Optimization vs. Reinforcement Learning for Wirelessly Powered Sensor Networks

We consider a sensing application where the sensor nodes are wirelessly powered by an energy beacon. We focus on the problem of jointly optimizing the energy allocation of the energy beacon to different sensors and the data transmission powers of the sensors in order to minimize the field reconstruction error at the sink. In contrast to the standard ideal linear energy harvesting (EH) model, we consider practical non-linear EH models. We investigate this problem under two different frameworks: i) an optimization approach where the energy beacon knows the utility function of the nodes, channel state information and the energy harvesting characteristics of the devices; hence optimal power allocation strategies can be designed using an optimization problem and ii) a learning approach where the energy beacon decides on its strategies adaptively with battery level information and feedback on the utility function. Our results illustrate that deep reinforcement learning approach can obtain the same error levels with the optimization approach and provides a promising alternative to the optimization framework.

[1]  Koji Ishibashi,et al.  Wireless Power Transfer for Distributed Estimation in Sensor Networks , 2017, IEEE Journal of Selected Topics in Signal Processing.

[2]  Bruno Clerckx,et al.  Waveform Design for Wireless Power Transfer , 2016, IEEE Transactions on Signal Processing.

[3]  I. Olkin,et al.  Inequalities: Theory of Majorization and Its Applications , 1980 .

[4]  Pieter Abbeel,et al.  Benchmarking Deep Reinforcement Learning for Continuous Control , 2016, ICML.

[5]  Bruno Clerckx,et al.  Wireless Information and Power Transfer: Nonlinearity, Waveform Design, and Rate-Energy Tradeoff , 2016, IEEE Transactions on Signal Processing.

[6]  Yi Huang,et al.  A High-Efficiency Broadband Rectenna for Ambient Wireless Energy Harvesting , 2015, IEEE Transactions on Antennas and Propagation.

[7]  Derrick Wing Kwan Ng,et al.  Simultaneous wireless information and power transfer in modern communication systems , 2014, IEEE Communications Magazine.

[8]  Derrick Wing Kwan Ng,et al.  Practical Non-Linear Energy Harvesting Model and Resource Allocation for SWIPT Systems , 2015, IEEE Communications Letters.

[9]  Caijun Zhong,et al.  Application of smart antenna technologies in simultaneous wireless information and power transfer , 2014, IEEE Communications Magazine.

[10]  Bruno Clerckx,et al.  Waveform Design for Wireless Power Transfer With Limited Feedback , 2017, IEEE Transactions on Wireless Communications.

[11]  Erik G. Larsson,et al.  Simultaneous Information and Power Transfer for Broadband Wireless Systems , 2012, IEEE Transactions on Signal Processing.

[12]  Bruno Clerckx,et al.  Waveform optimization for Wireless Power Transfer with nonlinear energy harvester modeling , 2015, 2015 International Symposium on Wireless Communication Systems (ISWCS).

[13]  Zhu Han,et al.  Machine Learning Paradigms for Next-Generation Wireless Networks , 2017, IEEE Wireless Communications.

[14]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[15]  Rong Du,et al.  Lifetime maximization for sensor networks with wireless energy transfer , 2016, 2016 IEEE International Conference on Communications (ICC).

[16]  Sergey Levine,et al.  Trust Region Policy Optimization , 2015, ICML.

[17]  Mats Viberg,et al.  Simultaneous information and power transfer under a non-linear RF energy harvesting model , 2017, 2017 IEEE International Conference on Communications Workshops (ICC Workshops).

[18]  Derrick Wing Kwan Ng,et al.  Robust Resource Allocation for MIMO Wireless Powered Communication Networks Based on a Non-Linear EH Model , 2016, IEEE Transactions on Communications.