Neural network-based adaptive beamforming for one- and two-dimensional antenna arrays

TLDR

In modern cellular, satellite, and GPS systems, desired and interfering signals continuously change direction, necessitating fast tracking to adapt antenna patterns. The study proposes a neural network method to compute weights for 1‑D and 2‑D adaptive antenna arrays. The method employs a three‑layer radial basis function neural network to determine the optimal array weights. The network’s outputs closely match the Wiener solution, validating its effectiveness.

Abstract

We present a neural network approach to the problem of finding the weights of one- (1-D) and two-dimensional (2-D) adaptive arrays. In modern cellular satellite mobile communications systems and in global positioning systems (GPSs), both desired and interfering signals change their directions continuously. Therefore, a fast tracking system is needed to constantly track the users and then adapt the radiation pattern of the antenna to direct multiple narrow beams to desired users and nulls interfering sources. In the approach suggested in this paper, the computation of the optimum weights is accomplished using three-layer radial basis function neural networks (RBFNN). The results obtained from this network are in excellent agreement with the Wiener solution.