Emerging Architectures for Global System Science

The following Great Innovative Idea is from Michela Milano at the University of Bologna-Italy and Pascal Van Hentenryck from NICTA Optimisation Research Group and the University of Michigan. Their Emerging Architectures for Global System Science paper was one of the winners at the Computing Community Consortium (CCC) sponsored Blue Sky Ideas Conference Track at the 29th Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence (AAAI-15), January 25-30, 2015 in Austin, Texas.

The Innovative Idea

Our society is organized around a number of (interdependent) global systems: Logistic and supply chains, health services, energy networks, financial markets, computer networks, and cities. Typically, people optimize these systems by considering sub-systems in isolation and ignoring aspects that cannot be modelled easily such as human behavior.

The key idea behind our research is that we should look at global systems much more holistically and pay more attention to interactions between complex infrastructures, man-made processes, natural phenomena, and human behavior. It is the right time to do so because, for the first time in the history of mankind, we have access to data sets of unprecedented scale and accuracy about these infrastructures, processes, natural phenomena, and human behaviors. In addition, there has been tremendous progress in optimization technology (prescriptive analytics) and machine learning (predictive analytics) and their integration may bring substantial benefits.

Impact

Global systems are ubiquitous. By modeling and optimizing them more globally, the hope is to improve social welfare across these systems. This may mean responding better to disasters, saving and producing energy more effectively, improving the quality of life in our cities and health care delivery, or making a supply chain more efficient and resilient.

Other Research

Traditionally, we have been studying well-isolated optimization problems, using techniques from artificial intelligence and operations research, and their hybridization. But, in the last few years, we started looking at energy, disaster management, and supply chains and to integrate strategic, tactical, and operation planning under uncertainty and merging predictive and prescriptive analytics. A key aspect of our research is also to build the underlying mathematical optimization techniques and technology that will scale to these global systems.

Researcher’s Background

We are both computer scientists working in mathematical optimization, often bridging the gap between theory and practice. We prove theorems, we build large systems, and we try solve real applications in the field.