Decision and Control of Complex Systems: a Data-Driven Framework

Project Status: Active

The objective of this research is to develop the mathematical foundations and framework for controlling and optimizing complex systems by developing data-driven machine learning and artificial intelligence.  We plan to develop a unified theoretical foundation based on probabilistic graphical models (PGMs), addressing the challenges on model structure determination, model parameter estimation, and the foundational issue of analyzing uncertainties.  The research efforts in this project are organized into four inter-dependent technical thrusts: model construction, uncertainty quantification, decision and control, and continual learning.  The focus of the first two thrusts is to develop theories and methods for construction of PGM-based complex system models based on observational data under multiple sources of uncertainty. 

The goal of the decision and control thrust is to develop a control mechanism for complex systems with uncertainties and limited observability.  The continual learning thrust copes with the time-varying nature of the underlying dynamics.  The objective of a cross-cutting thrust, application demonstration, is to develop the strategy for general applicability and validation, and to conduct proof-of-concept demonstrations.  The development of these applied math capabilities for the decision and control will not only advance our understanding of the complex system from a theoretical perspective but also significantly impact the Department of Energy’s scientific missions.

Last Updated: September 1, 2020 - 9:01 pm