Emerging Architectures for Global System Science

Authors: Michela Milano, Pascal Van Hentenryck

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Global System Science (GSS) (Jaeger et al. 2013) is the evidence-based study of such complex systems. Its goal is to identify fundamental concepts that help structure problems, identify phenomena, and organize actions. GSS looks at systems holistically, studying their main components and how they interact. In particular, GSS jointly studies The underlying complex infrastructure/organization, including the physical laws and the process governing it. The environment influencing and being influenced by the system. The human factor driving and perturbing the dynamics of such systems. The conflicting interests of a number of self-interested actors involved in the process. The different time/geographical scales at which the system components operate. The goals of GSS research are already present in the study of many isolated subsystems and they include: Descriptive analytics: Understanding the system behaviour, its components, and their relations. Predictive analytics: Predicting how the system will behave over time. Operational Control: Controlling and optimizing the dynamics of the system. ... Figure 2: The Financial Incentives and the Photovolatic Panels (in k Ws) Installed in Emilia-Romagna. Figure 3 depicts our partial implementation of the general architecture. It considers both the strategic and tactical levels. An optimization model is used for the strategic component, while the tactical decision-making module is implemented through mechanism design. Finally, a multi-agent simulation is used for predictive modeling in the tactical layer, capturing both economic and social influence.
Researcher Affiliation Academia Michela Milano(1), Pascal Van Hentenryck(2) (1) DISI, University of Bologna Italy (2) NICTA and the Australian National University, Australia (pvh@nicta.com.au)
Pseudocode No The paper does not contain any pseudocode or algorithm blocks. It includes architectural diagrams (Figure 1, 3, 4, 5) but no step-by-step algorithms formatted as pseudocode.
Open Source Code No The paper does not include any statement or link indicating that the source code for the described methodology or architecture is publicly available.
Open Datasets No The paper discusses the use of 'data sets of unprecedented scale and accuracy' in the introduction and mentions 'data sources about population, mobility patterns, and background traffic' in the context of case studies. However, it does not specify any publicly available datasets by name, provide direct links, DOIs, or formal citations with author/year information for any datasets used in implied experiments.
Dataset Splits No The paper discusses general modeling and simulation approaches within case studies but does not provide specific details on dataset splits (e.g., training, validation, test percentages or counts) or cross-validation methodologies.
Hardware Specification No The paper does not specify any hardware details (e.g., CPU, GPU, memory, or specific computing infrastructure) used for running any simulations or computations mentioned.
Software Dependencies No The paper mentions types of models and tools like 'optimization model', 'mechanism design', 'multi-agent simulation', 'hydro-dynamic models', 'neural nets (Bartolini et al. 2011)', 'decision trees, and regression models (Borghesi et al. 2013)'. However, it does not provide specific version numbers for any of these software components, libraries, or solvers.
Experiment Setup No The paper discusses high-level architectural concepts and outlines the application of various models (e.g., optimization, simulation) within case studies. However, it does not provide specific experimental setup details such as hyperparameter values (e.g., learning rates, batch sizes), training configurations, or model initialization settings.