Joint Transmitter and Receiver Power Allocation under Minimax MSE Criterion with Perfect and Imperfect CSI for MC-CDMA Transmissions

Chirawat KOTCHASARN  Poompat SAENGUDOMLERT  

Publication
IEICE TRANSACTIONS on Communications   Vol.E91-B   No.6   pp.1970-1979
Publication Date: 2008/06/01
Online ISSN: 1745-1345
DOI: 10.1093/ietcom/e91-b.6.1970
Print ISSN: 0916-8516
Type of Manuscript: PAPER
Category: Wireless Communication Technologies
Keyword: 
joint transmitter and receiver power allocation,  nonlinear optimization,  minimax optimization,  robust optimization,  semidefinite programming,  bilinear matrix inequality,  MC-CDMA,  

Full Text: PDF(1.2MB)>>
Buy this Article




Summary: 
We investigate the problem of joint transmitter and receiver power allocation with the minimax mean square error (MSE) criterion for uplink transmissions in a multi-carrier code division multiple access (MC-CDMA) system. The objective of power allocation is to minimize the maximum MSE among all users each of which has limited transmit power. This problem is a nonlinear optimization problem. Using the Lagrange multiplier method, we derive the Karush-Kuhn-Tucker (KKT) conditions which are necessary for a power allocation to be optimal. Numerical results indicate that, compared to the minimum total MSE criterion, the minimax MSE criterion yields a higher total MSE but provides a fairer treatment across the users. The advantages of the minimax MSE criterion are more evident when we consider the bit error rate (BER) estimates. Numerical results show that the minimax MSE criterion yields a lower maximum BER and a lower average BER. We also observe that, with the minimax MSE criterion, some users do not transmit at full power. For comparison, with the minimum total MSE criterion, all users transmit at full power. In addition, we investigate robust joint transmitter and receiver power allocation where the channel state information (CSI) is not perfect. The CSI error is assumed to be unknown but bounded by a deterministic value. This problem is formulated as a semidefinite programming (SDP) problem with bilinear matrix inequality (BMI) constraints. Numerical results show that, with imperfect CSI, the minimax MSE criterion also outperforms the minimum total MSE criterion in terms of the maximum and average BERs.