Urban traffic congestion is one of the most severe problems of everyday life in metropolitan areas. In an effort to deal with these problems, intelligent transportation systems (ITS) technologies have concentrated in recent years on dealing with urban congestion. One of the most critical aspects of ITS success is the provision of accurate real time information and short term predictions of traffic parameters such as traffic flow, travel speed and occupancies. Thus traffic volume forecast will support proactive, dynamic traffic control. This research effort is focused on traffic volume forecasting model using time series analysis. Box and Jenkins approach is used to estimate the time series models. A 1 minute data set representing traffic volume was collected on national highway NH-1 to develop time series model. The Box-Jenkins auto regressive integrated moving average (ARIMA) model of order (p, d, q) is chosen. The values of parameters are determined which fits better for given data set of traffic volume. The developed model is easy to understand and implement. Further model is computationally tractable and only requires the storage of the last forecasted errors and current traffic observations. The results show different model specifications are appropriate for different time periods of day. (A). For the covering abstract of the conference see E216632.
Samenvatting