Non-blocking Vehicle Movement Method in Parallel Microscopic Traffic Simulation

A micro-traffic simulation and vehicle movement technology, applied in the field of micro-traffic simulation and system simulation, can solve problems such as difficulty in balancing thread load, high computer performance requirements, and failure to achieve hardware performance, to meet real-time simulation, eliminate synchronization overhead, The effect of improving overall performance

Active Publication Date: 2017-08-25
浙江成功软件开发有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because the microscopic traffic simulation system needs to simulate the behavior of each vehicle, the performance requirements of the computer are high, and the traditional microscopic traffic simulation system cannot simulate a large-scale traffic system.
[0003] At present, there are two types of parallel micro-traffic simulation methods. One is to create multiple threads, and each thread completes a specific job, but the threads are asymmetrical, that is, each thread is responsible for different tasks, so it is difficult to balance the threads. The load between them cannot make the number of threads flexibly increase or decrease according to the number of CPU cores; another type of parallel simulation method threads are equal, but locks are used to control the interaction of threads, that is, a blocking synchronization scheme
No matter which solution, it has not yet reached the limit of hardware performance, which will affect the further improvement of the performance of the micro simulation system

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Non-blocking Vehicle Movement Method in Parallel Microscopic Traffic Simulation
  • Non-blocking Vehicle Movement Method in Parallel Microscopic Traffic Simulation
  • Non-blocking Vehicle Movement Method in Parallel Microscopic Traffic Simulation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0022] A non-blocking vehicle moving method in a parallel micro-traffic simulation of the present invention comprises the following steps:

[0023] (1) Simulation initialization stage, including the following sub-steps:

[0024] (1.1) Create a vehicle management device (LVC) for each lane in each road segment.

[0025] The vehicle management device (hereinafter referred to as LVC) is used to manage the vehicles on the lane, and its structure is as follows: figure 1 As shown, it consists of two parts: a buffer, which can hold at most a pointer to a vehicle object, and is used to save the vehicle that has just entered from the upstream of the lane; a vehicle container, which is used to save the vehicles on the lane, and the vehicles are in the order of their positions Sort. In the simulation initialization stage, it is necessary to create an LVC for each lan...

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

No PUM Login to view more

Abstract

The invention discloses a non-blocking vehicle movement method in parallel micro-traffic simulation. The method first creates a vehicle management device for the lane in each road section, which is used to manage the vehicles on the lane. Road segments are divided into multiple groups, and each group is assigned a thread responsible for simulating the state of the vehicle. When the vehicle travels across the road, it will bring about the problem of concurrency and thread competition. To solve this problem, this method uses a hardware-level atomic instruction CAS instruction to implement an optimistic concurrency strategy based on conflict detection, that is, non-blocking synchronization. The scheme avoids the use of locks, reduces the performance loss of interaction between threads in the concurrent simulation environment, and significantly improves the performance of the entire micro-traffic simulation system, meeting the real-time simulation needs of urban-scale road traffic systems.

Description

technical field [0001] The invention relates to the field of system simulation and micro-traffic simulation, in particular to a non-blocking vehicle moving method in micro-traffic simulation in a parallel environment. Background technique [0002] Traffic problem has always been a serious social problem, restricting the development of cities. Because the road traffic system is a complex giant system, pure theoretical research or experimental methods are not good enough, but the microcosmic traffic simulation system based on computer simulation technology is an effective means to analyze and solve traffic problems. Because the microscopic traffic simulation system needs to simulate the behavior of each vehicle, it requires high computer performance, and the traditional microscopic traffic simulation system cannot simulate a large-scale traffic system. [0003] At present, there are two types of parallel micro-traffic simulation methods. One is to create multiple threads, and...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/50
Inventor 张子健陆宇飞陈奇江洁羽
Owner 浙江成功软件开发有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products