Metareasoning Approaches to Thermal Management During Image Processing
| dc.contributor.advisor | Herrmann, Jeffrey W | en_US |
| dc.contributor.author | Dawson, Michael Kenneth | en_US |
| dc.contributor.department | Mechanical Engineering | en_US |
| dc.contributor.publisher | Digital Repository at the University of Maryland | en_US |
| dc.contributor.publisher | University of Maryland (College Park, Md.) | en_US |
| dc.date.accessioned | 2022-06-15T05:46:43Z | |
| dc.date.available | 2022-06-15T05:46:43Z | |
| dc.date.issued | 2022 | en_US |
| dc.description.abstract | Resource-constrained electronic systems are present in many semi- and fully-autonomous systems and are tasked with computationally heavy tasks such as image processing. Without sufficient cooling, these tasks often increase device temperature up to a predetermined maximum, beyond which the task is slowed by the device firmware to maintain the maximum. This is done to avoid decreased processor lifespan due to thermal fatigue or catastrophic processor failure due to thermal overstress. This thesis describes a study that evaluated how well metareasoning can manage the central processing unit (CPU) temperature during image processing (object detection and classification) on two devices: a Raspberry Pi 4B and an NVIDIA Jetson Nano Developer Kit. Three policies that employ metareasoning were developed; one which maintains a constant image throughput, one which maintains a constant expected detection precision, and a third that trades between throughput and precision losses based on a user-defined parameter. All policies used the EfficientDet series of object detectors. Depending on the policy, these networks were either switched between, delayed, or both. This thesis also considered cases that used the system's built-in throttling policy to control the temperature. A policy was also created via reinforcement learning. The policy was able to adjust the detection precision and program throughput based on a set of states corresponding to the possible temperatures, neural networks, and processing delays. All three designed metareasoning policies were able to stabilize the device temperature without relying on thermal throttling. Additionally, the policy created through reinforcement learning was able to successfully stabilize the device temperature, though less consistently. These results suggest that a metareasoning-based approach to thermal management in image processing is able to provide a platform-agnostic and programmatic way to comply with constant or variable temperature constraints. | en_US |
| dc.identifier | https://doi.org/10.13016/bnma-qmkn | |
| dc.identifier.uri | http://hdl.handle.net/1903/28798 | |
| dc.language.iso | en | en_US |
| dc.subject.pqcontrolled | Mechanical engineering | en_US |
| dc.subject.pquncontrolled | Image Processing | en_US |
| dc.subject.pquncontrolled | Metareasoning | en_US |
| dc.subject.pquncontrolled | Thermal Management | en_US |
| dc.title | Metareasoning Approaches to Thermal Management During Image Processing | en_US |
| dc.type | Thesis | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Dawson_umd_0117N_22493.pdf
- Size:
- 26.65 MB
- Format:
- Adobe Portable Document Format