A data-driven control model building method for regional traffic signals
A data-driven control and model-building technology, used in the control of traffic signals, traffic control systems, and traffic control systems for road vehicles, etc.
Active Publication Date: 2022-01-18
NORTH CHINA UNIVERSITY OF TECHNOLOGY
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Traditional traffic signal control is mostly model-based control methods. The traffic control system constructed by it has the problem that the applicability of the model depends on certain assumptions and specific conditions in actual engineering applications, which limits the wide application of the model. The main reason for this phenomenon is The three elements that determine the control strategy are not a complete linear relationship, but a strong coupling relationship between them, and human behavior is difficult to predict. Therefore, the control model constructed for vehicles and roads is consistent with actual error
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] The method comprises the steps of:
[0043] Step 1: Establish positive system model
[0044]The traffic control system has an obvious feature, that is, the non-negativity of the traffic state, which is initially in a non-negative state space, and the traffic state always remains non-negative during the evolution process, such as the number of vehicles in the road section, queue length, traffic density, occupancy rate, etc. A system with such properties is called a positive system. The positive system model Compartment model is a very simplified model. The Compartment system models the evolution of network traffic flow, which can describe the characteristics of network oversaturation with any control structure. The non-negativity constraint of the system state is guaranteed by the nature of the system itself. Given the network traffic flow input, according to the non-negative matrix theory, the network has a unique stable equilibrium. point, the analytical calculation ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a method for establishing a regional traffic signal data-driven control model. The invention is based on floating car data (a typical source of mobile detection data), obtains traffic parameters at intersections through an estimation method, and builds a cycle based on a store-and-forward modeling method. The vehicle number estimation model adjusts the constraints on the green light time at intersections, and introduces a time-varying control signal period C(k) to obtain a new green light time constraint, so as to avoid wasting green light time. At this time, consider breaking the fixed-period constraint , so as to ensure that the space occupancy always satisfies x i (k+1)≥0, the established regional traffic signal control model can simultaneously describe the undersaturated, critically saturated and oversaturated traffic state forms at the intersection, and a multi-agent network-based space occupancy balance is proposed. Targeted regional traffic signal data-driven control model.
Description
technical field [0001] The invention relates to the technical field of intelligent traffic signal control, in particular to a method for establishing a regional traffic signal data-driven control model. Background technique [0002] With the development of social economy and urban transportation, the number of urban car ownership in my country has increased rapidly. At present, the road construction capacity of most cities is far behind the growth rate of motor vehicles, and the contradiction between the two is mainly reflected in the increasingly serious road traffic congestion. Therefore, under limited road space resources, improving road utilization and travel efficiency through intelligent traffic control methods is an important task that urban traffic managers must consider. [0003] With the continuous development of ITS (Intelligent Transport System, ITS) technology, various advanced traffic detection equipment is widely used, which has brought great changes to urban...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/07G08G1/081G08G1/01
CPCG08G1/07G08G1/0112G08G1/081G08G1/0104
Inventor 张海波王力吉鸿海潘彦斌李丹阳
Owner NORTH CHINA UNIVERSITY OF TECHNOLOGY