ABSTRACT
Reducing the energy consumption of mobile phones is a major concern in the design of cellular modem solutions for LTE and 5G standards. Apart from optimizing hardware for power efficiency, dynamic power management, i.e., powering down idle system components, is a crucial means to achieve this goal. The techniques proposed so far, however, are reactive rather than proactive. This leads to the inability to exploit a significant amount of opportunities to power down components, as the opportunity is recognized too late. We propose a dynamic power management technique that is capable of exploiting said opportunities through the application of reinforcement learning prediction techniques for proactive power management. However, the additional computational effort for prediction algorithms must be carefully analyzed and taken into account. Therefore, we investigate which conditions have to be met in order to achieve net energy savings. The proposed technique has been implemented and evaluated for potential savings on simulated traces of LTE data. The resulting predictor is designed to be trained online, without any prior system knowledge. For a fair evaluation and comparison, the power consumption of the training phase is also considered in the analysis. It is shown that energy savings of up to 23.9 % may be obtained on a modem for scenarios such as HTTP streaming.
- 2016. ns-3. https://www.nsnam.org/. (2016).Google Scholar
- Omer Anjum, Tapani Ahonen, Fabio Garzia, Jari Nurmi, Claudio Brunelli, and Heikki Berg. 2011. State of the art baseband DSP platforms for Software Defined Radio: A survey. EURASIP JWCN 2011, 1 (2011), 5.Google ScholarCross Ref
- Nicola Baldo. 2011. The ns-3 LTE module by the LENA project. (2011).Google Scholar
- Luca Benini, Alessandro Bogliolo, and Giovanni De Micheli. 2000. A survey of design techniques for system-level dynamic power management. IEEE transactions on VLSI systems 8, 3 (2000), 299--316. Google ScholarDigital Library
- Sourjya Bhaumik, Shoban Preeth Chandrabose, Manjunath Kashyap Jataprolu, Gautam Kumar, Anand Muralidhar, Paul Polakos, Vikram Srinivasan, and Thomas Woo. 2012. CloudIQ: A framework for processing base stations in a data center. In Proceedings of the 18th annual international conference on Mobile computing and networking. ACM, 125--136. Google ScholarDigital Library
- Peter Brand, Jonathan Ah Sue, Johannes Brendel, Joachim Falk, Ralph Hasholzner, Jürgen Teich, and Stefan Wildermann. 2017. Exploiting Predictability in Dynamic Network Communication for Power-Efficient Data Transmission in LTE Radio Systems. In Proceedings of the 20th International Workshop on Software and Compilers for Embedded Systems. ACM, 64--67. Google ScholarDigital Library
- Xiaomeng Chen, Jiayi Meng, Y Charlie Hu, Maruti Gupta, Ralph Hasholzner, Venkatesan Nallampatti Ekambaram, Ashish Singh, and Srikathyayani Srikanteswara. 2017. A Fine-grained Event-based Modem Power Model for Enabling In-depth Modem Energy Drain Analysis. Proceedings of the ACM on Measurement and Analysis of Computing Systems 1, 2 (2017), 45. Google ScholarDigital Library
- Eui-Young Chung, Luca Benini, and Giovanni De Micheli. 1999. Dynamic power management using adaptive learning tree. In Proceedings of the 1999 IEEE/ACM international conference on Computer-aided design. IEEE Press, 274--279. Google ScholarDigital Library
- Denis C Daly, Laura C Fujino, and Kenneth C Smith. 2017. Through the Looking Glass--The 2017 Edition: Trends in Solid-State Circuits from ISSCC. IEEE Solid-State Circuits Magazine 9, 1 (2017), 12--22.Google ScholarCross Ref
- Gaurav Dhiman and Tajana Simunic Rosing. 2006. Dynamic Power Management Using Machine Learning. In Proceedings of the 2006 IEEE/ACM International Conference on Computer-aided Design (ICCAD '06). ACM, New York, NY, USA, 747--754. Google ScholarDigital Library
- J. Falk, C. Haubelt, and J. Teich. 2006. Efficient Representation and Simulation of Model-Based Designs in SystemC. In Proc. FDL (Sep. 19-22) (EDL'06). 129--134.Google Scholar
- Stefanos Kaxiras, Girija Narlikar, Alan D Berenbaum, and Zhigang Hu. 2001. Comparing power consumption of an SMT and a CMP DSP for mobile phone workloads. In Proceedings of the 2001 international conference on Compilers, architecture, and synthesis for embedded systems. ACM, 211--220. Google ScholarDigital Library
- Robin Kravets and Parameshwaran Krishnan. 2000. Application-driven power management for mobile communication. Wireless Networks 6, 4 (July 2000), 263--277. Google ScholarDigital Library
