Progressive Recovery from Failure in Multi-layered Interdependent Network Using a New Model of Interdependency

Mazumder, Anisha; Zhou, Chenyang; Das, Arun; Sen, Arunabha

doi:10.1007/978-3-319-31664-2_38

Cited by 9 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Progressive recovery problems in interdependent networks have been discussed in [15], [9], [10], [16]. Classifying the progressive recovery problems by the types of interdependency, the work [15] proposes the optimum algorithm for a special case and heuristic algorithms for other cases. ILP and Dynamic Programming-based algorithms are employed to solve a variant of the progressive recovery problem in [9].…”

Section: Related Workmentioning

confidence: 99%

DeepPR: Incremental Recovery for Interdependent VNFs with Deep Reinforcement Learning

Ishigaki

Devic

Gour

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

The increasing reliance upon cloud services entails more flexible networks that are realized by virtualized network equipment and functions. When such advanced network systems face a massive failure by natural disasters or attacks, the recovery of the entire system may be conducted in a progressive way due to limited repair resources. The prioritization of network equipment in the recovery phase influences the interim computation and communication capability of systems, since the systems are operated under partial functionality. Hence, finding the best recovery order is a critical problem, which is further complicated by virtualization due to dependency among network nodes and layers. This paper deals with a progressive recovery problem under limited resources in networks with VNFs, where some dependent network layers exist. We prove the NP-hardness of the progressive recovery problem and approach the optimum solution by introducing DeepPR, a progressive recovery technique based on Deep Reinforcement Learning (Deep RL). Our simulation results indicate that DeepPR can achieve the near-optimal solutions in certain networks and is more robust to adversarial failures, compared to a baseline heuristic algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%

DeepPR: Incremental Recovery for Interdependent VNFs with Deep Reinforcement Learning

Ishigaki

Devic

Gour

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

show abstract

“…This module will support multi-layer interdependent network modeling utilizing IIM, and implement the techniques proposed for problems studied under the IIM setting, such as (i) identification of the K most vulnerable nodes [23], (ii) root cause analysis of failures [11], (iii) the entity hardening problem [2], (iv) the smallest pseudotarget set identification problem [13], (v) the robustness analysis problem [3], and (vi) progressive recovery from failure in multi-layer interdependent networks [18]. It may be noted that, as of writing this paper this module is currently under development and will be part of the tool upon its completion.…”

Section: Robust Multi-layer Interdependent Network Design Modulementioning

confidence: 99%

Raptor: a network tool for mitigating the impact of spatially correlated failures in infrastructure networks

et al. 2017

Self Cite

View full text Add to dashboard Cite

Current practices of fault-tolerant network design ignore the fact that most network infrastructure faults are localized or spatially correlated (i.e., confined to geographic regions). Network operators require new tools to mitigate the impact of such region based faults on their infrastructures. Utilizing the support from the U.S. Department of Defense, and by consolidating a wide range of theories and solutions developed in the last few years, the authors of this paper have developed RAPTOR, an advanced Network Planning and Management Tool that facilitates the design and provisioning of robust and resilient networks. The tool provides multi-faceted network design, evaluation and simulation capabilities for network planners. Future extensions of the tool currently being worked upon not only expand the tool's capabilities, but also extend these capabilities to heterogeneous interdependent networks such as communication, power, water and satellite networks.

show abstract

“…As discussed in Section II-E, the Implicative Interdependency Model provides a powerful technique for modeling dependencies in multi-layer interdependent networks. Using this model the authors of [23] studied the progressive recovery problem in interdependent networks with the objective of maximizing system utility during the system recovery process. This module implements the progressive recovery algorithm of [23], and can be used to sequence recovery of network entities from a post-fault to a pre-fault network state that maximizes system utility during the recovery process.…”

Section: F Module For Progressive Recovery From Region-based Failuresmentioning

confidence: 99%

“…Using this model the authors of [23] studied the progressive recovery problem in interdependent networks with the objective of maximizing system utility during the system recovery process. This module implements the progressive recovery algorithm of [23], and can be used to sequence recovery of network entities from a post-fault to a pre-fault network state that maximizes system utility during the recovery process. The module is currently under development and will be part of the NPMT upon its completion.…”

Section: F Module For Progressive Recovery From Region-based Failuresmentioning

confidence: 99%

A Network Planning and Management Tool for mitigating the impact of spatially correlated failures in infrastructure networks

Das

Sen

Qiao

et al. 2016

2016 12th International Conference on the Design of Reliable Communication Networks (DRCN)

Self Cite

View full text Add to dashboard Cite

Current practices of fault-tolerant network design ignore the fact that most network infrastructure faults are localized or spatially correlated (i.e., confined to regions). Network operators require new tools to mitigate the impact of such region based faults on their infrastructures. Utilizing the support from the U.S. Department of Defense, and by consolidating a wide range of theories and solutions developed in the last few years, the authors of this paper have developed an advanced Network Planning and Management Tool (NPMT) that facilitates the design and provisioning of robust and resilient networks. The tool provides multi-faceted network design, evaluation and simulation capabilities for network planners. Future extensions of the tool currently being worked upon not only expand the tools capabilities, but also extend these capabilities to heterogeneous interdependent networks such as communication, power, water and satellite networks.

show abstract

Progressive Recovery from Failure in Multi-layered Interdependent Network Using a New Model of Interdependency

Cited by 9 publications

References 8 publications

DeepPR: Incremental Recovery for Interdependent VNFs with Deep Reinforcement Learning

DeepPR: Incremental Recovery for Interdependent VNFs with Deep Reinforcement Learning

Raptor: a network tool for mitigating the impact of spatially correlated failures in infrastructure networks

A Network Planning and Management Tool for mitigating the impact of spatially correlated failures in infrastructure networks

Contact Info

Product

Resources

About