{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-1319"},"canonical_url":"https://search.dev.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-1319","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Reducing Cluster Power Consumption by Dynamically Suspending Idle Nodes","abstract":"Close to 1% of the world's electricity is consumed by computer servers. Given that the increased use of electricity raises costs and damages the environment, optimizing the world's computing infrastructure for power consumption is worthwhile. This thesis is one attempt at such an optimization. In particular, I began by building a cluster of 6 Intel Atom based low-power nodes to perform work analogous to data center clusters. Then, I installed a version of Hadoop modified with a novel power management system on the cluster. The power management system uses different algorithms to determine when to turn off idle nodes in the cluster. Using the experimental cluster running a modified Hadoop installation, I performed a series of experiments. These tests assessed various strategies for choosing nodes to suspend across a variety of workloads. The experiments validated that turning off idle nodes can yield power savings. While my experimental procedure caused the apparent throughput to significantly decrease, I argue that using more realistic workloads would have yielded much better throughput with slightly reduced power consumption. Additionally, my analysis of the results, show that the percentage power savings in a larger, more realistically sized cluster would be higher than shown in my experiments.","abstract_html":"Close to 1% of the world's electricity is consumed by computer servers. Given that the increased use of electricity raises costs and damages the environment, optimizing the world's computing infrastructure for power consumption is worthwhile. This thesis is one attempt at such an optimization. In particular, I began by building a cluster of 6 Intel Atom based low-power nodes to perform work analogous to data center clusters. Then, I installed a version of Hadoop modified with a novel power management system on the cluster. The power management system uses different algorithms to determine when to turn off idle nodes in the cluster. Using the experimental cluster running a modified Hadoop installation, I performed a series of experiments. These tests assessed various strategies for choosing nodes to suspend across a variety of workloads. The experiments validated that turning off idle nodes can yield power savings. While my experimental procedure caused the apparent throughput to significantly decrease, I argue that using more realistic workloads would have yielded much better throughput with slightly reduced power consumption. Additionally, my analysis of the results, show that the percentage power savings in a larger, more realistically sized cluster would be higher than shown in my experiments.","abstract_has_math":false,"creators":["Oppenheim, Brian Michael"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Phillip Nico"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-06-01T07:00:00Z","date_published":"2010-06-01T07:00:00Z","updated_at":"2026-07-24T01:32:50Z","subjects":["hadoop","cluster","power consumption","vovo","green computing","sustainability","OS and Networks","Other Computer Sciences","Systems Architecture"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2010.77"],"render_values":[{"text":"10.15368/theses.2010.77","href":"https://doi.org/10.15368/theses.2010.77","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/305","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Phillip Nico"]},{"key":"dc:creator","label":"Author","values":["Oppenheim, Brian Michael"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-06-07T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["hadoop","cluster","power consumption","vovo","green computing","sustainability","OS and Networks","Other Computer Sciences","Systems Architecture"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/305","10.15368/theses.2010.77"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Close to 1% of the world's electricity is consumed by computer servers. Given that the increased use of electricity raises costs and damages the environment, optimizing the world's computing infrastructure for power consumption is worthwhile. This thesis is one attempt at such an optimization. In particular, I began by building a cluster of 6 Intel Atom based low-power nodes to perform work analogous to data center clusters. Then, I installed a version of Hadoop modified with a novel power management system on the cluster. The power management system uses different algorithms to determine when to turn off idle nodes in the cluster. Using the experimental cluster running a modified Hadoop installation, I performed a series of experiments. These tests assessed various strategies for choosing nodes to suspend across a variety of workloads. The experiments validated that turning off idle nodes can yield power savings. While my experimental procedure caused the apparent throughput to significantly decrease, I argue that using more realistic workloads would have yielded much better throughput with slightly reduced power consumption. Additionally, my analysis of the results, show that the percentage power savings in a larger, more realistically sized cluster would be higher than shown in my experiments."]},{"key":"dc:title","label":"Title","values":["Reducing Cluster Power Consumption by Dynamically Suspending Idle Nodes"]}]}],"canonical_facts":{"dc:contributor":["Phillip Nico"],"dc:creator":["Oppenheim, Brian Michael"],"dc:date.available":["2010-06-07T07:00:00Z"],"dc:description.abstract":["Close to 1% of the world's electricity is consumed by computer servers. Given that the increased use of electricity raises costs and damages the environment, optimizing the world's computing infrastructure for power consumption is worthwhile. This thesis is one attempt at such an optimization. In particular, I began by building a cluster of 6 Intel Atom based low-power nodes to perform work analogous to data center clusters. Then, I installed a version of Hadoop modified with a novel power management system on the cluster. The power management system uses different algorithms to determine when to turn off idle nodes in the cluster. Using the experimental cluster running a modified Hadoop installation, I performed a series of experiments. These tests assessed various strategies for choosing nodes to suspend across a variety of workloads. The experiments validated that turning off idle nodes can yield power savings. While my experimental procedure caused the apparent throughput to significantly decrease, I argue that using more realistic workloads would have yielded much better throughput with slightly reduced power consumption. Additionally, my analysis of the results, show that the percentage power savings in a larger, more realistically sized cluster would be higher than shown in my experiments."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/305","10.15368/theses.2010.77"],"dc:subject":["hadoop","cluster","power consumption","vovo","green computing","sustainability","OS and Networks","Other Computer Sciences","Systems Architecture"],"dc:title":["Reducing Cluster Power Consumption by Dynamically Suspending Idle Nodes"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-07-24T01:32:50Z"}