作者: Wai Yuen Szeto , S Travis Waller , ManWo Ng
DOI:
关键词: Distribution (mathematics) 、 Bounded function 、 Mathematics 、 Reliability (statistics) 、 Mathematical optimization 、 Probability distribution 、 Interval (mathematics) 、 Structure (category theory) 、 Econometrics 、 Bounding overwatch 、 Random variable
摘要: An assumption that pervades the current transportation system reliability assessment literature is probability distributions of sources uncertainty (i.e. road capacities and travel demand) are known explicitly. However, this distribution may be unavailable (inaccurate) in reality as there no (insufficient) data to calibrate distribution. In paper, authors relax present a method assess time distribution-free sense methodology only requires mean values capacity demand they reside bounded interval. Moreover, proposed eliminates need specify dependence structure among random variables. Instead deriving exact probabilities on times exceeding certain thresholds via computationally intensive methods, develop analytical inequalities quickly obtain bounds desired probability. Numerical experiments demonstrate derived nontrivial for most interesting cases from perspective.