Intelligent management system for road traffic condition instant prediction

Abstract

The invention discloses a system for intelligent management on the basis of the prediction of future road traffic conditions (speed and flow). The system comprises a data fusion processing module, a mathematic model prediction computation module and a traffic guidance management module based on prediction. The system creates standardized information input by implementing data fusion on the diversified traffic information collected in real-time, judges, by means of historic data, interconnection of road network traffic flows to establish a parameterized statistical model and further computes the traffic conditions (such as speed and flow) of each road in the road network in the coming 90 minutes, wherein, the time precision is consistent with the time interval of the real-time data collection. Then the system further judges and creates quantifiable traffic indicators in accordance with the prediction result, comprising: the traffic jam probability of each road in the future, the time the jammed roads are clear and traffic flow abnormal alarms, thus providing policy support for traffic participants and managers.

Description

Technical field [0001] The present invention is a system for intelligent management based on real-time prediction of future road traffic conditions (speed and flow). Background technique [0002] In the transportation domain, travel time is essential to provide navigation for travelers and dispatchers. In the traffic network, this information is usually obtained by taking the average value of each link. Based on the average travel time, we can use many shortest path algorithms to find the best travel route. A path in a traffic network is composed of one or more road segments. There are several traditional approaches to computing navigation and optimal paths for future time periods. [0003] The most common method is to take the average. This method can provide the user with an average best path. However, due to road congestion, there will be a large gap between the average travel time of a certain road segment and the real travel time at a certain time. For example, th...

AI Technical Summary

Problems solved by technology

[0007] The third method is to predict by computer neural network and non-parametric regression model. This type of method has been tried by many research groups for actual traffic prediction since the 1990s. However, due to the inherent shortcomings of this method, Its calculation speed is slow and it cannot be used to predict the road network with large-scale precision coverage at the same time, and her prediction accuracy is not high. More importantly, in this type of solution, some external factors (such as weather, road zero-time construction, Large-scale activities) can not reflect the impact on traffic flow in time.

[0010] (2) Since the effects of weather or events are very different for different road segments, it is often not enough to calculate the average travel time with a single weighting factor

In addition, high-detail data for the current situation, as assumed in the first traditional method, is generally not available for most road segments, and is not effective for very short-term predictions

Images