumption control while adhering to strict performance requirements. The evaluation of the proposed power-saving framework shows that it is more stable, and has achieved more than 34.6% efficiency improvement, outperforming other methods by more than 16%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_00168 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Deep Reinforcement Learning for Energy-Efficient on the Heterogeneous Computing Architecture Yu, Zheqi Zhang, Chao Machado, Pedro Zahid, Adnan Fernandez-Hart, Tim. Imran, Muhammad A. Abbasi, Qammer H. Signal Processing The growing demand for optimal and low-power energy consumption paradigms for IOT devices has garnered significant attention due to their cost-effectiveness, simplicity, and intelligibility. In this article, an AI hardware energy-efficient framework to achieve optimal energy savings in heterogeneous computing through appropriate power consumption management is proposed. The deep reinforcement learning framework is employed, utilising the Actor-Critic architecture to provide a simple and precise method for power saving. The results of the study demonstrate the proposed approach's suitability for different hardware configurations, achieving notable energy consumption control while adhering to strict performance requirements. The evaluation of the proposed power-saving framework shows that it is more stable, and has achieved more than 34.6% efficiency improvement, outperforming other methods by more than 16%. |
| title | Deep Reinforcement Learning for Energy-Efficient on the Heterogeneous Computing Architecture |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2302.00168 |