Abstract
As the world around us gets equipped with widespread sensing, computing, communication, and actuation capabilities, opportunities to improve the quality of life arise. Smart infrastructures promise to dramatically increase safety and efficiency. While data abounds, the modeling and understanding of large-scale complex systems, such as energy distribution, transportation, or communication networks, water management systems, and buildings, presents several challenges. Deriving models from first principles via white or gray box modeling is infeasible. Classical black-box modeling is also not practical as model selection is hard, interactions change over time, and evolution can be observed passively without the chance to conduct experiments through data injection or manipulation of the system. Moreover, the causality structure of such systems is largely unknown.
We contend that determining data-driven, minimalistic models, capable of explaining dynamical phenomena and tracking their validity over time, is an essential step toward building dependable systems. In this work we will outline challenges, review existing work, and propose future research directions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Amini, H., Minca, A.: Inhomogeneous financial networks and contagious links. Oper. Res. 64(5), 1109–1120 (2016)
Barnett, L., Barrett, A.B., Seth, A.K.: Granger causality and transfer entropy are equivalent for Gaussian variables. Phys. Rev. Lett. 103(23), 238701 (2009)
Battistelli, G., Tesi, P.: Detecting topology variations in dynamical networks. In: 54th Conference on Decision and Control, pp. 3349–3354. IEEE (2015)
Chernoff, H.: Approaches in sequential design of experiments. Technical report, Stanford University, CA, Department of Statistics (1973)
Costanzo, J.A., Materassi, D., Sinopoli, B.: Inferring link changes in acyclic networks through power spectral density variations. In: 55th Annual Allerton Conference on Communication, Control, and Computing (2017)
Danks, D., Plis, S.: Learning causal structure from undersampled time series. In: NIPS Workshop on Causality (2013)
Etesami, J., Kiyavash, N.: Directed information graphs: a generalization of linear dynamical graphs. In: American Control Conference (ACC 2014), pp. 2563–2568. IEEE (2014)
Granger, C.: Investigating causal relations by econometric models and cross-spectral methods. Econometrica 37, 424–438 (1969)
Lacerda, G., Spirtes, P.L., Ramsey, J., Hoyer, P.O.: Discovering cyclic causal models by independent components analysis. arXiv preprint arXiv:1206.3273 (2012)
Massey, J.: Causality, feedback and directed information. In: Proceedings of International Symposium on Information, Theory and Application, (ISITA-1990), pp. 303–305 (1990)
Materassi, D., Salapaka, M.: On the problem of reconstructing an unknown topology via locality properties of the Wiener filter. IEEE Trans. Autom. Control 57(7), 1765–1777 (2012)
Materassi, D.: Norbert Wiener’s legacy in the study and inference of causation. In: 2014 IEEE Conference on Norbert Wiener in the 21st Century (21CW), pp. 1–6. IEEE (2014)
Materassi, D., Innocenti, G.: Topological identification in networks of dynamical systems. IEEE Trans. Autom. Control 55(8), 1860–1871 (2010)
Materassi, D., Salapaka, M.V.: Network reconstruction of dynamical polytrees with unobserved nodes. In: 51st Annual Conference on Decision and Control, pp. 4629–4634. IEEE (2012)
Materassi, D., Salapaka, M.V.: Reconstruction of directed acyclic networks of dynamical systems. In: American Control Conference (ACC 2013), pp. 4687–4692. IEEE (2013)
Materassi, D., Salapaka, M.V.: Graphoid-based methodologies in modeling, analysis, identification and control of networks of dynamic systems. In: American Control Conference (ACC 2016), pp. 4661–4675. IEEE (2016)
Mooij, J.M., Peters, J., Janzing, D., Zscheischler, J., Shölkopf, B.: Distinguishing cause from effect using observational data: methods and benchmarks. J. Mach. Learn. Res. 17, 1–102 (2016)
Pearl, J.: Causality. Cambridge University Press, Cambridge (2009)
Pearl, J.: Simpson’s paradox: an anatomy. Department of Statistics, UCLA (2011)
Pearl, J., Verma, T.S.: A theory of inferred causation. Stud. Logic Found. Math. 134, 789–811 (1995)
Quinn, C.J., Coleman, T.P., Kiyavash, N., Hatsopoulos, N.G.: Estimating the directed information to infer causal relationships in ensemble neural spike train recordings. J. Comput. Neurosci. 30(1), 17–44 (2011)
Rahimian, M.A., Preciado, V.M.: Detection and isolation of failures in directed networks of lti systems. IEEE Trans. Control Netw. Syst. 2(2), 183–192 (2015)
Sadamoto, T., Ishizaki, T., Imura, J.I.: Hierarchical distributed control for networked linear systems. In: 2014 IEEE 53rd Annual Conference on Decision and Control (CDC), pp. 2447–2452. IEEE (2014)
Schreiber, T.: Measuring information transfer. Phys. Rev. Lett. 85(2), 461 (2000)
Talukdar, S., Prakash, M., Materassi, D., Salapaka, M.V.: Reconstruction of networks of cyclostationary processes. In: 2015 IEEE 54th Annual Conference on Decision and Control (CDC), pp. 783–788. IEEE (2015)
Verma, T.S., Pearl, J.: Equivalence and synthesis of causal models. Technical report R-150, UCLA, Computer Science Department (1990)
Weerakkody, S., Sinopoli, B., Kar, S., Datta, A.: Information flow for security in control systems. In: 55th Annual Conference on Decision and Control, pp. 5065–5072. IEEE (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Sinopoli, B., Costanzo, J.A.W.B. (2018). Modeling Dynamical Phenomena in the Era of Big Data. In: Lohstroh, M., Derler, P., Sirjani, M. (eds) Principles of Modeling. Lecture Notes in Computer Science(), vol 10760. Springer, Cham. https://doi.org/10.1007/978-3-319-95246-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-95246-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-95245-1
Online ISBN: 978-3-319-95246-8
eBook Packages: Computer ScienceComputer Science (R0)