Cross-Layer Resource Allocation Optimization by Hopfield Neural Networks in OFDMA-Based Wireless Mesh Networks

This paper presents a novel method based on Hopfield Neural Networks (HNN) for Cross-layer Dynamical Resource Allocation in Orthogonal Frequency Division Multiple Access (OFDMA)-based Wireless Mesh Networks (WMN). The objective is to optimize the maximization of the system throughput using HNN under the conditions of the signal-to-interference-plus-noise ratio (SINR) constraint, power constraint and time delay constraint. The objective problem is simplified by dividing the bit-loading matrix into three matrixes. The simulation results show that HNN method can effectively solve optimization problems of resource allocation in such system, and it is more effective than the selected Greedy Algorithm (GA) method.