Estimation of MIMO Wireless Channels Using Artificial Neural Networks

Estimation of MIMO Wireless Channels Using Artificial Neural Networks

Kandarpa Kumar Sarma (Indian Institute of Technology, India) and Abhijit Mitra (Indian Institute of Technology, India)
DOI: 10.4018/978-1-61350-429-1.ch026
OnDemand PDF Download:


Artificial Neural Network (ANN) is a non-parametric statistical tool which can be used for a host of pattern classification and prediction problems. It has excelled in diverse areas of application ranging from character recognition to financial problems. One of these areas, which have ample of scope of application of the ANN, is wireless communication. Especially, in segments like Multi-Input Multi-Output (MIMO) wireless channels ANNs have seldom been used for problems like channel estimation. Very few reported work exists in this regard. This work is related to the application of ANN for estimation of a MIMO channel of a wireless communication set-up. As Orthogonal Frequency Division Multiplexing (OFDM) is becoming an option to tackle increased demands of higher data rates by the modern generation mobile communication networks, a MIMO-OFDM system assisted by an ANN based channel estimation can offer better quality of service (QoS) and higher spectral efficiency.
Chapter Preview

1. Introduction

The proliferation of mobile communication networks over the last few years have congested the available spectrum, raised the levels of intersymbol interference (ISI) and have threatened to degrade quality of service (QoS) thereby necessitating the search for innovative solutions to increase overall efficiency (Bolcskei & Zurich, 2006). Additionally there is a constant demand for higher bandwidth, increased data rates, lower cost, greater coverage etc for which the mobile networks are creating congestion in the available spectrum. In such a situation Multiple-Input Multiple-Output (MIMO) wireless technology seems to be able to meet these demands by offering increased spectral efficiency. MIMO architectures are useful for combined transmit receive diversity. When used in parallel mode of transmission, MIMO systems offer high data rates in a narrow bandwidth. MIMO systems, characterized by multiple antenna elements at the transmitter and receiver, have demonstrated the potential for increased capacity in rich multipath environments.

OFDM is gradually emerging as the chosen modulation technique for wireless communications nowadays. It is being adopted as one of the alternatives to meet the demands of high data rates by present day mobile communication networks. OFDM uses non-overlapping adjacent channel to increase spectral efficiency and allows multiple carriers be used to transmit different symbols with spectral overlap while ensuring co-existence of nearby signals due to orthogonality (Bolcskei & Zurich, 2006) to (Jiang & Hanzo, 2007).

The combination MIMO-OFDM together provides greater spatial multiplexing gain, and improved link reliability due to antenna diversity. This is because MIMO channel becomes frequency selective for high data rate transmission and OFDM can transform such frequency selective channels into a set of parallel frequency flat MIMO channels. Together the combination reduces receiver design complexity. Also OFDM is effective in dealing with multipath fading and ISI (Yang, 2005). Yet channel estimation remains a challenging issue for MIMO-OFDM systems.

Two common practices of channel estimation in MIMO - OFDM systems are pilot-based channel estimation and blind channel estimation. Pilot-based estimation techniques use least-squares (LS), minimum mean-square error (MMSE) and linear minimum mean square error (LMMSE) estimators. The pilot - based channel estimation, by requiring pilot symbol bits to be inserted as training sequence along with OFDM blocks, causes waste of bandwidth. Blind estimation techniques don’t require training sequences but are extremely computationally intensive (Colieri et al., 2002) (Gacanin, Takaoka, & Adachi, 2005). Innovative means are being formulated to tackle channel estimation and improve performance of mobile systems.

Complete Chapter List

Search this Book: