面向边缘计算环境的智能手机背光调节机制
|
摘要
智能手机已成为日常生活中不可或缺的工具,被广泛地用于流媒体应用,而流媒体是一种资源消耗型的任务,手机单次充满电使用时间明显缩短.针对该问题,提出一种面向边缘计算环境的智能手机动态背光调节机制,在保证视觉效果的同时有效减少智能手机的能耗.该机制利用边缘计算节点的低延迟等优势,当视频数据传输到边缘计算节点时,通过分析视频帧像素亮度,确定视频帧在手机端显示时的局部最优背光亮度值.然后,从像素亮度和对比度两个方面进行背光亮度补偿,准确度量并减少亮度补偿造成的失真.最后,根据连续帧间的亮度关系,确定背光亮度保持不变的帧间隔.实验结果表明,在无显著增加延迟和视频失真的前提下,该机制能降低手机端20%～30%的能耗.
Smartphone has become an indispensable tool in our daily life,and been widely used for accessing media stream. However,the media-stream is a kind of resource consuming task,and the battery life on a smartphone is significantly shortened after each full charging. To address this challenge,this paper proposes an edge-computing based backlight scaling for smart phone,focusing on effectively reducing smartphone's energy consumption while guaranteeing visual effect. This mechanism takes advantage of edge computing in terms of computing ability,low delay and so on. Upon receiving video frames,edge-computing node determines locally optimized backlight level of video frame when displayed on smartphone through analysis of pixel luminance. Then,backlight brightness compensation is performed with pixel luminance adjustment and contrast enhancement. Correspondingly,the distortion caused by backlight brightness compensation can be accurately measured and reduced. Finally,the interval(in term of number of frames)where the backlight level remain constant is determined according to the relation between consecutive frames. Our experiment results show that this mechanism can reduce smartphone's energy consumption by 20% to 30%,without significantly increasing the delay and video distortion.
Smartphone has become an indispensable tool in our daily life,and been widely used for accessing media stream. However,the media-stream is a kind of resource consuming task,and the battery life on a smartphone is significantly shortened after each full charging. To address this challenge,this paper proposes an edge-computing based backlight scaling for smart phone,focusing on effectively reducing smartphone's energy consumption while guaranteeing visual effect. This mechanism takes advantage of edge computing in terms of computing ability,low delay and so on. Upon receiving video frames,edge-computing node determines locally optimized backlight level of video frame when displayed on smartphone through analysis of pixel luminance. Then,backlight brightness compensation is performed with pixel luminance adjustment and contrast enhancement. Correspondingly,the distortion caused by backlight brightness compensation can be accurately measured and reduced. Finally,the interval(in term of number of frames)where the backlight level remain constant is determined according to the relation between consecutive frames. Our experiment results show that this mechanism can reduce smartphone's energy consumption by 20% to 30%,without significantly increasing the delay and video distortion.
引文
[1] Raffin E,Hamidouche W,Nogues E,et al. Scalable HEVC decoder for mobile devices:trade-off betw een energy consumption and quality[C]. Proceedings of the IEEE International Conference on Design and Architectures for Signal and Image Processing(DASIP),2017:18-25.
[2] Uitto M. Energy consumption evaluation of H. 264 and HEVC video encoders in high-resolution live streaming[C]. Proceedings of the IEEE International Conference on Wireless and M obile,Computing Netw orking and Communications(WiM ob),2016:1-7.
[3] Leu J S,Tung N H,Liu C Y. Non-parametric RSS prediction based energy saving scheme for moving smartphones[J]. IEEE Transactions on Computers,2014,63(7):1793-1801.
[4] Ismail M,Zhuang W,Elhedhli S. Energy and content aware multihoming video transmission in heterogeneous networks[J]. IEEE Transactions on Wireless Communications,2013,12(7):3600-3610.
[5] Yan Z,Chen C W. RnB:rate and brightness adaptation for rate-distortion-energy tradeoff in HTTP adaptive streaming over mobile devices[C]. Proceedings of the ACM International Conference on M obile Computing and Netw orking(M obiCom),2016:308-319.
[6] Lin C H,Hsiu P C,Hsieh C K. Dynamic backlight scaling optimization:a cloud-based energy-saving service for mobile streaming applications[J]. IEEE Transactions on Computers,2014,63(2):335-348.
[7] Carroll A,Heiser G. An analysis of power consumption in a smartphone[C]. Proceedings of the 2010 Usenix Conference on Usenix Technical Conference,2010:21-24.
[8] Shi Xiao-juan. The design and implementation of low-power display subsystem on intelligent mobile terminal[D]. Nanjing:Southeast University,2010.
[9] Satyanarayanan M,Schuster R,Ebling M,et al. An open ecosystem for mobile-cloud convergence[J]. Communications M agazine IEEE,2015,53(3):63-70.
[10] Alvi S A,Afzal B,Shah G A,et al. Internet of multimedia things:Vision and challenges[J]. Ad Hoc Netw orks,2015,33:87-111.
[11] Liu Y,Xiao M,Dong M,et al. Content-adaptive display power saving for internet video applications on mobile devices[J]. ACM Transactions on M ultimedia Computing Communications&Applications,2016,12(5s):84-85.
[12] Xiao M,Liu Y,Guo L,et al. Reducing display power consumption for real-time video calls on mobile devices[C]. Proceedings of IEEE/ACM International Symposium on Low Pow er Electronics and Design(ISLPED),2015:285-290.
[13] Liu Y,Xiao M,Dong M,et al. GoCAD:GPU-assisted online content-adaptive display pow er saving for mobile devices in internet streaming[C]. Proceedings of International Conference on World Wide Web(WWW),2016:1329-1338.
