A knowledge based real-time travel time prediction system for urban network

Abstract

Many approaches had been proposed for travel time prediction in these decades; most of them focus on the predicting the travel time on freeway or simple arterial network. Travel time prediction for urban network in real time is hard to achieve for several reasons: complexity and path routing problem in urban network, unavailability of real-time sensor data, spatiotemporal data coverage problem, and lacking real-time events consideration. In this paper, we propose a knowledge based real-time travel time prediction model which contains real-time and historical travel time predictors to discover traffic patterns from the raw data of location based services by data mining technique and transform them to travel time prediction rules. Besides, dynamic weight combination of the two predictors by meta-rules is proposed to provide a real-time traffic event response mechanism to enhance the precision of the travel time prediction.

Introduction

Nowadays, travel time information plays an important role in several fields of intelligent transportation systems (ITS), such as advanced traffic management systems (ATMS), advanced traveler information system (ATIS), commercial vehicle operation (CVO) and emergency management system (EMS). Besides, travel time prediction (TTP) also contributes to traveler, traffic administrator, and logistics operators. For travelers and logistic operators, accurate travel time estimation could avoid congested sections to reduce transport costs and increase service quality. For traffic managers, travel time information is an important index of traffic system operation. Furthermore, using travel time information can scatter the condensed traffic volume and sharply reduce the habitual traffic congestion in effective, because people might choose various public transportations as their wishes. So, real-time TTP is a meaningful traffic index to be referred. However, TTP for urban network is highly stochastic and time-dependent due to random fluctuation in travel demands, interruptions caused by traffic control devices, incidents, road construction, and weather conditions. In other words, travel time is affected by a set of traffic factors including speed limit, traffic volume, routing path selected, occupancy of road and traffic facilities (e.g., signals) as well as non-traffic factors including traffic event, weather, road construction, etc. Most previous researches predicted travel time based on some traffic factors, such as speed, volume or occupancy, and did not take the non-traffic factors into consideration. Thus, the previous research approaches did not work well in real traffic condition.

Study by Iroy and Kuwahara (2001) found that level of reduction in congestion depends on the complexity of the road network. Vehicular flows on freeways are often treated as uninterrupted flows; flows on urban network are conceivably much more complicated since vehicles traveling on urban network are subject to not only queuing delays but also signal delays as well as to turning delays. Thus, TTP for an urban network is more challenging than predicting the travel time for freeway or single arterial. Besides, the routing and path selection problems should be solved in TTP for urban network, e.g., the TTP model has to decide which path on a given OD (origin and destination) pair as request to be the suggested path. Many models had been proposed for travel time prediction in these decades, but most of them focused on predicting the travel time on freeway (Chien and Kuchipudi, 2003, Rice and van Zwet, 2004, Wu et al., 2004) or simple arterial network (Jiang and Zhang, 2003, Lin et al., 2004).

In the past, many ITS studies and transportation agencies use the traffic data from dual-loop detectors which are capable of archiving with traffic count (the number of vehicles that pass over the detector in that period of time), velocity, and occupancy (the fraction of time that vehicles are detected) and readily available in many locales of freeways and urban roadways (Lin & Zito, 2005). Nowadays, traffic data collecting techniques have made great progress and evolved to real-time collecting in order to improve traffic management efficiency. In Lin and Zito (2005), traffic information collection and travel time measurement can be divided into three categories: site-based, vehicle-based and sensor-based measurement. Site-based measurement collects vehicle license plate characters and arrival times at various checkpoints through automatic vehicle identification (AVI) technologies, matches the license plates between consecutive checkpoints, and computes travel times from the difference between arrival times. Vehicle-based methods make TTP by analyzing raw data collected from fleet of probe vehicles. Sensor-based methods make TTP measurement by collecting raw data from the stationary sensors like loops detectors, transponders or radio beacons installed at arterial roads. However, each traffic information collection method used for TTP has some drawbacks and limitations. For example, site-based and sensor-based TTP methods have the spatial coverage problem because the sensors or AVI devices are fixed and limited. Vehicle-based TTP methods (Chung et al., 2003, Nakata and Takeuchi, 2004, Yang, 2005) have cost, spatial and temporal coverage problems because the total cost is very high if a dedicated fleet of urban network traffic probing vehicle is maintained.

