Experienced travel time prediction for congested freeways

Abstract

a b s t r a c tTravel time is an important performance measure for transportation systems, and dissemination of travel time information can help travelers make reliable travel decisions such as route choice or departure time. Since the traffic data collected in real time reflects the past or current conditions on the roadway, a predictive travel time methodology should be used to obtain the information to be disseminated. However, an important part of the literature either uses instantaneous travel time assumption, and sums the travel time of roadway segments at the starting time of the trip, or uses statistical forecasting algorithms to predict the future travel time. This study benefits from the available traffic flow fundamentals (e.g. shockwave analysis and bottleneck identification), and makes use of both historical and real time traffic information to provide travel time prediction. The methodological framework of this approach sequentially includes a bottleneck identification algorithm, clustering of traffic data in traffic regimes with similar characteristics, development of stochastic congestion maps for clustered data and an online congestion search algorithm, which combines historical data analysis and real-time data to predict experienced travel times at the starting time of the trip. The experimental results based on the loop detector data on Californian freeways indicate that the proposed method provides promising travel time predictions under varying traffic conditions.

Urban Road Travel Time Prediction based on ELM

“…Accuracy TTP enables drivers to make decisions, such as route choice and departure time. Besides, the TTP can be used by transportation agencies to deploy efficient control measures and to prevent potential traffic congestion [1]. The travel time and other variables(such as traffic speed,density,flow occupancy,etc) are directly used as the state variable in time series model methods or data-driven methods, and they can be used to predict travel times [2].Time series methods construct the time series relationship of travel time or traffic state, and then current and/or past traffic data are used in then constructed models to predict travel times in the next time interval [3].…”

Modelling reliability and distribution of travel times in transit

“…Another limitation of the GMM model is its instability for each run of the algorithm, due to random initialization of the parameters, small sample size and inadequate number of components (B.-J. Yildirimoglu and Geroliminis, 2013). It is important to properly clean the data and determine the optimal number of components for GMM model in practice.…”

“…GMM is a special type of mixture models where the component distribution is Gaussian and is used as a clustering method that is more appropriate than k-means clustering, especially when clusters have different sizes and correlation within them (Yildirimoglu and Geroliminis, 2013). A GMM model with K components has the following PDF:…”

“…The GMM model can be estimated using the Expectation-maximization (EM) algorithm (Kazagli and Koutsopoulos, 2013;Yildirimoglu and Geroliminis, 2013). Considering a sequence of …”

“…k-means++ selects each centroid with a probability proportional to the distance from itself to the closest centre that has been already chosen. It has been used in the literature to find centroid seeds for the k-means Artificial cuts relate to the fact that when some natural clusters may be classified in an artificial way to satisfy the given cluster number and thus can cause instability (Yildirimoglu and Geroliminis, 2013). The silhouette width (SW) for a point measures how similar the point is to points in its own cluster, compared to points in other clusters.…”