Abstract: Short-term traffic flow forecasting is not only a core element of intelligent transportation system but also plays an important role in traffic information service and traffic guidance. Short-term traffic flow forecasting is highlighted and has become reality in the light of the fact that the feasibility of data collection and travelers’ expectation of high travel quality. A short-term traffic flow forecasting model of multiple road cross-sections in a road network based on chaotic time series analysis is proposed in this paper considering the chaotic and relative character of traffic state. The parameters of the forecasting model are compared with single road cross-sections based on the chaotic time series analysis and can be obtained by particle swarm optimization algorithm. Meanwhile, the proposed forecasting models and methods of multiple road cross-sections in a road network were tested by real-time traffic flow data from urban expressway and the results were satisfying.

Key words: intelligent transportation system, short-term forecast, chaotic theory, multidimensional time series, particle swarm optimization

摘要： 短时交通流预测是智能交通系统的核心内容和交通信息服务、交通诱导的重要基础。目前，道路交通数据采集设备的性价比越来越合理，道路上交通数据的采集设备不断完善，使得短时交通流状态的分析处理和预测成为可能。考虑到道路网交通状态的混沌特性和相关性，应用多维混沌时间序列可对道路网多断面交通状态进行预测。建立的多维混沌时间序列模型中有多个参数需要确定，并且与以往一维混沌时间序列预测中参数确定原则既有区别又有联系，因此在分析其差异性之后，本文利用粒子群优化算法优化模型中参数，当输入新的数据时，应用该模型就可以预测道路多点的交通状态。通过某城市快速路上7个断面交通流量来验证模型的有效性。

关键词: 智能交通, 短时交通状态预测, 混沌理论, 多维时间序列, 粒子群优化算法