Energy-Adaptive Checkpoint-Free Intermittent Inference for Low Power Energy Harvesting Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916647884816384 |
|---|---|
| author | Islam, Sahidul Wei, Wei Banarjee, Jishnu Pan, Chen |
| author_facet | Islam, Sahidul Wei, Wei Banarjee, Jishnu Pan, Chen |
| contents | Deep neural network (DNN) inference in energy harvesting (EH) devices poses significant challenges due to resource constraints and frequent power interruptions. These power losses not only increase end-to-end latency, but also compromise inference consistency and accuracy, as existing checkpointing and restore mechanisms are prone to errors. Consequently, the quality of service (QoS) for DNN inference on EH devices is severely impacted. In this paper, we propose an energy-adaptive DNN inference mechanism capable of dynamically transitioning the model into a low-power mode by reducing computational complexity when harvested energy is limited. This approach ensures that end-to-end latency requirements are met. Additionally, to address the limitations of error-prone checkpoint-and-restore mechanisms, we introduce a checkpoint-free intermittent inference framework that ensures consistent, progress-preserving DNN inference during power failures in energy-harvesting systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06663 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Energy-Adaptive Checkpoint-Free Intermittent Inference for Low Power Energy Harvesting Systems Islam, Sahidul Wei, Wei Banarjee, Jishnu Pan, Chen Computational Engineering, Finance, and Science Deep neural network (DNN) inference in energy harvesting (EH) devices poses significant challenges due to resource constraints and frequent power interruptions. These power losses not only increase end-to-end latency, but also compromise inference consistency and accuracy, as existing checkpointing and restore mechanisms are prone to errors. Consequently, the quality of service (QoS) for DNN inference on EH devices is severely impacted. In this paper, we propose an energy-adaptive DNN inference mechanism capable of dynamically transitioning the model into a low-power mode by reducing computational complexity when harvested energy is limited. This approach ensures that end-to-end latency requirements are met. Additionally, to address the limitations of error-prone checkpoint-and-restore mechanisms, we introduce a checkpoint-free intermittent inference framework that ensures consistent, progress-preserving DNN inference during power failures in energy-harvesting systems. |
| title | Energy-Adaptive Checkpoint-Free Intermittent Inference for Low Power Energy Harvesting Systems |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2503.06663 |