Distributed Decision Modules for Conflict Resolution in Automated Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated control systems face challenges in managing large numbers of conflicting constraints, operating in a coordinated manner with other systems, and making real-time control decisions with partial information, especially in complex physical systems like micro-grids, vehicles, inventory management, and cyber-security.
Innovation Solution
The Collaborative Distributed Decision (CDD) system constructs and deploys executable decision modules that interact with users to generate, test, and optimize control actions, using a distributed architecture with components like Decision Module Construction, Control Action Determination, and Coordinated Control Management to synchronize control actions across multiple modules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a distributed architecture with multiple decision modules is used to control complex systems, then the system's ability to handle conflicting constraints and operate in coordinated manner is improved, but the device complexity and difficulty of managing interactions between modules increases
Solution Approach 1:
The control system is divided into multiple independent decision modules, each responsible for specific control decisions. Each module contains its own inference engine and constraint handling capabilities, allowing the system to manage complex conflicting constraints by distributing the decision-making process across modular components rather than requiring a monolithic control structure.
Solution Approach 2:
The decision modules are designed with universal interfaces and standardized communication protocols that enable them to function in multiple roles. Each module can operate independently or coordinate with others, and the modular architecture allows modules to be reused across different control scenarios, reducing overall system complexity despite the distributed nature.
2Speed
If real-time control decisions are made with partial information, then the speed of control response is improved, but the measurement precision and reliability of control decisions deteriorates
Solution Approach 1:
The decision modules incorporate feedback mechanisms that continuously update the state of the controlled system. By using feedback loops, the system can make real-time decisions with available partial information while progressively refining the accuracy of control decisions as more information becomes available through continuous monitoring and state updates.
Solution Approach 2:
The system performs preliminary inference and prediction based on available partial information to prepare control decisions in advance. The probabilistic inference engines generate predicted states and evaluate potential control actions before full information is available, enabling faster response times while maintaining decision quality through anticipatory computation.
Data Source
AI summary
Techniques are described for implementing automated control systems that manipulate operations of specified target systems, such as by modifying or otherwise manipulating inputs or other control elements of the target system that affect its operation (e.g., affect output of the target system). An automated control system may in some situations have a distributed architecture with multiple decision modules that each controls a portion of a target system and operate in a partially decoupled manner with respect to each other, such as by each decision module operating to synchronize its local solutions and proposed control actions with those of one or more other decision modules, in order to determine a consensus with those other decision modules. Such inter-module synchronizations may occur repeatedly to determine one or more control actions for each decision module at a particular time, as well as to be repeated over multiple times for ongoing control.