Distributed Sensor Agent Consensus Filtering for Robust State Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional centralized Kalman filters are inadequate for distributed processing scenarios, particularly in noisy, time-varying random fields, due to limitations in data privacy and robustness against server failures.
Innovation Solution
A distributed linear filtering and prediction method utilizing a network of sensor agents that detect, estimate, and share data to generate consensus estimates, employing directed optimal gain matrices and a System-Observation-Communication Model framework to ensure robustness and accuracy across a multi-agent network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a centralized Kalman filter is used, then filtering and prediction can be performed with a single processing system, but the system lacks robustness against server failures and compromises data privacy
Solution Approach 1:
The centralized processing system is segmented into multiple distributed sensor agents, each capable of independent filtering and prediction operations. This segmentation eliminates the single point of failure in centralized systems while maintaining collective system functionality through distributed consensus algorithms.
Solution Approach 2:
A consensus mechanism acts as an intermediary between distributed sensor agents, enabling them to reach agreement on state estimates without requiring a centralized server. This intermediary layer provides robustness against failures while preserving data privacy by allowing agents to share only processed estimates rather than raw data.
2Reliability
If a centralized server processes all data, then computational resources are concentrated, but data privacy is compromised and the system is vulnerable to single points of failure
Solution Approach 1:
Data processing is segmented across multiple distributed agents rather than centralized, allowing each agent to retain local data privacy while contributing to collective estimation. This segmentation ensures that no single point controls all data, preserving privacy and enhancing robustness.
Solution Approach 2:
Each sensor agent performs self-service filtering and prediction operations using its own computational resources, eliminating the need to transmit raw data to a centralized server. This self-service approach maintains data privacy while achieving reliable distributed consensus through local processing and selective information sharing.
3Reliability
If sensor agents operate independently without restoration mechanisms, then the system is simpler, but disconnected agents cannot recover and maintain accurate estimates
Solution Approach 1:
A feedback mechanism monitors the connection status of sensor agents and triggers restoration operations when disconnections are detected. This feedback loop ensures that disconnected agents can recover and re-synchronize with the distributed network, maintaining estimate consistency without requiring overly complex predetermined restoration protocols.
Data Source
AI summary
In one aspect of the invention, there is a computer-implemented method including: detecting, by a processor set of a first sensor agent, sensor data from one or more sensors comprised in the first sensor agent; determining, by the processor set, an own series of estimates, based on the sensor data; transmitting, by the processor set, the own series of estimates; receiving, by the processor set, at least one additional series of estimates from additional sensor agents; restoring, by the processor set, in response to detecting that a second sensor agent of the additional sensor agents has become disconnected and then re-connected, the transmitting of the series of estimates to the second sensor agent and the receiving of the series of estimates from the second sensor agent; and outputting, by the processor set, based on the own series of estimates and the additional series of estimates, a series of consensus estimates.