Maximum Entropy Method and It's Application in Probability Density Function of Traffic Flow
-
摘要: 交通流统计分布函数的形式具有多样性, 选择把数据套到一个适合的分布上去常常是困难的。为此, 寻求一种简便的产生概率密度函数的统一方法是十分必要的。运用最大熵原理不仅导出了几个科学实践中常见的概率分布密度函数, 而且在分析物理学中已有的导出公式的基础上给出了交通工程实践中产生概率密度函数的统一方法及其实用的数值算法。理论例题仿真与实例计算验证表明该方法和程序是合理有效的Abstract: Probability density function of traffic flow varies with different survey data.It is difficult to find a probability density function fitting for all kinds of traffic survey data.So to get an ordinary generating method of probability density function is greatly important for traffic researcher and engineer. The authors analyze the problem from the view of maximum entropy principle, work out six probability density function which often appear in traffic practice, and derive a formula and it's practical algorithm from physicist's achievement.The method and program are proven to be really effective in theoretical simulation and practice examination.
-
Key words:
- maximum entropy method /
- traffic flow /
- probability density function
-
表 1 熵达极大时的分布密度函数
约束方程 概率分布函数 名称 说明 1 均值给定, 且大于‚ f (x) =pqx 几何 x为离散变量, p+q=1 2 均值给定, 且大于 指数 x为连续变量, a为x的下限 3 x仅能出现在a、b之间 均匀 x为连续变量, b > a 4 x的方差固定为 正态 x为连续变量, x的均值为μ 5 韦伯 x > a 6 罗吉斯蒂克 x > a -
[1] JAYNES E T. Information theory and statistical mechanics[J]. Physical Review, 1957, 106(4): 620-630. [2] 吴乃龙, 袁素云. 最大熵方法[M]. 长沙: 湖南科学技术出版社, 1999.286-298.