Road congestion prediction method based on minimum variation coefficient evaluation and reasoning model

Abstract

The invention discloses a road smoothness predicting method based on a minimum variable coefficient assessment and inference model. According to the method, sample analysis and digging of vehicle-mounted GPS historical data are carried out, a variable coefficient assessment method and a technique for building a road traffic flow characteristic interference model in a sampling cycle are adopted, and road short-time smoothness and future smoothness trends are inferred through floating vehicle data analysis. According to the method, typical sample analysis based on a GPS is adopted, and a statistic cycle is obtained by means of a parameter optimization technique of a road smoothness analysis model, so that the method is supported by a strict mathematical model and has wide adaptability; road situation property types and corresponding rule base relations are quickly obtained by building the road traffic flow characteristic model, road smoothness trend prediction capacity is obtained based on knowledge inference, and statistic efficiency and the service level are greatly improved.

Description

technical field [0001] The invention relates to an optimal statistical cycle method based on the minimum variation coefficient, in particular to a road traffic congestion prediction method based on the minimum variation coefficient evaluation and reasoning model. Background technique [0002] Since the 1960s, people began to apply mature forecasting models in other fields to the field of traffic flow forecasting, and developed a variety of forecasting models and methods, such as time series models, historical trend models, Kalman filter models and neural network models, etc. . [0003] Because time series model modeling is simple and easy to understand, it is especially suitable for stable traffic volume forecasting, so it has been widely used at home and abroad. In recent years, some domestic scholars have further applied the time series model to the real-time prediction of traffic flow. But the model also showed significant inadequacies in predicting delays when traffic ...

AI Technical Summary

Problems solved by technology

However, because the short-term prediction of traffic flow in the next few minutes is affected by large random disturbances and uncertain factors, the research on the real-time prediction model of short-term traffic flow has not yet achieved satisfactory results.

Images