Towards a Green Future: Energy Efficient Conversational AI on the Edge
| dc.contributor.advisor | Qasem, Apan | |
| dc.contributor.author | Williams, Kaylee | |
| dc.date.accessioned | 2022-07-13T22:20:35Z | |
| dc.date.available | 2022-07-13T22:20:35Z | |
| dc.date.issued | 2022-05 | |
| dc.description.abstract | This project aims to show that emerging compute- and data-intensive workloads can be executed in an energy efficient way on low-power edge devices. To this end, I set up a cloud compute cluster consisting of three Raspberry Pis based on the ARM architecture. I then built a conversational AI app, a simple chatbot, to run on this cluster. My proposed framework reduces the energy cost in two ways (i) there is no need to communicate to back-end servers, saving bandwidth and (ii) all computation takes place on a low-power ARM processor, greatly reducing the carbon intensity at the cost of slightly diminished performance. Right now and in the future, complex applications can be created and run efficiently using the proposed framework. | |
| dc.description.department | Computer Science | |
| dc.format | Text | |
| dc.format.extent | 25 pages | |
| dc.format.medium | 1 file (.pdf) | |
| dc.identifier.citation | Williams, K. (2022). Towards a green future: Energy efficient conversational AI on the edge (Unpublished thesis). Texas State University, San Marcos, Texas. | |
| dc.identifier.uri | https://hdl.handle.net/10877/15973 | |
| dc.language.iso | en | |
| dc.subject | Raspberry Pi | |
| dc.subject | edge | |
| dc.subject | computing | |
| dc.subject | conversational AI | |
| dc.subject | chatbot | |
| dc.subject | energy efficient | |
| dc.subject | efficiency | |
| dc.title | Towards a Green Future: Energy Efficient Conversational AI on the Edge | |
| dc.type | Thesis | |
| thesis.degree.department | Honors College | |
| thesis.degree.discipline | Computer Science | |
| thesis.degree.grantor | Texas State University |