Traffic Bottleneck Detection on Transportation Network Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods are inadequate for detecting traffic bottlenecks in non-linear roadway networks and fail to classify bottlenecks that vary in location across time periods or days, limiting their effectiveness in managing complex traffic congestion.
Innovation Solution
A system and method utilizing link-speed data on a directed graph of roadway links to detect and classify bottlenecks, even with incomplete data, by projecting traffic data onto road network links and defining nearby upstream links to identify sustained or recurring bottlenecks, regardless of location variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing bottleneck detection methods are used on linear detector sequences, then simple bottlenecks on single roadways can be detected, but bottlenecks in non-linear roadway networks and complex bottleneck patterns cannot be detected
Solution Approach 1:
The patent transitions from analyzing linear sequences of detector data to analyzing spatial graphs representing non-linear roadway networks. By mapping detectors to graph nodes and incorporating spatial relationships, the system detects bottlenecks in multi-dimensional network structures rather than simple linear sequences, enabling detection of complex bottleneck patterns across interconnected roadways.
Solution Approach 2:
The patent segments the roadway network into discrete graph components (nodes representing detectors/intersections and edges representing roadway segments). This segmentation allows the system to analyze complex network structures by breaking them down into manageable units while preserving spatial relationships, enabling detection of bottlenecks in non-linear configurations.
2Adaptability or versatility
If bottleneck detection requires exact location matching across time periods, then sustained bottlenecks at fixed locations can be identified, but bottlenecks that vary in location across time periods or days cannot be detected
Solution Approach 1:
The patent implements dynamic bottleneck detection by allowing bottleneck characteristics to evolve across time periods. Instead of requiring fixed location matching, the system identifies recurring bottlenecks that may shift locations by analyzing temporal patterns in the graph data, accommodating the dynamic nature of traffic congestion while maintaining detection accuracy.
Solution Approach 2:
The system uses feedback from historical bottleneck detection across multiple time periods to improve ongoing detection. By comparing detected bottlenecks against historical patterns and allowing for location variations, the system identifies recurring bottlenecks even when their precise locations shift, using past detection results to inform current analysis.
3Reliability
If complete link-speed data is required for accurate bottleneck detection, then detection accuracy is high, but the system cannot operate with incomplete data from certain roadway links
Solution Approach 1:
The patent uses the graph structure as an intermediary to connect and relate available detector data points. When data from certain roadway links is missing, the graph framework allows the system to infer bottleneck conditions by analyzing relationships between available data points and their spatial connections in the network, maintaining detection capability despite incomplete data.
Solution Approach 2:
The graph-based detection framework serves multiple functions: it structures available data, identifies spatial relationships, and compensates for missing data through network analysis. This universal approach allows the system to operate reliably whether data is complete or incomplete, adapting to varying data availability while maintaining detection accuracy.
Data Source
AI summary
Traffic congestion detection, classification and identification includes analysis of link-speed data representative of vehicular speed and capacity on one or more roadway segments to determine non-linear, multi-segment traffic bottlenecks in a transportation network graph. Link-speed data is processed to detect bottleneck conditions, classify bottlenecks and bottleneck-like traffic features according to their complexity, and identify sustained or recurring bottlenecks. Such a system and method of traffic congestion detection, classification and identification provides a framework for using this link-speed data to detect the head and queue of bottlenecks on a directed graph representing the transportation network, classify the resulting bottlenecks and bottleneck-like traffic features according to the shape of their queue, and identify and measure sustained or recurrent bottlenecks even when the location, or head, of the bottleneck varies slightly across multiple time periods or across multiple days.