There are numerous previous TTP approaches based on the historical traffic data analysis in the literatures, which can be categorized as follows (Lin & Zito, 2005): regression method (mathematical model) (Wu et al., 2004), time series estimation method, hybrid of data fusion or combinative model (Wen, Lee, & Cho, 2005) and artificial intelligence method like neural network (Mark, Sadek, & Rizzo, 2004). In Nakata and Takeuchi (2004), auto regression (AR) model and state space model for time series modeling were used to predict travel time. The Kalman filtering provides an efficient computational (recursive) in many TTP researches (Chung, 2003, Chung et al., 2003, Lin et al., 2004, Yang, 2005), because it is very powerful in several aspects: it supports estimations of past, present, and even future states even if the precise nature of the modeled system is unknown. In Wu et al. (2004), the support vector regression model was used to predict travel time for highway users. In Bajwa, Chung, and Kuwahara (2004), pattern matching technique was used for TTP. Traffic patterns similar to the current traffic are searched among the historical patterns, and the closest matched patterns are used to extrapolate the present traffic condition. Chung et al. (2003) developed an OD estimation method to make more accurate estimation of traffic flow and traffic volume in congestion traffic status. Moreover, the data fusion models of TTP integrated grey theory (Takahashi, Takahashi, & Izumi, 2003) and neural network-based. Yang (2005) developed some hybrid models toward data treatment and data fusion for traffic detector data on freeway.

However, most of the previous works only consider the static models of spatial network and predicted travel time based on the historical collected data, and thus lack the consideration of real-time events and traffic status. In other words, none of real-time events (e.g., detours and traffic congestions) affecting the spatial network can be reflected in the prediction result. Travel time prediction for urban network in real time is hard to achieve due to the following reasons: (1) network complexity, (2) path routing and selection problem in road network, (3) the collection of sensor data in real time is not available or cost-effective, (4) spatiotemporal data coverage problem of sensor- or vehicle-based travel time prediction, and (5) low precision due to lack of event response mechanism. To make TTP system more practical and more precise, a real-time knowledge based TTP model is proposed in this paper to take the advantage of independent knowledge base so that TTP knowledge can be dynamically adjusted to fit the changing requirement and response to external events. It results in that prior knowledge contributed by domain expert (meta-rules) and pattern knowledge mining from LBS-based applications can be evolved with the environment.

The basic idea of the proposed TTP model is that travel time along a selected path can be estimated by summing up the links travel time with intersections delay, as shown in Eq. (1), where link travel time can be estimated by linear combination of current (real time) and historical predictors. Origin (O), destination (D) and journey start time (t) are the input parameters of the prediction formula T(O, D, t). Two sub-functions T_c and T_h are two link travel time predictors based on current and historical traffic information, respectively, and T_d presents the total intersection delays of the passing through intersections in the path. Two control variables α and β are the weighted combination variables for current (T_c) and historical (T_h) predictors, respectively. The weights for these two predictors are decided by meta-rules given by domain expert, which are discussed in Section 3.

$$\begin{array}{cc}\hfill & T(O\text{,}D\text{,}t)=\alpha ·T_{\text{c}}(O\text{,}D)+\beta ·T_{\text{h}}(O\text{,}D\text{,}t)+T_{\text{d}}(O\text{,}D\text{,}t)\hfill \\ \hfill & \text{where}\alpha +\beta =1\hfill \end{array}$$

The objective of this paper is to propose a real-time TTP model for an urban network that predicts travel time by linear combination of the results of real-time and historical travel time predictors based on the request of an origin (O) and destination (D) pair. The model utilizes the raw data of location-based services (LBS), transforms it to the traffic information by combining the geographical information system (GIS), and predicts travel time by integrating the historical traffic data regression, real-time traffic information and real-time external information sources, where external information sources include the real-time information that may affect TTP, such as incidents, road construction, and weather. Besides, meta-rules offered by traffic domain experts to raise the precision of real-time TTP can dynamically tune the combination weights of historical and real-time TTP according to the external events. For example, a current car accident on a link in the path of O, D pair may trigger one of the meta-rules to raise the weight of real-time TTP on that link, because the traffic delay on that link will be reflected immediately by the real-time LBS. This model combining the data mining and knowledge based system technologies mines the traffic patterns from location-based services (LBS) and transforms them to the TTP inference rules, so that it can handle the issues of non-traffic factors as well as traffic factors.

The model proposed in this paper utilizes the raw data of LBS-based applications, and regards the vehicles in the LBS-based applications as the traffic probing vehicle. Comparing to the traditional vehicle-based TTP, it is cost-effective because the traffic information is derived by only mining the raw data of LBS-based applications. Moreover, the size of LBS fleet has the temporal and spatial coverage advantages. Traffic information can be dynamically gathered in the LBS fleet operation area 24 h per day in real time.

The following sections are arranged as follows. Section 2 gives the introduction of LBS, and explains how traffic information can be derived from LBS. The proposed knowledge based TTP methodology is detailedly discussed in Section 3. In Section 4, we implemented the prototype TTP system for Taipei urban network by utilizing the taxi dispatching system as our LBS data source. Real-time, historical and linear combination predictors are evaluated and compared in this section. Finally, concluding remarks and future research are presented in Section 5.