Decision Support for Complex Networks
Permanent URI for this collection
1 - 5 of 5
ItemMachine Learning of Semi-Autonomous Intelligent Mesh Networks Operation Expertise( 2019-01-08)Operating networks in very dynamic environments makes network management both complex and difficult. It remains an open question how mesh or hastily formed networks with many nodes could be managed efficiently. Considering the various constraints such as limited communication channels on network management in dynamic environments, the need for semi-autonomous or autonomous networks is evident. Exploitation of machine learning techniques could be a way to solve this network management challenge. However, the need for large training datasets and the infrequency of network management events make it uncertain whether this approach is effective for highly dynamic networks and networks operating in unfriendly conditions, such as tactical military networks. This paper examines the feasibility of this approach by analyzing a recorded dataset of a mesh network experiment in a highly dynamic, austere military environment and derives conclusions for the design of future mesh networks and their network management systems.
ItemIn-Depth Behavior Modeling of Transportation Networks: Description and Preliminary Results of a Subway Network Model( 2019-01-08)This paper describes the conceptual ideas behind a computer-aided microsimulation model combining agent-based modeling and discrete event simulation in order to reproduce the complex behavior of a fictitious subway system. Such a model allows passengers to be both active and passive agents behaving according to the model rules, and also affecting them in return, for more realistic results. Decision support in this network can be approached from both the passenger and the network operator perspective, by correctly predicting ridership and system delays. Preliminary results are presented, together with some of the challenges faced throughout the development process.
ItemRisk-Based Decision Support Model for the Optimal Operation of a Smart Energy Distribution Company for Enabling Emerging Resources( 2019-01-08)In this paper, a risk-based decision support model is developed for a smart energy distribution company, enabling emerging resources like renewable energy sources, electric vehicles and demand response programs in a holistic approach. Because of the inherent uncertainties of these emerging resources, the conditional value-at-risk (CVaR) method is adopted to restrict the distribution company’s risk. A risk aversion parameter sensitivity analysis is also provided on the optimal operation of the smart energy distribution company. The proposed model is thoroughly tested on a 15-bus distribution grid system, and the numerical results prove the effectiveness of the model in risk management.
ItemAdvancing Spatiotemporal Modeling of Access to Healthcare – A Methodological Perspective( 2019-01-08)Modelers apply system dynamics (SD) modeling in various fields for different purposes including policy analysis, however, they need to integrate SD with other methodologies to facilitate the inclusion of spatial factors and study their influence on the system’s behavior. We investigate the combination of SD modeling with Geographic Information Systems using healthcare data to facilitate the study of both spatial and systemic factors for more effective policy design. We propose an algorithm for integrating these methodologies and explain one of its applications in the complex health systems—Medicaid beneficiaries’ access to primary care (PC). Our results reveal insights and information that were not available through merely SD modeling; this approach provides the opportunity for policymakers to learn about the influence of spatiotemporal factors on health outcomes in a complex health system, and identify the areas with a high need for PC providers.