Bayonet traffic flow prediction method

Abstract

The invention discloses a bayonet traffic flow prediction method. The method comprises the following steps: step 1, preprocessing historical bayonet traffic data; step 2, constructing a data structureto store the historical data; 3, acquiring historical data required by the prediction model from the R tree; and step 4, finding K most relevant historical time periods for prediction in combinationwith the relevant checkpoints and the relevant time periods. According to the problem of traffic flow prediction, an algorithm idea of non-parametric regression is utilized, a method of combining an Rtree and a hash function is used for storing and searching data, historical data and surrounding intersection data are combined for traffic flow prediction, and the prediction requirement of trafficdata flow is efficiently met. According to the invention, the congestion condition of the target intersection at the prediction time can be predicted according to the demand of the user for the traffic congestion prediction condition, and the prediction of the traffic flow can be efficiently and accurately realized.

Description

technical field [0001] The invention proposes an efficient checkpoint traffic flow prediction method. [0002] technical background [0003] Traffic flow prediction at city checkpoints plays an important role in real life, such as navigation systems and online map services. Real-time route planning based on real-time traffic flow prediction technology can guide users to avoid traffic jams, which not only shortens the time required for travel, but also saves energy and reduces air pollution. In recent years, the core subsystems of Intelligent Transportation System (ITS) are Traffic Signal Control System (TSCS) and Traffic Flow Guidance System (TFGS), and these functions have been widely used in China. TSCS manages the traffic flow state of the road through marking control, and TFGS provides traffic information for drivers so that drivers can adjust their driving routes to achieve overall traffic flow balance, that is, try to make the road smooth, and accurate traffic flow inf...

AI Technical Summary

Problems solved by technology

However, existing traffic flow prediction models suffer from one or more of the following disadvantages: (1) The data used are collected by traffic sensors, which cannot effectively cover urban areas

However, due to the large urban traffic flow and the complex urban road network, the traffic flow prediction model based on the above method is not suitable for urban areas

(3) Some urban traffic flow prediction models use additional information that has an impact on traffic data (such as occupancy data and weather data) to make predictions, but such models are usually used in specific locations in urban central areas and cannot cover the entire city well , the scope of application is small

Images