Blind adaptive energy estimation for decorrelating decision-feedback CDMA multiuser detection using learning-type stochastic approximations

This paper investigates the application of linear reinforcement learning stochastic approximation to the blind adaptive energy estimation for a decorrelating decision-feedback (DDF) multiuser detector over synchronous code-division multiple-access (CDMA) radio channels in the presence of multiple-access interference (MAI) and additive Gaussian noise. The decision-feedback incorporated into the structure of a linear decorrelating detector is able to significantly improve the weaker users´ performance by cancelling the MAI from the stronger users. However, the DDF receiver requires the knowledge of the received energies. In this paper, a new novel blind estimation mechanism is proposed to estimate all the users´ energies using a stochastic approximation algorithm without training data. In order to increase the convergence speed of the energy estimation, a linear reinforcement learning technique is conducted to accelerate the stochastic approximation algorithms. Results show that our blind adaptation mechanism is able to accurately estimate all the users´ energies even if the users of the DDF detector are not ranked properly. After performing the blind energy estimation and then reordering the users in a nonincreasing order, numerical simulations show that the DDF detector for the weakest user performs closely to the maximum likelihood detector, whose complexity grows exponentially with the number of users