Tuning an underwater communication link

We present machine learning algorithms to tune an underwater communication link. The link tuner is characterized by 3 features: a) It is data driven, rather than physics driven. Hence, it only needs bit error rate information as input and is independent of the modem implementation, b) The tuner balances exploration of the search space against exploitation of existing knowledge, and c) It optimizes for the average data rate, instead of searching for maximum possible data rate. We implement the link tuner on the UNET-II modem and present results from simulations, water tank tests and field trials. The results demonstrate a significant improvement in average data rate as compared to the average data rate attained without tuning.

[1]  Sean R Eddy,et al.  What is dynamic programming? , 2004, Nature Biotechnology.

[2]  Mandar Chitre,et al.  UNDERWATER ACOUSTIC COMMUNICATIONS IN WARM SHALLOW WATER CHANNELS , 2006 .

[3]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[4]  Mandar Chitre,et al.  Reliable Point-to-Point Underwater Acoustic Data Transfer: To Juggle or Not to Juggle? , 2015, IEEE Journal of Oceanic Engineering.

[5]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[6]  Konstantin Kebkal,et al.  Ultrasonic link for improved incoherent data transmission in horizontal shallow water channels , 2003, Oceans 2003. Celebrating the Past ... Teaming Toward the Future (IEEE Cat. No.03CH37492).

[7]  Greg Welch,et al.  Welch & Bishop , An Introduction to the Kalman Filter 2 1 The Discrete Kalman Filter In 1960 , 1994 .

[8]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[9]  Milica Stojanovic,et al.  Recent advances in high-speed underwater acoustic communications , 1996 .

[10]  Mandar Chitre,et al.  Data driven algorithms to tune physical layer parameters of an underwater communication link , 2010, OCEANS'10 IEEE SYDNEY.

[11]  S. Singh,et al.  The WHOI micro-modem: an acoustic communications and navigation system for multiple platforms , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[12]  Haris Volos,et al.  On Balancing Exploration Vs. Exploitation in a Cognitive Engine for Multi-Antenna Systems , 2009, GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference.

[13]  Fei Peng,et al.  Adaptive Modulation and Coding for IEEE 802.11n , 2007, 2007 IEEE Wireless Communications and Networking Conference.

[14]  Mehryar Mohri,et al.  Multi-armed Bandit Algorithms and Empirical Evaluation , 2005, ECML.

[15]  James Preisig,et al.  Acoustic propagation considerations for underwater acoustic communications network development , 2006, Underwater Networks.

[16]  Clive Tang,et al.  An adaptive learning approach to adaptive OFDM , 2004, 2004 IEEE Wireless Communications and Networking Conference (IEEE Cat. No.04TH8733).

[17]  Lijun Qian,et al.  Energy Efficient Adaptive Modulation in Wireless Cognitive Radio Sensor Networks , 2007, 2007 IEEE International Conference on Communications.

[18]  Masanobu Suzuki,et al.  Digital Acoustic Image Transmission System For Deep-sea Research Submersible , 1992, OCEANS 92 Proceedings@m_Mastering the Oceans Through Technology.

[19]  K. J. Ray Liu,et al.  Channel-aware priority transmission scheme using joint channel estimation and data loading for OFDM systems , 2005, IEEE Transactions on Signal Processing.

[20]  Haris Volos,et al.  Cognitive Engine Design for Link Adaptation: An Application to Multi-Antenna Systems , 2010, IEEE Transactions on Wireless Communications.

[21]  M. Chitre,et al.  The UNET-2 modem — An extensible tool for underwater networking research , 2012, 2012 Oceans - Yeosu.

[22]  Xinwei Yu,et al.  ML-Based Channel Estimations for Non-Regenerative Relay Networks with Multiple Transmit and Receive Antennas , 2012, IEEE Journal on Selected Areas in Communications.

[23]  Curt Schurgers,et al.  Design of a low-cost, underwater acoustic modem for short-range sensor networks , 2010 .

[24]  Joseph A. Rice,et al.  Acoustic communication channel modeling for the Baltic Sea , 1999, Oceans '99. MTS/IEEE. Riding the Crest into the 21st Century. Conference and Exhibition. Conference Proceedings (IEEE Cat. No.99CH37008).

[25]  Sumei Sun,et al.  Link adaptation based on adaptive modulation and coding for multiple-antenna OFDM system , 2008, IEEE Journal on Selected Areas in Communications.

[26]  J. Bather,et al.  Multi‐Armed Bandit Allocation Indices , 1990 .

[27]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[28]  Haris I. Volos,et al.  Cognitive Radio Engine Design for Link Adaptation , 2010 .

[29]  Robert J. Urick,et al.  Principles of underwater sound , 1975 .

[30]  Michael B. Porter,et al.  Acoustic propagation in very shallow water , 2010, 2010 International WaterSide Security Conference.

[31]  Milica Stojanovic,et al.  Underwater Acoustic Communications and Networking: Recent Advances and Future Challenges , 2008 .

[32]  P. W. Jones,et al.  Bandit Problems, Sequential Allocation of Experiments , 1987 .

[33]  Konstantinos Pelekanakis,et al.  NATURAL GRADIENT-BASED ADAPTIVE ALGORITHMS FOR SPARSE UNDERWATER ACOUSTIC CHANNEL IDENTIFICATION , 2011 .