As artificial intelligence (AI) applications become more common on the edge of networks, like Raspberry Pi servers, it is crucial to optimize their energy use. This research project investigates how AI algorithms affect energy efficiency and resource usage on Raspberry Pi servers. Two models were created: one predicts resource usage, and the other predicts power consumption of AI algorithms on Raspberry Pi. Several factors are considered like CPU and memory use, algorithm speed, dataset size, and types of algorithms and datasets. Using regression-based methods, we model how these factors affect energy use. By converting categorical factors into numerical ones, we develop models that describe the relationship between factors and energy use on Raspberry Pi. This research contributes practical tools that empower developers to assess the energy impact of AI deployments on edge servers, offering unique insights that are not readily available through solely profiling-based approaches. Our work facilitates scheduling AI applications on edge servers for energy efficiency without compromising performance.
","abstract_html":"<p>As artificial intelligence (AI) applications become more common on the edge of networks, like Raspberry Pi servers, it is crucial to optimize their energy use. This research project investigates how AI algorithms affect energy efficiency and resource usage on Raspberry Pi servers. Two models were created: one predicts resource usage, and the other predicts power consumption of AI algorithms on Raspberry Pi. Several factors are considered like CPU and memory use, algorithm speed, dataset size, and types of algorithms and datasets. Using regression-based methods, we model how these factors affect energy use. By converting categorical factors into numerical ones, we develop models that describe the relationship between factors and energy use on Raspberry Pi. This research contributes practical tools that empower developers to assess the energy impact of AI deployments on edge servers, offering unique insights that are not readily available through solely profiling-based approaches. Our work facilitates scheduling AI applications on edge servers for energy efficiency without compromising performance.</p>","abstract_has_math":false,"creators":["Bhagavathula, Vamsi Krishna"],"institution":null,"degree_name":"Master of Science","degree_level":"Thesis","degree_discipline":"TSYS School of Computer Science","degree_department":null,"school":null,"contributors":["Yi Zhou","Rania Hodhod","Lixin Wang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-01-01T08:00:00Z","date_published":"2024-01-01T08:00:00Z","updated_at":"2026-07-24T01:44:41Z","subjects":["Edge computing","Energy efficiency","Predictive modeling","Machine learning regression","Resource utilization","AI algorithms.","Computer Sciences"],"languages":["english"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://csuepress.columbusstate.edu/theses_dissertations/511","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Yi Zhou","Rania Hodhod","Lixin Wang"]},{"key":"dc:creator","label":"Author","values":["Bhagavathula, Vamsi Krishna"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2024-04-18T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["TSYS School of Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Edge computing","Energy efficiency","Predictive modeling","Machine learning regression","Resource utilization","AI algorithms.","Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["english"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://csuepress.columbusstate.edu/theses_dissertations/511"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As artificial intelligence (AI) applications become more common on the edge of networks, like Raspberry Pi servers, it is crucial to optimize their energy use. This research project investigates how AI algorithms affect energy efficiency and resource usage on Raspberry Pi servers. Two models were created: one predicts resource usage, and the other predicts power consumption of AI algorithms on Raspberry Pi. Several factors are considered like CPU and memory use, algorithm speed, dataset size, and types of algorithms and datasets. Using regression-based methods, we model how these factors affect energy use. By converting categorical factors into numerical ones, we develop models that describe the relationship between factors and energy use on Raspberry Pi. This research contributes practical tools that empower developers to assess the energy impact of AI deployments on edge servers, offering unique insights that are not readily available through solely profiling-based approaches. Our work facilitates scheduling AI applications on edge servers for energy efficiency without compromising performance.
"]},{"key":"dc:title","label":"Title","values":["Towards Energy-Efficient Edge Computing for tiny AI Applications"]}]}],"canonical_facts":{"dc:contributor":["Yi Zhou","Rania Hodhod","Lixin Wang"],"dc:creator":["Bhagavathula, Vamsi Krishna"],"dc:date.available":["2024-04-18T07:00:00Z"],"dc:description.abstract":["As artificial intelligence (AI) applications become more common on the edge of networks, like Raspberry Pi servers, it is crucial to optimize their energy use. This research project investigates how AI algorithms affect energy efficiency and resource usage on Raspberry Pi servers. Two models were created: one predicts resource usage, and the other predicts power consumption of AI algorithms on Raspberry Pi. Several factors are considered like CPU and memory use, algorithm speed, dataset size, and types of algorithms and datasets. Using regression-based methods, we model how these factors affect energy use. By converting categorical factors into numerical ones, we develop models that describe the relationship between factors and energy use on Raspberry Pi. This research contributes practical tools that empower developers to assess the energy impact of AI deployments on edge servers, offering unique insights that are not readily available through solely profiling-based approaches. Our work facilitates scheduling AI applications on edge servers for energy efficiency without compromising performance.
"],"dc:identifier":["https://csuepress.columbusstate.edu/theses_dissertations/511"],"dc:language":["english"],"dc:subject":["Edge computing","Energy efficiency","Predictive modeling","Machine learning regression","Resource utilization","AI algorithms.","Computer Sciences"],"dc:title":["Towards Energy-Efficient Edge Computing for tiny AI Applications"],"thesis:degree_discipline":["TSYS School of Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science"]},"updated_at":"2026-07-24T01:44:41Z"}