A Prediction Method for Efficient Parking Spaces

Abstract

The invention relates to an effective parking space prediction method which is used for predicting the number of effective parking spaces of small and medium-sized parking lots. The effective parking space prediction method is characterized by comprising the following steps: step one, a time sequence of initial effective parking spaces is acquired; step two, initial prediction is performed by applying a GM(1, 1) prediction model according to the time sequence of the effective parking spaces so as to acquire an initial prediction time sequence; step three, a Markov prediction model is built to perform modification prediction so as to acquire a modification prediction time sequence; step four, an early prediction time period and a late prediction time period are set; step five, early prediction is performed on the early prediction time period by applying a wavelet neural network according to the modification prediction time sequence so as to acquire an early prediction value and an early prediction time sequence; step six, prediction is performed on the late prediction time period by applying a Lyapunov exponent method according to the early prediction time sequence so as to acquire a late prediction value; and step seven, performing combination calculation on the early prediction value and the late prediction value so as to acquire a predicted value of the parking spaces.

Description

technical field [0001] The invention relates to a method for predicting effective parking spaces, in particular to a method for predicting effective parking spaces for small and medium-sized parking lots. Background technique [0002] Effective parking spaces refer to the parking spaces available for parking vehicles in the current parking lot. Parking demand, the effective parking spaces in different time periods have great fluctuations; (2) Spatial inhomogeneity: the parking demand in different functional areas of the city is different, resulting in parking lots in different areas in the same time period. There is a big difference in the number of effective parking spaces, and the supply and demand in the urban central area and non-central areas are unbalanced; (3) Resource limitations: the main planning and construction of most cities in my country have been completed, especially in the urban central area. very limited. Therefore, it is necessary to adopt a suitable method...

AI Technical Summary

Problems solved by technology

[0007] Although the first method combines multiple influencing factors, it can make short-term predictions for effective parking spaces, but its ability to deal with data fluctuations is weak, and the stability of prediction results is poor.

The second method can significantly reduce the volatility of the collected data and modify the output results, but its computing power has certain limitations, and the accuracy rate will decrease when the data is large

Although the third method has high fault tolerance and robustness, and has the prediction ability of fitting nonlinear complex systems, due to its limited processing ability for input data, the prediction tends to fall into local optimum, and the prediction results fluctuate randomly. The stability is large, and the prediction results are sometimes less stable

Images