Equalization of the non-linear 60 GHz channel: comparison of reservoir computing to traditional approach

The non linearities in a communication channel can severely affect the communicationquality. These problems are encountered in many communication systems. Because of the highcomplexity of their power amplifiers, which have a severe non-linear behaviour, combined withan important pathloss, which imposes an important output power, the 60 GHz communicationsare strongly affected by these non-linearities. Taking these non-linearities into account in channelequalization can increase the communication performances and enable us to work near the saturationpoint of the amplifier. This paper presents the reservoir computer as a new approach for theequalization of a non-linear communication channels in the case of the 60 GHz communications.We compare the performances and the complexity of the reservoir computer algorithm with aniterative maximum likelihood (ML) equalizer. We find that the reservoir computer is an interestinglow complexity solution for this task.

[1]  Sergio Benedetto,et al.  Principles of Digital Transmission: With Wireless Applications , 1999 .

[2]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[3]  P. De Doncker,et al.  Performance and improvement of the finite order compensation in a non-linear DVB-S2 communication channel , 2012, 2012 IEEE First AESS European Conference on Satellite Telecommunications (ESTEL).

[4]  Chia-Chin Chong,et al.  An Overview of Multigigabit Wireless through Millimeter Wave Technology: Potentials and Technical Challenges , 2007, EURASIP J. Wirel. Commun. Netw..

[5]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[6]  Sergio Benedetto,et al.  Principles of digital transmission , 1999 .

[7]  Peter Tiño,et al.  Minimum Complexity Echo State Network , 2011, IEEE Transactions on Neural Networks.

[8]  A. Maltsev,et al.  Statistical channel model for 60 GHz WLAN systems in conference room environment , 2010, Proceedings of the Fourth European Conference on Antennas and Propagation.

[9]  Jochen J. Steil,et al.  Recent advances in efficient learning of recurrent networks , 2009, ESANN.

[10]  Franois Horlin,et al.  Digital Compensation for Analog Front-Ends: A New Approach to Wireless Transceiver Design , 2008 .

[11]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[12]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .