基于模糊神经网络的异构无线网络接入选择算法

Fuzzy neural network based access selection algorithm in heterogeneous wireless networks

针对现有异构无线网络基于模糊逻辑及神经网络的接入选择方法未能合理考虑网络负载状况的问题,提出一种基于RBF(径向基函数)模糊神经网络的接入选择方法。该方法以可接入网络的接入阻塞率相等为模糊神经网络参数强化学习的目标,对网络负载程度具有很好的动态适应性,实现了智能化的接入判决。仿真结果表明,该方法能有效均衡异构无线网络间的负载,保障实时与非实时业务的QoS,并且相对于负载均衡算法(MLB算法)降低了网络的接入阻塞率。

Aiming at working out the problem that fuzzy logic and neural network based access selection algorithm didn’t consider the load state reasonably in heterogeneous wireless network,a RBF（radial basis function） fuzzy neural network based access selection algorithm was proposed.The algorithm executed factors reinforcement learning for the fuzzy neu-ral network with the objective of the equal blocking probability of accessible networks to adapt for load state dynamically,and achieved the intelligent access judgment.The simulation results show that the algorithm can balance the load of het-erogeneous wireless networks effectively and guarantee the QoS of real time and non-real time services,as well as de-crease the blocking probability compared to the maximum load balance based algorithm（MLB algorithm）.