- S-B Lee, Ioannis Pefkianakis, Adam Meyerson, Shugong Xu, and Songwu Lu. 2009. Proportional fair frequency-domain packet scheduling for 3GPP LTE uplink. In INFOCOM 2009, IEEE. IEEE, 2611--2615.Google ScholarCross Ref
- James MacGlashan. 2017. Burlap: Brown-UMBC reinforcement learning and planning. http://burlap.cs.brown.edu/. (2017). Accessed: 2017-11-3.Google Scholar
- S. Mannor, B. Kveton, S. Siddiqi, and C. Yu. 2006. Machine learning for adaptive power management. Autonomic Computing 10, 4 (2006), 299--312.Google Scholar
- Rafael Rosales, Michael Glass, Jürgen Teich, Bo Wang, Yang Xu, and Ralph Hasholzner. 2014. MAESTRO-holistic actor-oriented modeling of nonfunctional properties and firmware behavior for MPSoCs. ACM Transactions on Design Automation of Electronic Systems (TODAES) 19, 3 (2014), 23. Google ScholarDigital Library
- Gavin A Rummery and Mahesan Niranjan. 1994. On-line Q-learning using connectionist systems. Vol. 37. University of Cambridge, Department of Engineering.Google Scholar
- Einar Cesar Santos. 2017. A Simple Reinforcement Learning Mechanism for Resource Allocation in LTE-A Networks with Markov Decision Process and Q-Learning. arXiv preprint arXiv:1709.09312 (2017).Google Scholar
- Stefania Sesia, Matthew Baker, and Issam Toufik. 2011. LTE-the UMTS long term evolution: from theory to practice. John Wiley & Sons. Google ScholarDigital Library
- Iraj Sodagar. 2011. The mpeg-dash standard for multimedia streaming over the internet. IEEE MultiMedia 18, 4 (2011), 62--67. Google ScholarDigital Library
- Mani B Srivastava, Anantha P Chandrakasan, and Robert W Brodersen. 1996. Predictive system shutdown and other architectural techniques for energy efficient programmable computation. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 4, 1 (1996), 42--55. Google ScholarDigital Library
- Jonathan Ah Sue, Ralph Hasholzner, Johannes Brendel, Martin Kleinsteuber, and Jüergen Teich. 2016. A binary time series model of LTE scheduling for machine learning prediction. In Foundations and Applications of Self* Systems, IEEE International Workshops on. IEEE, 269--270.Google Scholar
- Bo Wang, Yang Xu, Ralph Hasholzner, Rafael Rosales, Michael Glaß, and Jürgen Teich. 2014. End-to-end power estimation for heterogeneous cellular LTE SoCs in early design phases. In Power and Timing Modeling, Optimization and Simulation (PATMOS), 2014 24th International Workshop on. IEEE, 1--8.Google Scholar
- Yanzhi Wang, Qing Xie, Ahmed Ammari, and Massoud Pedram. 2011. Deriving a Near-optimal Power Management Policy Using Model-free Reinforcement Learning and Bayesian Classification. In Proceedings of the 48th Design Automation Conference (DAC '11). ACM, New York, NY, USA, 41--46. Google ScholarDigital Library
- Christopher JCH Watkins and Peter Dayan. 1992. Q-learning. Machine learning 8, 3-4 (1992), 279--292.Google Scholar
- Zhiyuan Xu, Yanzhi Wang, Jian Tang, Jing Wang, and Mustafa Cenk Gursoy. 2017. A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs. In Communications (ICC), 2017 IEEE International Conference on. IEEE, 1--6.Google ScholarCross Ref
Index Terms
- Reinforcement Learning for Power-Efficient Grant Prediction in LTE
Recommendations
Exploiting Predictability in Dynamic Network Communication for Power-Efficient Data Transmission in LTE Radio Systems
SCOPES '17: Proceedings of the 20th International Workshop on Software and Compilers for Embedded SystemsIn embedded systems powered by batteries, power is undoubtedly a critical resource making power management an important topic in the design phase. Even though power management is a heavily researched topic, most approaches focus on improving the way the ...
Reinforcement learning based energy efficient LTE RAN
GECCO Comp '14: Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary ComputationReducing power consumption in LTE networks has become an important issue for mobile network operators. The 3GPP organization has included such operation as one of SON (Self-Organizing Networks) functions [1][2]. Using the approach presented in this ...
Adaptive power management using reinforcement learning
ICCAD '09: Proceedings of the 2009 International Conference on Computer-Aided DesignSystem level power management must consider the uncertainty and variability that comes from the environment, the application and the hardware. A robust power management technique must be able to learn the optimal decision from past history and improve ...
Comments