首页|基于SMA-SVR模型的城市道路短时交通流预测

基于SMA-SVR模型的城市道路短时交通流预测

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
短时交通流预测是动态交通控制与管理领域的关键问题之一.由于不确定性和非线性的存在,短时交通流预测仍然是一项具有挑战性的任务.为了提高短时交通流预测的准确性,通过提出一种基于黏菌算法(Slime Mould Algorithm,SMA)优化的支持向量回归模型(Support Vector Regression,SVR)研究了短时交通流的预测.收集蚌埠市东海大道-曹山路交叉口工作日早晚高峰交通流量数据,利用SMA对SVR模型的惩罚参数和核函数参数进行高效寻优,建立SMA-SVR模型进行了案例验证.研究结果表明,相比于原始SVR模型以及基于粒子群优化算法和麻雀搜索算法的SVR模型,SMA-SVM模型预测精度是最高的,即R2=0.97054,RMSE=47.7826,MAPE=7.1703％,并且迭代收敛速度也是最快的.可见,SMA-SVR模型能够较好地适配于城市道路的短时交通流预测.
Short-Term Traffic Flow Prediction on Urban Roads Based on SMA-SVR Models
Short-term traffic flow prediction is one of the key issues in the field of dynamic traffic control and management.Due to uncertainty and nonlinearity,short-term traffic flow prediction is still a challenging task.In order to improve the accuracy of short-time traffic flow prediction,this paper propo-ses a Support Vector Regression(SVR)model optimised based on Slime Mould Algorithm(SMA).the data of weekday morning and evening peak traffic flow at Donghai Avenue-Caoshan Road intersection in Bengbu City were collected,the penalty parameters and kernel function parameters of the SVR model are efficiently optimised using SMA,the SMA-SVR model is built for case validation.The results show that the SMA-SVM model has the highest prediction accuracy,i.e.R2=0.97054,RMSE=47.7826,MAPE=7.1703％,and the fastest iterative convergence speed compared with the original SVR model and the SVR model based on the Particle Swarm Optimisation algorithm and the Sparrow Search algorithm.It can be seen that the proposed SMA-SVM model can be used for short-term traffic flow prediction on urban roads.

urban roadsshort-term traffic flowSupport Vector Regression modelsSlime Mould Optimisation

岳鑫鑫、常山、马露、于敏、韩意

展开 >

安徽科技学院建筑学院,安徽 蚌埠 233030

合肥工业大学土木与水利工程学院,安徽 合肥 230009

城市道路 短时交通流 支持向量回归模型 黏菌优化

安徽省高校科学研究重大项目安徽省高校科学研究重点项目安徽省高校科学研究重点项目安徽省高校优秀青年骨干教师国内访问研修项目

2023AH0402742023AH0518412023AH051863gxgnfx2022042

2024

安顺学院学报
安顺学院

安顺学院学报

影响因子：0.155
ISSN：1673-9507
年,卷(期)：2024.26(3)
  • 5