Neural network-based task scheduling with preemptive fan control
Pages 77 - 84
Abstract
As cooling cost is a significant portion of the total operating cost of supercomputers, improving the efficiency of the cooling mechanisms can significantly reduce the cost. Two sources of cooling inefficiency in existing computing systems are discussed in this paper: temperature variations, and reactive fan speed control. To address these problems, we propose a learning-based approach using a neural network model to accurately predict core temperatures, a preemptive fan control mechanism, and a thermal-aware load balancing algorithm that uses the temperature prediction model. We demonstrate that temperature variations among cores can be reduced from 9° C to 2° C, and that peak fan power can be reduced by 61%. These savings are realized with minimal performance degradation.
References
[1]
B. Acun, A. Gupta, N. Jain, A. Langer, H. Menon, E. Mikida, X. Ni, M. Robson, Y. Sun, E. Totoni, et al. Parallel programming with migratable objects: charm++ in practice. In SC14: International Conference for High Performance Computing, Networking, Storage and Analysis, pages 647--658. IEEE, 2014.
[2]
B. Acun, P. Miller, and L. V. Kale. Variation among processors under turbo boost in hpc systems. In Proceedings of the 2016 International Conference on Supercomputing, page 6. ACM, 2016.
[3]
ASCAC Subcommittee. Top ten exascale research challenges. US Department Of Energy Report, 2014.
[4]
S. Ashby, P. Beckman, J. Chen, P. Colella, B. Collins, D. Crawford, J. Dongarra, D. Kothe, R. Lusk, P. Messina, et al. The opportunities and challenges of exascale computing. Summary Report of the Advanced Scientific Computing Advisory Committee (ASCAC) Subcommittee, pages 1--77, 2010.
[5]
S. Aswath Narayana. An artificial neural networks based temperature prediction framework for network-on-chip based multicore platform. Master's thesis, Rochester Institute of Technology, 2016.
[6]
A. Bhatele. Automating Topology Aware Mapping for Supercomputers. PhD thesis, Dept. of Computer Science, University of Illinois, August 2010. http://hdl.handle.net/2142/16578.
[7]
D. Carraway. lookbusy - a synthetic load generator. https://www.devin.com/lookbusy/.
[8]
H. Demuth and M. Beale. Neural Network Toolbox for Use with MATLAB. http://www.mathworks.com/help/nnet/.
[9]
T. V. T. Duy, Y. Sato, and Y. Inoguchi. Performance evaluation of a green scheduling algorithm for energy savings in cloud computing. In Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW), 2010 IEEE International Symposium on, pages 1--8. IEEE, 2010.
[10]
J. Huang, H. Jin, X. Xie, and Q. Zhang. Using narx neural network based load prediction to improve scheduling decision in grid environments. In Third International Conference on Natural Computation (ICNC 2007), volume 5, pages 718--724. IEEE, 2007.
[11]
W. Huang, C. Lefurgy, W. Kuk, A. Buyuktosunoglu, M. Floyd, K. Rajamani, M. Allen-Ware, and B. Brock. Accurate fine-grained processor power proxies. In Proceedings of the 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture, pages 224--234, 2012.
[12]
Y. Inadomi, T. Patki, K. Inoue, M. Aoyagi, B. Rountree, M. Schulz, D. Lowenthal, Y. Wada, K. Fukazawa, M. Ueda, et al. Analyzing and mitigating the impact of manufacturing variability in power-constrained supercomputing. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, page 78. ACM, 2015.
[13]
E. K. Lee, H. Viswanathan, and D. Pompili. Vmap: Proactive thermal-aware virtual machine allocation in hpc cloud datacenters. In High Performance Computing (HiPC), 2012 19th International Conference on, pages 1--10, 2012.
[14]
H. Menon, B. Acun, S. G. De Gonzalo, O. Sarood, and L. Kalé. Thermal aware automated load balancing for hpc applications. In 2013 IEEE International Conference on Cluster Computing (CLUSTER), pages 1--8. IEEE, 2013.
