A Solution of Traffic Problems Based on MapReduce
With the number of cars increasing sharply, traffic becomes a big problem in our daily life. We may think of solving the problem by analyzing the global position system (GPS) data got from cars, but another problem arises, that is, how we can analyze the large-scale data set. The MapReduce programming model is inspired by Google and targets data-intensive parallel computations. This paper presents the results of the situations of several roads at different time and the trends of traffic in each road, after analyzing the huge database by taking a modified velocity–time integration we proposed and run on the MapReduce parallel model. The experiment results show that the algorithm is effective and efficient and the model is efficient to handle with large-scale data set.
KeywordsMapReduce Parallel computation Traffic problems GPS Modified velocity–time model
This research was jointly supported by Research Innovation Fund for College Student of Beijing University of Posts and Telecommunications, P. R. China.
- 1.Jiang G, Chang A, Li Q, Yi F (2009) Estimation Approaches of average link travel time using GPS data[J]. J Jilin Univ: Eng Technol 39(2):182–186Google Scholar
- 2.Zhu L, Lu Y, Mao S (2006) Estimation of parameters of mixed exponential distribution. Chin J Appl Prob Stat 22(2):137–150Google Scholar
- 3.Guan Y, Zhang N, Zhu J, et al (2010) Modeling on-ramp capacity with driver behavior variation[J]. J Transport Syst Eng Info Technol 12(1):122–127Google Scholar
- 4.Casella G, Berger RL (2002) Statistical inference [M], China Machine Press, BeijingGoogle Scholar
- 5.Jin S, Wang D, Tao P et al (2010) Nonlane based full velocity difference car following model[J]. Phys A 389(21):4654–4662Google Scholar
- 7.Dean J, Ghemawat S (2004) MapReduce: simplified data processing on large clusters. OSDI 23:9–27Google Scholar
- 8.Abadi DJ, Madden SR, Hachem N (2008) Column-stores vs. row-stores: how different are they really? In: Proceedings of the SIGMOD conference on management of data, vol 1. pp 22–29Google Scholar
- 9.Boral H et al (2009) Prototyping Bubba, a highly parallel database system. IEEE T Knowl and Data En 2:4–24Google Scholar
- 10.Stonebraker M, Rowe L (1986) The design of Postgres. In: Proceedings of the SIGMOD conference, pp 340–355Google Scholar
- 11.Teradata Corp. (1985) Database computer system manual, Release 1.3, Los Angeles, CAGoogle Scholar
- 12.Bai H, Yao L, Lu S (2011) An alert aggregation algorithm based on MapReduce computing model. Inform Technol 4:85–92Google Scholar