Abstract
The recovery of an infrastructure system after a disruptive event is vital for other systems (and for the community) that require its functionality. Disruptive events occur due to various reasons and for a system to be resilient, it is important to be prepared and ready to respond and restore. Understanding the time required for restoration for different disruptive scenarios enables decision-makers to plan for and schedule resources. In this research work, we explore different machine learning techniques to predict the time taken for an interdependent network to be restored after a disruption. We use as independent variables the restoration rates of disrupted components, and we generate the resulting network restoration time dependent variable from a network restoration optimization model. We illustrate the results of several machine learning techniques with a system of interdependent water, gas, and power utilities in Shelby County, TN and implement two types of disruption: random and spatial. The different predictive techniques used are a linear model, decision trees, gradient boosting, and random forest, which provided consistent predictions. To portray the consistency of prediction, 30 random samples (a widely accepted sample size) were trained, predicted and the results were compared. Linear model provided the best prediction results for both random and spatial disruptions with a mean RMSE of 3.8, mean correlation of 0.92 and mean bias of 0.012 for the random disruption, and mean RMSE of 1.15, mean correlation of 0.99 and mean bias of − 0.002 for the spatial disruption.
Similar content being viewed by others
References
Almoghathawi Y, Barker K, Albert LA (2019) Resilience-driven restoration model for interdependent infrastructure networks. Reliab Eng Syst Saf 185:12–23. https://doi.org/10.1016/j.ress.2018.12.006
Barabadi A, Ayele YZ (2018) Post-disaster infrastructure recovery: prediction of recovery rate using historical data. Reliab EngSyst Saf 169:209–223. https://doi.org/10.1016/j.ress.2017.08.018
Bell MGH, Kanturska U, Schmöcker JD, Fonzone A (2008) Attacker-defender models and road network vulnerability. Phil Trans R Soc A 366(1872):1893–1906. https://doi.org/10.1098/rsta.2008.0019
Breiman L (2001) Machine learning. Random For. https://doi.org/10.1201/9780429469275-8
Breusch TS, Pagan AR (1979) A simple test for heteroscedasticity and random coefficient variation. Econometrica 47(5):1287–1294
Brown G, Carlyle M, Salmerón J, Wood K (2006) Defending critical infrastructure. Interfaces 36(6):530–544. https://doi.org/10.1287/inte.1060.0252
Church RL, Scaparra MP, Middleton RS (2004) Identifying critical infrastructure: the median and covering facility interdiction problems. Ann Assoc Am Geogr 94(3):491–502. https://doi.org/10.1111/j.1467-8306.2004.00410.x
Ciulla G, D’Amico A (2019) Building energy performance forecasting: a multiple linear regression approach. Appl Energy 253:113500. https://doi.org/10.1016/j.apenergy.2019.113500
Connelly EB, Allen CR, Hatfield K, Palma-Oliveira JM, Woods DD, Linkov I (2017) Features of resilience. Environ Syst Decis 37(1):46–50. https://doi.org/10.1007/s10669-017-9634-9
Friedman J (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232
Ganin AA, Mersky AC, Jin AS, Kitsak M, Keisler JM, Linkov I (2019) Resilience in intelligent transportation systems (ITS). Transp Res Part C 100:318–329
Ghannad P, Asce SM, Lee Y-C, Asce AM, Choi JO (2020) Prioritizing postdisaster recovery of transportation infrastructure systems using multiagent reinforcement learning. J Manag Eng 37(1):04020100. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000868
Ghorbani-Renani N, González AD, Barker K, Morshedlou N (2020) Protection-interdiction-restoration: Tri-level optimization for enhancing interdependent network resilience. Reliab Eng Syst Saf. https://doi.org/10.1016/j.ress.2020.106907
Ghorbani-Renani N, González AD, Barker K (2021) A decomposition approach for solving tri-level defender-attacker-defender problems. Comput Ind Eng. https://doi.org/10.1016/j.cie.2020.107085
González AD, Dueñas-Osorio L, Sánchez-Silva M, Medaglia AL (2016) The interdependent network design problem for optimal infrastructure system restoration. Computer-Aided Civil Infrastruct Eng 31(5):334–350. https://doi.org/10.1111/mice.12171
Gurobi Optimization L.L.C. (2020). Gurobi optimizer reference manual. https://www.gurobi.com/wp-content/plugins/hd_documentations/documentation/8.0/refman.pdf
Heft MW (2015) Interconnected networks. J Dental Res. https://doi.org/10.1177/0022034515584386
Hosseini S, Barker K, Ramirez-Marquez JE (2016) A review of definitions and measures of system resilience. Reliab Eng Syst Saf 145:47–61. https://doi.org/10.1016/j.ress.2015.08.006
Kitsak M, Ganin AA, Eisenberg DA, Krapivsky PL, Krioukov D, Alderson DL, Linkov I (2018) Stability of a giant connected component in a complex network. Phys Rev E 97:012309
Linkov I, Eisenberg DA, Plourde K, Seager TP, Allen J, Kott A (2013) Resilience metrics for cyber systems. Environ Syst Decis 33(4):471–476. https://doi.org/10.1007/s10669-013-9485-y
