Real time prediction of unoccupied parking space using time series model

Parking guidance system is an important mean to alleviate status quo of urban static traffic, improve the level of city traffic management and protect the urban environment. Timely and accurate information of remaining berths plays an important role in the parking guidance system which guides the driver to find a parking space efficiently. Therefore, this paper focused on the prediction methods of the unoccupied parking space. Then ARIMA model was selected to forecast the unoccupied parking space. And residual berths forecast model was established based on the general process of ARIMA model. At last, the paper combined the actual data to test the accuracy of forecast and compared with the effect of neural network prediction. Thus, the effectiveness and applicability of ARIMA model to predict residual berths were verified.