机构地区: 深圳职业技术学院
出 处: 《计算机仿真》 2010年第12期323-326,共4页
摘 要: 根据交通流量数据具有非周期性、非线性和随机性等特点,为了更准确地对交通流量进行预测,实现交通智能控制和规划是主要问题。交通流量预测中存在容易陷入局部极小值、收敛速度慢,泛化能力差等问题,影响了交通流量预测的实用性和准确性。提出基于粒子群(PSO)优化RBF神经网络的交通流量预测方法。利用PSO算法操作简单、容易实现等特点及其深刻的智能背景,对RBF神经网络的参数(中心和宽度)、连接权重进行优化,并用经PSO算法优化的RBF神经网络对短时交通流量进行仿真预测,仿真结果表明,PSO算法优化的RBF神经网络具有较高的预测精度,比RBF预测模型精度高、收敛快。PSO算法优化的RBF神经网络,适用于短时交通流量预测,预测精度较高,具有推广应用价值。 Traffic flow data are unperiodical,nonlinear and stochastic,the practicability and accuracy are affected by its drawbacks of falling into local optimization and low convergence rate.Thus,RBF neural network optimized by particle swarm optimization algorithm(PSO-RBFNN) is proposed to predict traffic flow in the paper.Being easy to realize,simple to operate with profound intelligence background,the parameters and connection weight are optimized by the algorithm and short time traffic flow prediction is simulated by the optimized RBF Neural Network.The predictiion results of the instance show that it has better prediction results,higher precision,faster convergence speed than that of RBf predicton model.The optimized RBF Neural Network is suitable for short time traffic flow prediction.The method has good prediction accuracy and popularization value.
领 域: [一般工业技术]