Pipelined IoT Digital Twins for Faster Incident Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Smart traffic systems and other complex systems face challenges in managing incidents in real-time due to the need for predictive capabilities and handling diverse, high-volume data streams from various sources, which limits their ability to respond quickly and effectively to events such as roadblocks or accidents.
Innovation Solution
The implementation of Pipelined Digital Twin Sequences, where an exploratory digital twin is created to simulate the effects of actions on the system by modifying its state and driving itself forward in time, allowing for faster-than-real-time predictions and decision-making, while maintaining a directed acyclic graph structure to manage data flow efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If real-time sensor data from multiple diverse sources is processed to manage incidents in smart traffic systems, then the system can provide comprehensive monitoring and analysis, but the system cannot respond quickly enough to take effective action
Solution Approach 1:
The system performs preliminary actions by creating exploratory digital twins that simulate potential incident scenarios and evaluate response options before actual incidents occur. This allows the system to pre-compute optimal responses and have them ready for rapid deployment when real incidents happen, thus reducing response time while maintaining comprehensive monitoring capabilities
Solution Approach 2:
The system creates digital twin copies of the physical traffic system that can be manipulated and simulated without affecting the real system. These exploratory digital twins serve as virtual test beds for evaluating different response strategies, allowing rapid experimentation and decision-making without the time constraints of real-time operations
2Speed
If exploratory digital twin is created to simulate action effects and drive itself forward in time for predictions, then faster-than-real-time predictions are achieved, but the system complexity increases
Solution Approach 1:
The system segments the digital twin functionality into distinct components: the source digital twin for real-time monitoring and exploratory digital twins for predictive simulation. This segmentation allows each component to be optimized independently, with exploratory twins using simplified models suitable for fast prediction while the source twin maintains comprehensive monitoring capabilities
Solution Approach 2:
The system employs dynamic modeling where exploratory digital twins can adjust their simulation speed and detail based on the specific prediction task. The twins are driven forward in simulated time at accelerated rates, dynamically balancing computational complexity with prediction speed requirements for different incident scenarios
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A method of predicting evolution of simulation results for an Internet of Things, loT, network, comprising: creating a source digital twin for the loT network, driven by real-time sensed data from objects fed to models of the objects, the source digital twin outputting a state of one or more of the objects in real time; optionally forming a main digital twin sequence by: additionally creating one or more clone digital twins, each including the same models and interconnections as the source digital twin; and connecting an input of a first clone digital twin with an output of the source digital twin via a data stream synthesizer node, wherein the data stream synthesizer node adds a time increment to the output of the source digital twin so that the source digital twin drives the first clone digital twin at the incremented time; and connecting an input of any further clone digital twin with an output of a preceding clone digital twin in the sequence via a further data stream synthesizer node, wherein the further data stream synthesizer node adds a further time increment to the output of the preceding clone digital twin so that the preceding clone digital twin drives the further clone digital twin at the further incremented time; creating an exploratory digital twin, which includes the same models and interconnections as the source digital twin; connecting an input of the exploratory digital twin with an output of one of: the source digital twin, the first clone digital twin, and any further clone digital twin, to initialise the exploratory digital twin; modifying an aspect of the exploratory digital twin to simulate an action taken on the exploratory digital twin; connecting an output of the exploratory digital twin with an input of the exploratory digital twin via an additional data stream synthesizer node, wherein the additional data stream synthesizer node adds an additional time increment to the output of the exploratory digital twin to drive the exploratory digital twin at the additionally incremented time; and executing the source digital twin, any clone digital twin, and the exploratory digital twin to provide an evolved modified state of one or more of the objects at the additionally incremented time as the output of the exploratory digital twin.