Matisziw TC, Murray AT, Grubesic TH (2010) Strategic network restoration. Netw Spat Econ 10(3):345–361. https://doi.org/10.1007/s11067-009-9123-x
Morshedlou N, González AD, Barker K (2018) Work crew routing problem for infrastructure network restoration. Transp Res Part B 118:66–89. https://doi.org/10.1016/j.trb.2018.10.001
Morshedlou N, Barker K, Sansavini G (2019) Restorative capacity optimization for complex infrastructure networks. IEEE Syst J 13(3):2559–2569. https://doi.org/10.1109/JSYST.2019.2915930
Nurre SG, Cavdaroglu B, Mitchell JE, Sharkey TC, Wallace WA (2012) Restoring infrastructure systems: an integrated network design and scheduling (INDS) problem. Eur J Oper Res 223(3):794–806. https://doi.org/10.1016/j.ejor.2012.07.010
Ransikarbum K, Mason SJ (2016) Goal programming-based post-disaster decision making for integrated relief distribution and early-stage network restoration. Int J Prod Econ 182:324–341. https://doi.org/10.1016/j.ijpe.2016.08.030
Rinaldi SM, Peerenboom JP, Kelly TK (2001) Identifying, understanding, and analyzing critical infrastructure interdependencies. IEEE Control Syst Mag 21(6):11–25. https://doi.org/10.1109/37.969131
Rocco S, C. M., & Muselli, M. (2004) Empirical models based on machine learning techniques for determining approximate reliability expressions. Reliab Eng Syst Saf 83(3):301–309. https://doi.org/10.1016/j.ress.2003.10.001
Rocco S, C. M., & Muselli, M. (2005) Approximate multi-state reliability expressions using a new machine learning technique. Reliab Eng Syst Saf 89(3):261–270. https://doi.org/10.1016/j.ress.2004.08.023
Rocco CM, Muselli M (2007) Network reliability assessment through empirical models using a machine learning approach. Stud Comput Intell 40:145–174. https://doi.org/10.1007/978-3-540-37372-8_6
Salmeron J, Wood K, Baldick R (2004) Under terrorist threat. IEEE Trans Power Syst 19(2):905–912
Sun J, Zhang Z (2020) A post-disaster resource allocation framework for improving resilience of interdependent infrastructure networks. Transp Res Part D 85:102455. https://doi.org/10.1016/J.TRD.2020.102455
Talebiyan H, Duenas-Osorio L (2020) Decentralized decision making for the restoration of interdependent networks. ASCE-ASME J Risk Uncertain Eng Syst, Part A 6(2):04020012. https://doi.org/10.1061/ajrua6.0001035
Touzani S, Granderson J, Fernandes S (2018) Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy Build 158:1533–1543. https://doi.org/10.1016/j.enbuild.2017.11.039
Turnquist M, Vugrin E (2013) Design for resilience in infrastructure distribution networks. Environmentalist 33(1):104–120. https://doi.org/10.1007/s10669-012-9428-z
Wells EM, Boden M, Tseytlin I, Linkov I (2022) Modeling critical infrastructure resilience under compounding threats: a systematic literature review. Progress Disaster Sci 15:100244
Wu B, Tang A, Wu J (2016) Modeling cascading failures in interdependent infrastructures under terrorist attacks. Reliab Eng Syst Saf 147:1–8. https://doi.org/10.1016/j.ress.2015.10.019
Yuan W, Zhao L, Zeng B (2014) Optimal power grid protection through a defender-attacker-defender model. Reliab Eng Syst Saf 121:83–89. https://doi.org/10.1016/j.ress.2013.08.003
Zhang Y, Yang N, Lall U (2016) Modeling and simulation of the vulnerability of interdependent power-water infrastructure networks to cascading failures. J Syst Sci Syst Eng 25(1):102–118. https://doi.org/10.1007/s11518-016-5295-3
Funding
Funding was provided by National Science Foundation (Grant No. 1635813, 2052930).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Appendix
Appendix
See Tables
6 and
7.
This section includes the modified model focusing on the third level, restoration level, of the existing tri-level formulation proposed by Ghorbani-Renani et al. (2020).
1.1 Model assumptions
The proposed optimization model has the following underlying assumptions associated with the structure and operation of the system of networks and their interdependencies, and recovery, among others.
-
Each infrastructure network consists of a set of nodes (including supply, demand, and transshipment nodes) connected by a set of links, such that each supply node, demand node, and link have known supply capacity, demand, and flow capacity, respectively.
-
There are work crews (work groups) responsible for repairing disrupted components in each infrastructure network, and this number can vary by network.
-
A work crew can only work on a single disrupted component at a time. A disrupted component can be restored by a single work crew (once the disrupted component is assigned to them) until they become operational.
-
There is a known restoration rate for each component, \(\lambda\), representing the proportion of the component restoration per unit time by each work crew.
-
Restoration time for each disrupted component is a function of both its failure and its restoration rate, both of which can vary by component.
-
Infrastructure networks are physically interdependent such that every “parent” node must be operational for the dependent “child” nodes to be operational.
