This Article 
 Bibliographic References 
 Add to: 
Application-Support Particle Filter for Dynamic Voltage Scaling of Multimedia Applications
Sept. 2012 (vol. 61 no. 9)
pp. 1256-1269
Jae-Beom Lee, Yonsei University, Seoul
Myoung-Jin Kim, Yonsei University, Seoul
Sungroh Yoon, Korea University, Seoul
Eui-Young Chung, Yonsei University, Seoul
Dynamic Voltage and Frequency Scaling (DVFS) is an effective low-power technique for real-time workloads. Its effectiveness critically depends on the accurate prediction of the task execution time. Many DVFS approaches have been proposed, but they are insufficient for highly nonstationary workloads. Several recent DVFS techniques adopted adaptive filters to improve accuracy. However, their improvement was rather limited, since they mainly focused on applying a filter framework to the target application without tuning it. We address this issue by proposing Particle Filter (PF)-based video decoders (MPEG2 and H.264) which exploit application-specific characteristics. More specifically, our PF-based video decoders utilize the size of each frame for the prediction of its decoding time. Compared to previous work, the PF is more suitable for our purpose, since it achieves higher prediction accuracy, even for highly nonstationary workloads such as H.264 clips. Our results show that the energy saved by the proposed approach is comparable to that of the ideal policy called oracle-DVFS, while the existing methods we tested were far inferior to oracle-DVFS in terms of H.264 video decoding. Additionally, when our method was used, only 0.40 and 6.88 percent of the frames missed their deadlines with negligible computational overhead for MPEG and H.264, respectively.

[1] L. Benini and G. De Micheli, Dynamic Power Management: Design Techniques and CAD Tools. Kluwer, 1997.
[2] G. Welch and G. Bishop, “An Introduction to the Kalman Filter,” technical report, Univ. of North Carolina at Chapel Hill, 1995.
[3] D. Shin, J. Kim, and S. Lee, “Intra-Task Voltage Scheduling for Low-Energy Hard Real-Time Applications,” IEEE Design and Test of Computers, vol. 18, no. 2, pp. 20-30, Mar. 2001.
[4] D. Shin and J. Kim, “A Profile-Based Energy-Efficient Intra-Task Voltage Scheduling Algorithm for Hard Real-Time Applications,” Proc. Int'l Symp. Low Power Embedded Design, pp. 271-274, 2001.
[5] J. Seo, T. Kim, and K.-S. Chung, “Profile-Based Optimal Intra-Task Voltage Scheduling for Hard Real-Time Applications,” Proc. Design Automation Conf. (DAC), pp. 87-92, 2004.
[6] A.C. Bavier, A.B. Montz, and L.L. Peterson, “Prediction MPEG Decoding Time,” Proc. ACM SIGMETRICS Performance Evaluation Rev., pp. 131-140, June 1998.
[7] J. Pouwelse, K. Langendoen, I. Lagendijk, and H. Sips, “Power-Aware Video Decoding,” Proc. Picture Coding Symp., pp. 303-306, 2001.
[8] S. Hong, S. Yoo, B. Bin, K.M. Choi, S.K. Eo, and T. Kim, “Dynamic Voltage Scaling of Supply and Body Bias Exploiting Software Runtime Distribution,” Proc. Conf. Design, Automation and Test in Europe, pp. 242-247, Mar. 2008.
[9] C. Xian, Y.-H. Lu, and Z. Li, “Dynamic Voltage Scaling for Multitasking Real-Time Systems with Uncertain Execution Time,” IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems, vol. 27, no. 8, pp. 1467-1478, Aug. 2008.
[10] M.S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A Tutorial on Particle Filters for On-Line Nonliear/Non-Gaussian Bayesian Tracking,” IEEE Trans. Signal Processing, vol. 50, no. 2, pp. 174-188, Feb. 2002.
[11] A. Doucet, S. Godsill, and C. Andreu, “On Sequential Monte Carlo Sampling Methods for Bayesian Filtering,” Statistics and Computing vol. 10, no. 3, pp. 197- 208, July 2000.
