DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal Processor
In this paper, we introduce the optimal DVFS control, formulated as a sequential decision-making problem, which aims to maximize the overall energy efficiency of processing the specific image task on an ISP chip. We apply the Parameterized Action Markov Decision Process (PAMDP) to model the above op...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11027120/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849420357095653376 |
|---|---|
| author | Yang Du Wenhong Li Xiaoyang Zeng |
| author_facet | Yang Du Wenhong Li Xiaoyang Zeng |
| author_sort | Yang Du |
| collection | DOAJ |
| description | In this paper, we introduce the optimal DVFS control, formulated as a sequential decision-making problem, which aims to maximize the overall energy efficiency of processing the specific image task on an ISP chip. We apply the Parameterized Action Markov Decision Process (PAMDP) to model the above optimization problem and solve the PAMDP with the proposed DS-HPPO deep reinforcement learning algorithm. We design and implement a verification system for the DS-HPPO-based optimal DVFS control policy by leveraging a self-designed ISP chip. Compared with the energy efficiency under the default operating condition of the ISP chip, the proposed DS-HPPO-based optimal DVFS control policy achieves a 33.988% improvement in energy efficiency. Furthermore, when accounting for the impact of manufacturing process variations on performance, power consumption, and chip area, the experimental result clearly demonstrates our work’s effectiveness and superiority over state-of-the-art works. |
| format | Article |
| id | doaj-art-34d5f8b9bd0c4b0abdc4ac324f3d2a9a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-34d5f8b9bd0c4b0abdc4ac324f3d2a9a2025-08-20T03:31:46ZengIEEEIEEE Access2169-35362025-01-011312308312309610.1109/ACCESS.2025.357734411027120DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal ProcessorYang Du0https://orcid.org/0009-0009-6896-7342Wenhong Li1https://orcid.org/0000-0001-8948-5865Xiaoyang Zeng2https://orcid.org/0000-0003-3986-137XState Key Laboratory of Integrated Chips and Systems, School of Microelectronics, Fudan University, Shanghai, ChinaState Key Laboratory of Integrated Chips and Systems, School of Microelectronics, Fudan University, Shanghai, ChinaState Key Laboratory of Integrated Chips and Systems, School of Microelectronics, Fudan University, Shanghai, ChinaIn this paper, we introduce the optimal DVFS control, formulated as a sequential decision-making problem, which aims to maximize the overall energy efficiency of processing the specific image task on an ISP chip. We apply the Parameterized Action Markov Decision Process (PAMDP) to model the above optimization problem and solve the PAMDP with the proposed DS-HPPO deep reinforcement learning algorithm. We design and implement a verification system for the DS-HPPO-based optimal DVFS control policy by leveraging a self-designed ISP chip. Compared with the energy efficiency under the default operating condition of the ISP chip, the proposed DS-HPPO-based optimal DVFS control policy achieves a 33.988% improvement in energy efficiency. Furthermore, when accounting for the impact of manufacturing process variations on performance, power consumption, and chip area, the experimental result clearly demonstrates our work’s effectiveness and superiority over state-of-the-art works.https://ieeexplore.ieee.org/document/11027120/Energy efficiencydynamic voltage and frequency scalingimage signal processordeep reinforcement learningproximal policy optimizationDS-HPPO |
| spellingShingle | Yang Du Wenhong Li Xiaoyang Zeng DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal Processor IEEE Access Energy efficiency dynamic voltage and frequency scaling image signal processor deep reinforcement learning proximal policy optimization DS-HPPO |
| title | DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal Processor |
| title_full | DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal Processor |
| title_fullStr | DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal Processor |
| title_full_unstemmed | DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal Processor |
| title_short | DS-HPPO Deep Reinforcement Learning for Optimal DVFS Control on an Image Signal Processor |
| title_sort | ds hppo deep reinforcement learning for optimal dvfs control on an image signal processor |
| topic | Energy efficiency dynamic voltage and frequency scaling image signal processor deep reinforcement learning proximal policy optimization DS-HPPO |
| url | https://ieeexplore.ieee.org/document/11027120/ |
| work_keys_str_mv | AT yangdu dshppodeepreinforcementlearningforoptimaldvfscontrolonanimagesignalprocessor AT wenhongli dshppodeepreinforcementlearningforoptimaldvfscontrolonanimagesignalprocessor AT xiaoyangzeng dshppodeepreinforcementlearningforoptimaldvfscontrolonanimagesignalprocessor |