RT Journal Article
T1 Resource management for power-constrained HEVC transcoding using reinforcement learning
A1 Costero Valero, Luis María
A1 Iranfar, Arman
A1 Zapater, Marina
A1 Atienza, David
A1 Olcoz Herrero, Katzalin
AB The advent of online video streaming applications and services along with the users' demand for high-quality contents require High Efficiency Video Coding (HEVC), which provides higher video quality and more compression at the cost of increased complexity. On one hand, HEVC exposes a set of dynamically tunable parameters to provide trade-offs among Quality-of-Service (QoS), performance, and power consumption of multi-core servers on the video providers' data center. On the other hand, resource management of modern multi-core servers is in charge of adapting system-level parameters, such as operating frequency and multithreading, to deal with concurrent applications and their requirements. Therefore, efficient multi-user HEVC streaming necessitates joint adaptation of application- and system-level parameters. Nonetheless, dealing with such a large and dynamic design space is challenging and difficult to address through conventional resource management strategies. Thus, in this work, we develop a multi-agent Reinforcement Learning framework to jointly adjust application- and system-level parameters at runtime to satisfy the QoS of multi-user HEVC streaming in power-constrained servers. In particular, the design space, composed of all design parameters, is split into smaller independent sub-spaces. Each design sub-space is assigned to a particular agent so that it can explore it faster, yet accurately. The benefits of our approach are revealed in terms of adaptability and quality (with up to to 4x improvements in terms of QoS when compared to a static resource management scheme), and learning time (6 x faster than an equivalent mono-agent implementation). Finally, we show that the power-capping techniques formulated outperform the hardware-based power capping with respect to quality.
PB IEEE Computer  Society
SN 1045-9219
YR 2020
FD 2020-12-01
LK https://hdl.handle.net/20.500.14352/6543
UL https://hdl.handle.net/20.500.14352/6543
LA eng
NO ©2020 IEEE Computer Society This work was supported by the EU (FEDER) and Spanish MINECO (RTI2018-093684-B-I00), MECD (FPU15/02050), CM(S2018/TCS-4423), and UCM (PR65/19-22445), the ERC Consolidator Grant COMPUSAPIEN (GA No. 725657), the H2020 RECIPE project (GA No. 801137), and the H2020 DeepHealth project (GA No. 825111)
NO Unión Europea. Horizonte 2020
NO Ministerio de Economía y Competitividad (MINECO)/FEDER
NO Ministerio de Educación, Cultura y Deporte (MECD)
NO Comunidad de Madrid
NO Universidad Complutense de Madrid
DS Docta Complutense
RD 3 may 2024