[14] Liu Q,Yan Z,Chen C W. Cloud-based video streaming with systematic mobile display energy saving:rate-distortion-display energy profiling[C]. Proceedings of IEEE International Conference on Image Processing(ICIP),2016:1504-1508.
[15] Shi Wei-song,Sun Hui,Cao Jie,et al. Edge computing:an emerging computing model for internet of everything era[J]. Journal of Computing Research and Development,2017,54(5):907-924.
[16] Yan Z,Xue J,Chen C W. Prius:hybrid edge cloud and client adaptation for HTTP adaptive streaming in cellular netw orks[J]. IEEE Transactions on Circuits&Systems for Video Technology,2017,(99):1-4.
[17] Thomos N,Boulgouris N V,Strintzis M G. Optimized transmission of JPEG2000 streams over w ireless channels[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2006,15(1):54-67.
[18] Wang Z,Bovik A C,Sheikh H R,et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2004,13(4):600-601.
[19] Sun W,Zhai G,Min X,et al. Dynamic backlight scaling considering ambient luminance for mobile energy saving[C]. Proceedings of the IEEE International Conference on M ultimedia and Expo(ICM E),2017:25-30.
[8]石晓娟.智能移动终端显示子系统低功耗的设计与实现[D].南京:东南大学,2010.
[15]施巍松,孙辉,曹杰,等.边缘计算:万物互联时代新型计算模型[J].计算机研究与发展,2017,54(5):907-924.
1 https://developer.android.com/training/monitoring-device-state/index.html.
2 https://github.com/ossrs/srs
3 http://ffmpeg.org
[2] Uitto M. Energy consumption evaluation of H. 264 and HEVC video encoders in high-resolution live streaming[C]. Proceedings of the IEEE International Conference on Wireless and M obile,Computing Netw orking and Communications(WiM ob),2016:1-7.
[3] Leu J S,Tung N H,Liu C Y. Non-parametric RSS prediction based energy saving scheme for moving smartphones[J]. IEEE Transactions on Computers,2014,63(7):1793-1801.
[4] Ismail M,Zhuang W,Elhedhli S. Energy and content aware multihoming video transmission in heterogeneous networks[J]. IEEE Transactions on Wireless Communications,2013,12(7):3600-3610.
[5] Yan Z,Chen C W. RnB:rate and brightness adaptation for rate-distortion-energy tradeoff in HTTP adaptive streaming over mobile devices[C]. Proceedings of the ACM International Conference on M obile Computing and Netw orking(M obiCom),2016:308-319.
[6] Lin C H,Hsiu P C,Hsieh C K. Dynamic backlight scaling optimization:a cloud-based energy-saving service for mobile streaming applications[J]. IEEE Transactions on Computers,2014,63(2):335-348.
[7] Carroll A,Heiser G. An analysis of power consumption in a smartphone[C]. Proceedings of the 2010 Usenix Conference on Usenix Technical Conference,2010:21-24.
[8] Shi Xiao-juan. The design and implementation of low-power display subsystem on intelligent mobile terminal[D]. Nanjing:Southeast University,2010.
[9] Satyanarayanan M,Schuster R,Ebling M,et al. An open ecosystem for mobile-cloud convergence[J]. Communications M agazine IEEE,2015,53(3):63-70.
[10] Alvi S A,Afzal B,Shah G A,et al. Internet of multimedia things:Vision and challenges[J]. Ad Hoc Netw orks,2015,33:87-111.
[11] Liu Y,Xiao M,Dong M,et al. Content-adaptive display power saving for internet video applications on mobile devices[J]. ACM Transactions on M ultimedia Computing Communications&Applications,2016,12(5s):84-85.
[12] Xiao M,Liu Y,Guo L,et al. Reducing display power consumption for real-time video calls on mobile devices[C]. Proceedings of IEEE/ACM International Symposium on Low Pow er Electronics and Design(ISLPED),2015:285-290.
[13] Liu Y,Xiao M,Dong M,et al. GoCAD:GPU-assisted online content-adaptive display pow er saving for mobile devices in internet streaming[C]. Proceedings of International Conference on World Wide Web(WWW),2016:1329-1338.
[14] Liu Q,Yan Z,Chen C W. Cloud-based video streaming with systematic mobile display energy saving:rate-distortion-display energy profiling[C]. Proceedings of IEEE International Conference on Image Processing(ICIP),2016:1504-1508.
[15] Shi Wei-song,Sun Hui,Cao Jie,et al. Edge computing:an emerging computing model for internet of everything era[J]. Journal of Computing Research and Development,2017,54(5):907-924.
[16] Yan Z,Xue J,Chen C W. Prius:hybrid edge cloud and client adaptation for HTTP adaptive streaming in cellular netw orks[J]. IEEE Transactions on Circuits&Systems for Video Technology,2017,(99):1-4.
[17] Thomos N,Boulgouris N V,Strintzis M G. Optimized transmission of JPEG2000 streams over w ireless channels[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2006,15(1):54-67.
[18] Wang Z,Bovik A C,Sheikh H R,et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2004,13(4):600-601.
[19] Sun W,Zhai G,Min X,et al. Dynamic backlight scaling considering ambient luminance for mobile energy saving[C]. Proceedings of the IEEE International Conference on M ultimedia and Expo(ICM E),2017:25-30.
[8]石晓娟.智能移动终端显示子系统低功耗的设计与实现[D].南京:东南大学,2010.
[15]施巍松,孙辉,曹杰,等.边缘计算:万物互联时代新型计算模型[J].计算机研究与发展,2017,54(5):907-924.
1 https://developer.android.com/training/monitoring-device-state/index.html.
2 https://github.com/ossrs/srs
3 http://ffmpeg.org