一种改进鲸鱼算法及其在短时交通流预测中的应用研究

Improved Whale Algorithm and Its Application in Short-term Traffic Flow Prediction

短时交通流预测在现代城市交通中有着重要的作用,可以帮助智能交通系统提供决策,提升人们的出行效率,这就使得提高短时交通流预测的精度成了当前研究的热点问题,本文通过引入自适应权重策略和天牛须搜索策略对鲸鱼优化算法做出改进,使用函数仿真实验证明了改进策略的有效性,然后将改进后的算法来优化最小二乘支持向量机(LSSVM)的惩罚因子和核函数参数并构建短时交通流量预测模型进行预测.通过仿真结果可以看出,对比其他模型,本文构建的ABOA-LSSVM模型在短时交通流预测方面具有优势,非常适合于交通流量预测.

Short-term traffic flow forecasting plays an important role in the modern urban traffic,it can help intelligent transportation systems provide decision-making and improve people′s travel efficiency thus raising the accuracy of the short-term traffic flow prediction becomes the hot spot problems of current research,in this paper,by introducing the adaptive weighting strategies and longicorn must search strategy to improve the whale optimization algorithm,through the function simulation results prove the validity of the improved strategies,and then use the improved algorithm to optimize the least squares support vector machine(LSSVM)punishment factor and kernel function parameters and build forecasting model to forecast short-term traffic flow.The simulation results show that the aboa-LSSVM model constructed in this paper has advantages in the accuracy of short-term traffic flow prediction compared with other models,and is very suitable for traffic flow prediction.