Short Term Prediction of Travel Time on Links of Network using Transit Buses Positioning System Data

Link travel time is the most important variable for determining travel route and start time of journeys. Link travel time is the basis of navigation and routing systems. Time dependent algorithms in Geographic Information Systems (GISs) calculate fastest routs based on the travel duration of links of a network depending on different times or dates. In fact, travel time estimation for future is the basis of time dependent routing. Currently different means of monitoring traffic flow such as traffic cameras or electromagnetic sensors are present [1]. However, these methods cannot estimate link travel time efficiently; high cost, low accuracy and dependency on human agents are major problems of using these methods. By emerging usage of portable receivers of positioning systems, researchers are more interested in exploiting the data produced by such equipments for monitoring traffic speed flow. Nowadays most public transit buses are equipped by AVL systems for monitoring purposes. In this research, travel durations of arterial links are estimated in real time by obtaining data from transit buses. Essential corrections for complications caused by buses slower speed and their leaving traffic flow at bus stops are modeled and applied towards a better assessment [5, 6].
Determining link travel durations in time intervals needs an analysis on spatio-temporal data. We estimate travel duration for time intervals of 15 minutes length (7am to 9pm) assuming invariant parameters in calculation of travel duration for each interval. In our approach, first we calculate the travel duration for buses and compensate for the delays caused by bus stops, which include the acceleration and deceleration time at each stop. Simultaneously, timing data of traffic lights control signals are also incorporated in computations to improve accuracy of bus travel duration estimation. We use historical data to find required parameters for calculating bus travel duration. In addition to historical data, we also integrate real-time data and time series analysis to improve our travel duration estimation. In this research we use Holt-winters analysis [14] for a short term prediction of travel time. Finally, we obtain a set of observation equation that is solved by an optimization method.
Buses movement data of two different bus routes in five days (6th to 10th December 2014) are used to estimate travel duration of three links in Motahari Street. Position information of each bus is provided every two minutes plus the time and position of every time the bus doors opens and closes. On the fifth day (10th December) three test vehicles equipped with GPS recievers are employed to collect validation movement data every one second. Drivers of the test vehicles are instructed to avoid extreme low or hight speed and drive with the flow of traffic in the middle lanes insofar as possible. Finally, calculated travel times are compared with results of two well-known methods namely baseline estimation algorithm [8] and Helinga method [4]. RMSE of the proposed approach indicates 22 percent improvement compared to Helinga approach and 30 percent improvement in comparison to baseline algorithm. This improvement shows that information obtained from a public bus monitoring system can be used efficiently for arterial link travel time estimation.