[15]
M. F. Moller. A scaled conjugate gradient algorithm for fast supervised learning. NEURAL NETWORKS, 6(4):525--533, 1993.
[16]
J. Moore, J. S. Chase, and P. Ranganathan. Weatherman: Automated, online and predictive thermal mapping and management for data centers. In 2006 IEEE International Conference on Autonomic Computing, pages 155--164. IEEE, 2006.
[17]
J. J. More. The levenberg-marquardt algorithm: Implementation and theory. Numerical Analysis, ed. G. A. Watson, Lecture Notes in Mathematics 630, Springer Verlag, pages 105--116, 1977.
[18]
T. Patki, D. K. Lowenthal, A. Sasidharan, M. Maiterth, B. L. Rountree, M. Schulz, and B. R. de Supinski. Practical resource management in power-constrained, high performance computing. In Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing, pages 121--132. ACM, 2015.
[19]
K. Pedretti, S. L. Olivier, K. B. Ferreira, G. Shipman, and W. Shu. Early experiences with node-level power capping on the cray xc40 platform. In Proceedings of the 3rd International Workshop on Energy Efficient Supercomputing, page 1. ACM, 2015.
[20]
M. Riedmiller and H. Braun. A direct adaptive method for faster backpropagation learning: the rprop algorithm. In Neural Networks, 1993., IEEE International Conference on, pages 586--591, 1993.
[21]
O. Sarood and L. V. Kale. A `cool' load balancer for parallel applications. In Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, page 21. ACM, 2011.
[22]
R. Sawyer. Calculating total power requirements for data centers. White Paper, American Power Conversion, 2004.
[23]
D. Tobias. Forward-looking fan control using system operation information, Feb. 7 2006. US Patent 6,996,441.
[24]
K. Zhang, S. Ogrenci-Memik, G. Memik, K. Yoshii, R. Sankaran, and P. Beckman. Minimizing thermal variation across system components. In Parallel and Distributed Processing Symposium (IPDPS), 2015 IEEE International, pages 1139--1148. IEEE, 2015.
- Neural network-based task scheduling with preemptive fan control
Recommendations
A Decoupling Control Method of Ceramic Roller Kiln Temperature Based on Thermal Balance
ICICIS '11: Proceedings of the 2011 International Conference on Internet Computing and Information ServicesAccording to the characteristics of ceramic roller kiln temperature process and the implementation scheme of temperature control, we proposed a new control method of the ceramic roller kiln temperature based on thermal balance. We set the difference ...
Predicting of fan speed for energy saving in HVAC system based on adaptive network based fuzzy inference system
In this paper, a HVAC (heating, ventilating and air-conditioning) system has two different zones was designed and fan motor speed to minimize energy consumption of the HVAC system was controlled by a conventional (proportional-integral-derivative) PID ...
A study on PID control with indirect liquid/steam heating
The purpose of this experimental study is to reach homogeneous temperature control effect on the heat plate. In this research, the heat plate is kept constant temperature by the state of dual-phases, i.e., the state of phase change between liquid and ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
November 2016
91 pages
ISBN:9781509038565
- General Chairs:
- Kirk Cameron,
- Adolfy Hoisie,
- Darren Kerbyson,
- David Lowenthal,
- Dimitrios S. Nikolopoulos,
- Sudha Yalamanchili,
- Program Chairs:
- Kevin Barker,
- Rong Ge
Sponsors
- SIGHPC: ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing
- IEEE-CS\DATC: IEEE Computer Society
In-Cooperation
Publisher
IEEE Press
Publication History
Published: 13 November 2016
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
SC16
Sponsor:
- SIGHPC
- IEEE-CS\DATC
SC16: The International Conference for High Performance Computing, Networking, Storage and Analysis
November 13 - 18, 2016
Utah, Salt Lake City
Acceptance Rates
Overall Acceptance Rate 17 of 33 submissions, 52%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 157Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 18 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in