A study on energy used to deliver H.264/AVC and H.265/HEVC video content

We propose an end-to-end approach to describe the energy usage of video delivery within a content delivery framework, and use this to investigate the energy usage behavior of two popular coding schemes, namely, H.264/AVC and H.265/HEVC. Our study based on the proposed model is backed up by measurements of encoding and decoding energy usage of a sample video and shows that, from an end-to-end perspective, taking into account all the elements of a content delivery network, neither of the coding formats is always dominant in terms of energy saving. We also find that the popularity of video content is a key parameter for predicting which encoding scheme saves most energy. In particular, we find that H.265 encoded content results in lower energy usage if the content is highly popular. On the other hand, for a content with predicted low popularity, more saving is achieved if H.264/AVC is used. This lead us to calculate a hybrid content delivery scheme, where the contents with low popularity are encoded and delivered in H.264/AVC format, whereas content of high popularity are encoded and delivered in the H.265/HEVC format. Also, our findings offer new insights into which elements of energy usage should be the focus of future research.

[1]  Zhan Ma,et al.  On Complexity Modeling of H.264/AVC Video Decoding and Its Application for Energy Efficient Decoding , 2011, IEEE Transactions on Multimedia.

[2]  David Flynn,et al.  HEVC Complexity and Implementation Analysis , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[3]  Eric Senn,et al.  A methodology for performance/energy consumption characterization and modeling of video decoding on heterogeneous SoC and its applications , 2015, J. Syst. Archit..

[4]  Lifeng Sun,et al.  A Joint Online Transcoding and Delivery Approach for Dynamic Adaptive Streaming , 2015, IEEE Transactions on Multimedia.

[5]  Daniel C. Kilper,et al.  On the Energy Efficiency of Content Delivery Architectures , 2011, 2011 IEEE International Conference on Communications Workshops (ICC).

[6]  Chong-Min Kyung,et al.  Energy-Aware System Design: Algorithms and Architectures , 2011 .

[7]  Giuseppe Bianchi,et al.  Per-Frame Energy Consumption in 802.11 Devices and Its Implication on Modeling and Design , 2015, IEEE/ACM Transactions on Networking.

[8]  R.S. Tucker,et al.  Architectures for energy-efficient IPTV networks , 2009, 2009 Conference on Optical Fiber Communication - incudes post deadline papers.

[9]  Ricardo L. de Queiroz,et al.  Energy-constrained real-time H.264/AVC video coding , 2013, ICASSP.

[10]  Mehmet Karaca,et al.  An energy consumption model for 802.11ac access points , 2014, 2014 22nd International Conference on Software, Telecommunications and Computer Networks (SoftCOM).

[11]  Elaine Wong,et al.  Energy efficient content distribution for VoD services , 2011, 2011 Optical Fiber Communication Conference and Exposition and the National Fiber Optic Engineers Conference.

[12]  Erwan Nogues,et al.  A DVFS based HEVC decoder for energy-efficient software implementation on embedded processors , 2015, 2015 IEEE International Conference on Multimedia and Expo (ICME).