摘要
提出一种用Hopfield神经网络对多用户OFDM通信系统进行子载波分配和比特自适应加载的方法,利用Hopfield神经网络的并行处理、收敛快、易收敛到最优解的特点,在系统性能一定和满足各个用户业务要求的条件下,对资源进行自适应分配,以使多用户OFDM系统的发射功率最小。将比特加载矩阵拆成三个矩阵来表示,简化了运算。仿真结果表明采用Hopfield神经网络方法可有效地解决通信中资源分配最优化问题,并且总体效果也优于采用遗传算法得到的结果。
This paper presents a novel method based on Hopfield Neural Networks (HNN) for the adaptive subcarrier assignment and bit loading in OFDM communication system. Utilizing the HNN characteristics such as parallel processing, fast convergence speed and easy convergence to the optimum, the method can minimize the transmitting power of the system through adaptive resource allocation, satisfying system performances and users' requirements. The method is simple in the computation by dividing the bit-loading matrix into three matrixes. The simulation results show that HNN can effectively solve optimization problems of resource allocation in such system, and it is more effective than the selected Genetic Algorithm (GA) method.
出处
《电路与系统学报》
CSCD
北大核心
2010年第2期47-51,共5页
Journal of Circuits and Systems
基金
国家自然科学基金(60672037)
山东省自然科学基金(Y2006G06)