1.2 Notation
An undirected network is denoted by \(G=\left(N,A\right)\), where \(N\) is the set of nodes, and \(A\) is the set of links. Assume a set \(K\) of networks, each with a set of nodes \({N}^{k}\) such that \({\bigcup }_{k\in K}{N}^{k}=N\) and set of links \({A}^{k}\) such that \({\bigcup }_{k\in K}{A}^{k}=A\). Nodes can consist of supply nodes (\({N}_{s}^{k}\subseteq {N}^{k}\)), demand nodes (\({N}_{d}^{k}\subseteq {N}^{k}\)) and transshipment nodes (\({N}^{k}\backslash \left\{{N}_{d}^{k},{N}_{s}^{k}\right\})\) such that \({N}_{s}^{k}\cap {N}_{d}^{k}=\varnothing\). Set \({N{^{\prime}}}^{k}\subseteq {N}^{k}\) is disrupted nodes, in network \(k\in K\).. Note that this model considers a single commodity flowing through each network, but it could be easily extended to a multicommodity model. \(\Psi\) represents interdependency among networks such that \(\left(\left(i,k\right),\left(\overline{i },\overline{k }\right)\right)\in \Psi\) denotes node \(i\in {N}^{k}\) in network \(k\in K\) physically depends on node \(\overline{i}\in {N }^{\overline{k} }\) in network \(\overline{k }\in K\) where \({N}^{k}\cap {N}^{\overline{k} }=\varnothing\), \({A}^{k}\cap {A}^{\overline{k} }=\varnothing\) and \(\forall k,\overline{k }\in K: k\ne \overline{k }\). Set \({R}^{k}\) represents the available work crews in network \(k\in K\). Set \(T\) provides the set of available time periods. Tables 6 and 7 outline the model parameters and decision variables, respectively.
1.3 Objective function
Define \(\zeta (t)\) as the weighted proportion of unmet demand (relative to the met demand before the disruption) at time \(t\), as shown in Eq. (3), where \({\eta }_{it}^{k}\) represents demand being met at node \(i\) in network \(k\) at time \(t\), \({\eta }_{{it}_{e}}^{k}\) represents the amount of demand met prior to the disruption at time \({t}_{e}\) (time at which disruption occurred), and \({w}_{i}^{k}\) is the relative importance of node \(i\) in network \(k\).
Then, the proposed objective function, which seeks to minimize the cumulative weighted fraction of unsupplied demand over the planning horizon for the disrupted scenario, is defined in Eq. (4).
1.4 Restoration scheduling
This model is related to the restoration of disrupted components. In this model, flow balance constraints enable decision variables to connect with the objective function. Therefore, restoration scheduling is automatically set to return the system of networks to a stable operation as rapidly as possible.
The restrictions associated with the restoration scheduling comprise constraints (5)–(24). Constraint (5) states that disrupted nodes cannot be functional at period 1, since they require at least one time unit to be reactivated. Constraints (6)–(9) represent the flow balance constraints at node \(i\in {N}^{k}\) in infrastructure network \(k\in K\) at time \(t\in T\). Constraint (10) represents the capacity restriction for each link \((i,j)\in {A}^{k}\). Constraints (11)–(12) ensure that a positive flow through any given link can be attained at a period \(t\in T\) only if starting and ending nodes of such a link were already recovered. Constraint (13) ensures that the restoration task of a disrupted node is continued without interruption once it has commenced. Constraints (14) and (15) calculate the total time that a specific work crew should be assigned to restore a disrupted node. Note that constraints (14) and (15) together help to deliver integer value for the total required recovery time of an element. Constraint (16) ensures that once the disrupted node, is fully restored at time \(t\in T\), they are labeled reactivated from the next period (\(t+1\in T\)) to the end of the time horizon of the model. Constraint (17) ensures that once the restoration of a disrupted node commences by a work crew at time \(t\in T\), that specific work crew completes restoration of that node. Constraint (18) states that, at the given time \(t\in T\), only one work crew can work on the restoration task of a specific disrupted node. Constraint (19) ensures that, at given time \(t\in T\), only one disrupted node can be restored by a given work crew. Constraint (20) establishes the interdependency among networks, ensuring that the positive flow through a link can be only available if their corresponding related parent nodes (in other networks) are operational. Finally, constraints (21)–(24) represent the nature of the decision variables for the restoration model
Parameter \(M\) in constraints (13)–(15) only needs to be greater than the maximum required time for restoring the disrupted components.
Note that demand nodes can be prioritized with the aim of emphasizing on their importance in a network. Therefore, parameters \({w}_{it}^{k}\) show the relative importance of node \(i\) in network \(k\) at time \(t\), which can be adjusted based on different aspects including locations of the demand nodes (e.g., near hospitals, shelters, and populated or more vulnerable areas). This prioritization affects the restoration process of the disrupted network by forcing the model to satisfy the demand in high-ranked nodes prior to others.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ramineni, G., Ghorbani-Renani, N., Barker, K. et al. Machine learning approaches to modeling interdependent network restoration time. Environ Syst Decis 43, 22–35 (2023). https://doi.org/10.1007/s10669-022-09882-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10669-022-09882-y