基于迟滞噪声混沌神经网络的导频分配

在多小区大规模多输入多输出(MIMO)系统中，导频污染已经成为制约整个系统的瓶颈。合理地使用导频资源能减轻导频污染的影响，为了寻找使边缘用户和容量最大的导频分配方式，该文首次提出了基于迟滞噪声混沌神经网络(HNCNN)的导频分配方案。迟滞噪声混沌神经网络作为良好的优化工具，其优化能力与所设计的能量函数相关。该方案结合导频资源使用的特点以及最大化边缘用户和容量的计算方式，设计了新的能量函数。仿真结果表明，网络能在一定迭代次数后收敛到较优的导频分配方式。与其它文献方案相比，采用以HNCNN为框架求取导频分配方式，可以更有效减轻导频污染的影响，使系统性能得到改善。

Hysteretic Noisy Chaotic Neural Networks Based Pilot Assignment

In multi-cell massive Multiple Input Multiple Output (MIMO) systems, pilot contamination has become the bottleneck which restricts the performance of the whole system, so the reasonable usage of pilot resources can mitigate the pilot contamination of the system. In order to find the pilot allocation method that maximizes the total transmission capacity of edge users, a pilot allocation scheme based on Hysteretic Noise Chaotic Neural Network (HNCNN) is proposed for the first time. HNCNN is a famous optimization tool, and its optimization ability is related to the designed energy function. This scheme combines the characteristics of pilot resource usage and the calculation method of maximizing the total transmission capacity of edge users to design a new energy function. The simulation results show that the proposed network can converge to a better pilot allocation mode after a certain number of iterations. Compared with other literature pilot allocation solution, the pilot allocation method based on HNCNN can further reduce the influence of pilot contamination and improve the system performance.