基于MapReduce的城市道路旅行时间实测计算

Urban Road Trip Time Measured Calculation Based on MapReduce

城市道路旅行时间计算一直是智能交通系统中研究的核心问题之一,准确高效的旅行时间计算可以有效地帮助道路管控,减少交通拥挤。然而面对巨大而且快速增长的城市道路交通检测数据,如何将分布式计算模式融合到传统的旅行时间计算问题中已成为一个亟待解决的问题。论文基于海量道路车牌识别数据,设计了基于MapReduce编程模型的城市道路旅行时间实测计算的算法。并利用Hadoop环境进行了实现,可以支持对自定义路段集下不同时间段道路旅行时间的计算。通过实验证明,相对于传统的旅行时间计算方式,在计算时间上基于MapReduce的旅行时间计算模式可以提高十倍以上。

The calculation of travel time in urban road has been one of the core issues in the study of the intelligent transportation systems. Accurate and efficient calculation of travel time can effectively help to control the urban road system and avoid traffic congestion. However, with a large and rapidly growing of urban road traffic monitor data, it would be a urgent problem to apply the distributed computing model to the traditional calculation of travel time. In this paper, based on massive road vehicle identification data, MapReduce programming framework is used to design a algorithm for actual measurement of urban road travel time. And using Hadoop environments to implement, it can support the calculation of road travel time in different time periods under the custom section sets. Our experiments show that MapReduce-based computing model is more than 10 times faster in computation time than the traditional way.