[12] F. Yao, A. Demers, and S. Shenker, “A Scheduling Model for Reduced CPU Energy,” Proc. Ann. Symp. Foundation of Computer Science, pp. 374-382, 1995.
[13] C. Im, H. Kim, and S. Ha, “Dynamic Voltage Scheduling Technique for Low-Power Multimedia Applications Using Buffers,” Proc. Int'l Symp. Low Power Embedded Design, pp. 34-39, 2001.
[14] R. Jejurika and R. Gupta, “Energy-Aware Task Scheduling with Task Synchronization for Embedded Real-Time Systems,” IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems, vol. 25, no. 6, pp. 1024-1037, June 2006.
[15] Y. Tan, P. Malani, Q. Qiu, and Q. Wu, “Workload Prediction and Dynamic Voltage Scaling for MPEG Decoding,” Proc. Asia and South Pacific Design Automation Conf. (ASP-DAC), 2006.
[16] M. Mesarina and Y. Turner, “Reduced Energy Decoding of MPEG Streams,” Proc. Multimedia Computing and Networking, 2002.
[17] K. Choi, W.-C. Cheng, and M. Pedram, “Frame-Based Dynamic Voltage Scaling for an MPEG Decoder,” J. Low Power Electronics, vol. 1, no. 1, pp. 44-51, Apr. 2005.
[18] A. Sinha and A.P. Chandrakasan, “Dynamic Voltage Scheduling Using Adaptive Filtering of Workload Traces,” Proc. Int'l Conf. VLSI Design, pp. 221-226, 2001.
[19] Y. Gu and S. Chakraborty, “Control Theory-Based DVS for Interactive 3D Games,” Proc. Design Automation Conf., pp. 740-745, 2008.
[20] S.-Y. Bang, K. Bang, S. Yoon, and E.-Y. Li, “Run-Time Adaptive Workload Estimation for Dynamic Voltage Scaling,” IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems, vol. 28, no. 9, pp. 1334-1347, Sept. 2009.
[21] J. Kim, S. Yoo, and C. Kyung, “Program Phase-Aware Dynamic Voltage Scaling under Variable Computational Workload and Memory Stall Environment,” IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems, vol. 30, no. 1, pp. 110-123, Jan. 2011.
[22] K. Choi, R. Soma, and M. Pedram, “Dynamic Voltage and Frequency Scaling Based on Workload Decomposition,” Proc. Int'l Symp. Low Power Electronic Devices, pp. 174-179, 2004.
[23] K. Choi, R. Soma, and M. Pedram, “Off-Chip Latency-Driven Dynamic Voltage and Frequency Scaling for an MPEG Decoding,” Proc. Design Automation Conf., pp. 544-549, 2004.
[24] R. van der Merwe, A. Doucet, N. de Freitas, and E. Wan, “The Unscented Particle Filter,” Technical Report CUED/F-INFENG/TR 380, Cambridge Univ. ENg. Dept., 2000.
[25] SMDK6410, view.php?num=23 , 2011.
[26] mplayer, , 2011.
[27] I. Richardson, “What Is H.264/AVC?”, 2005.
[28] A. Doucet, N. de Freitas, and N. Gordon, Sequential Monte Carlo Methods in Practice. Springer, 2001.
[29] A. Kong, J.S. Liu, and W.H. Wong, “Sequential Imputations and Bayesian Missing Data Problems,” J. Am. Statistical Assoc., vol. 89, no. 425, pp. 278-288, 1994.

Index Terms:
Dynamic voltage and frequency scaling, feedback control, low energy, sequential Monte Carlo, particle filter, nonstationarity.
Jae-Beom Lee, Myoung-Jin Kim, Sungroh Yoon, Eui-Young Chung, "Application-Support Particle Filter for Dynamic Voltage Scaling of Multimedia Applications," IEEE Transactions on Computers, vol. 61, no. 9, pp. 1256-1269, Sept. 2012, doi:10.1109/TC.2011.148
Usage of this product signifies your acceptance of the Terms of Use.