Mostrar el registro sencillo del ítem
Mean-Field Multi-Agent Contextual Bandit for Energy-Efficient Resource Allocation in vRANs
dc.contributor.author | Ayala-Romero, Jose A. | |
dc.contributor.author | Lo Schiavo, Leonardo | |
dc.contributor.author | Garcia-Saavedra, Andres | |
dc.contributor.author | Costa-Perez, Xavier | |
dc.date.accessioned | 2024-01-22T18:06:40Z | |
dc.date.available | 2024-01-22T18:06:40Z | |
dc.date.issued | 2024-05-20 | |
dc.identifier.uri | https://hdl.handle.net/20.500.12761/1785 | |
dc.description.abstract | Radio Access Network (RAN) virtualization, key for new-generation mobile networks, requires Hardware Accelerators (HAs) that swiftly process wireless signals from Base Stations (BSs) to meet stringent reliability targets. However, HAs are expensive and energy-hungry, which increases costs and has serious environmental implications. To address this problem, we gather data from our experimental platform and compare the performance and energy consumption of a HA (NVIDIA GPU V100) vs. a CPU (Intel Xeon Gold 6240R, 16 cores) for energy-friendly software processing. Based on the insights obtained from this data, we devise a strategy to offload workloads to HAs opportunistically to save energy while preserving reliability. This offloading strategy, however, needs to be configured in near-real-time for every BS sharing common computational resources. This renders a challenging multi-agent collaborative problem in which the number of involved agents (BSs) can be arbitrarily large and can change over time. Thus, we propose an efficient multi-agent contextual bandit algorithm called ECORAN, which applies concepts from mean field theory to be fully scalable. Using a real platform and traces from a production mobile network, we show that ECORAN can provide up to 40% energy savings with respect to the approach used today by the industry. | es |
dc.description.sponsorship | European Commission through Grant No. SNS-JU-101097083 (BeGREEN), 101139270 (ORIGAMI), and 101017109 (DAEMON) | es |
dc.language.iso | eng | es |
dc.title | Mean-Field Multi-Agent Contextual Bandit for Energy-Efficient Resource Allocation in vRANs | es |
dc.type | conference object | es |
dc.conference.date | 20-23 May 2024 | es |
dc.conference.place | Vancouver, Canada | es |
dc.conference.title | IEEE International Conference on Computer Communications | * |
dc.event.type | conference | es |
dc.pres.type | paper | es |
dc.type.hasVersion | AM | es |
dc.rights.accessRights | open access | es |
dc.acronym | INFOCOM | * |
dc.rank | A* | * |
dc.relation.projectName | BeGREEN (Beyond 5G Artificial Intelligence Assisted Energy Efficient Open Radio Access Network) | es |
dc.relation.projectName | ORIGAMI (Optimized resource integration and global architecture for mobile infrastructure for 6G) | es |
dc.relation.projectName | DAEMON (Network intelligence for aDAptive and sElf-Learning MObile Networks) | es |
dc.subject.keyword | vRAN | es |
dc.subject.keyword | Multi-agent systems | es |
dc.subject.keyword | Energy Efficiency | es |
dc.description.refereed | TRUE | es |
dc.description.status | inpress | es |