MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS

Balaji V. Venkatasubramanian; Mohamed Lotfi; Pierluigi Mancarella; André Águas; Mohammad Javadi; Leonel Carvalho; Clara Gouveia; Mathaios Panteli

doi:10.1049/icp.2023.0985

MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS

Balaji V. Venkatasubramanian, Mohamed Lotfi, Pierluigi Mancarella, André Águas, Mohammad Javadi, Leonel Carvalho, Clara Gouveia, Mathaios Panteli

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Distribution networks are vulnerable to natural hazards which can cause major social and economic consequences. Identifying vulnerable areas and developing operational strategies, such as dispatching mobile energy systems, can help mitigate the effects of extreme events. Conventional approaches, mainly N-1/N-2 contingency security analysis, are efficient but they do not fully provide a comprehensive picture of the stochastic nature of the hazard impact. Stochastic approaches are more accurate but in general they are computationally expensive and hence not practical for the resilient operational decision-making of distribution system operators. Therefore, this paper develops a novel framework based on an adjacency-resource matrix (ARM) and an unsupervised machine learning algorithm to first identify vulnerable nodes. Next, these vulnerable nodes are utilized in the mitigation stage in order to minimize the expected energy not served (EENS) against a natural hazard. The efficiency of the proposed framework is tested on a 125-node Portuguese distribution system.

Original language	English
Title of host publication	27th International Conference on Electricity Distribution, CIRED 2023
Publisher	Institution of Engineering and Technology
Pages	2908-2912
Number of pages	5
ISBN (Electronic)	9781839538551, 9781839538650, 9781839539022, 9781839539091, 9781839539107, 9781839539176, 9781839539220, 9781839539237, 9781839539305, 9781839539312, 9781839539329, 9781839539350, 9781839539367, 9781839539497, 9781839539503, 9781839539572, 9781839539596
DOIs	https://doi.org/10.1049/icp.2023.0985
Publication status	Published - 2023
Externally published	Yes
Event	27th International Conference on Electricity Distribution, CIRED 2023 - Rome, Italy Duration: 12 Jun 2023 → 15 Jun 2023

Conference

Conference	27th International Conference on Electricity Distribution, CIRED 2023
Country/Territory	Italy
City	Rome
Period	12/06/23 → 15/06/23

Bibliographical note

Publisher Copyright:
© The Institution of Engineering and Technology 2023.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1049/icp.2023.0985

Cite this

Venkatasubramanian, B. V., Lotfi, M., Mancarella, P., Águas, A., Javadi, M., Carvalho, L., Gouveia, C., & Panteli, M. (2023). MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS. In 27th International Conference on Electricity Distribution, CIRED 2023 (pp. 2908-2912). Institution of Engineering and Technology. https://doi.org/10.1049/icp.2023.0985

@inproceedings{8edbc3192898496189fbc20168a25d49,

title = "MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS",

abstract = "Distribution networks are vulnerable to natural hazards which can cause major social and economic consequences. Identifying vulnerable areas and developing operational strategies, such as dispatching mobile energy systems, can help mitigate the effects of extreme events. Conventional approaches, mainly N-1/N-2 contingency security analysis, are efficient but they do not fully provide a comprehensive picture of the stochastic nature of the hazard impact. Stochastic approaches are more accurate but in general they are computationally expensive and hence not practical for the resilient operational decision-making of distribution system operators. Therefore, this paper develops a novel framework based on an adjacency-resource matrix (ARM) and an unsupervised machine learning algorithm to first identify vulnerable nodes. Next, these vulnerable nodes are utilized in the mitigation stage in order to minimize the expected energy not served (EENS) against a natural hazard. The efficiency of the proposed framework is tested on a 125-node Portuguese distribution system.",

author = "Venkatasubramanian, {Balaji V.} and Mohamed Lotfi and Pierluigi Mancarella and Andr{\'e} {\'A}guas and Mohammad Javadi and Leonel Carvalho and Clara Gouveia and Mathaios Panteli",

note = "Publisher Copyright: {\textcopyright} The Institution of Engineering and Technology 2023.; 27th International Conference on Electricity Distribution, CIRED 2023 ; Conference date: 12-06-2023 Through 15-06-2023",

year = "2023",

doi = "10.1049/icp.2023.0985",

language = "English",

pages = "2908--2912",

booktitle = "27th International Conference on Electricity Distribution, CIRED 2023",

publisher = "Institution of Engineering and Technology",

address = "United Kingdom",

}

Venkatasubramanian, BV, Lotfi, M, Mancarella, P, Águas, A, Javadi, M, Carvalho, L, Gouveia, C & Panteli, M 2023, MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS. in 27th International Conference on Electricity Distribution, CIRED 2023. Institution of Engineering and Technology, pp. 2908-2912, 27th International Conference on Electricity Distribution, CIRED 2023, Rome, Italy, 12/06/23. https://doi.org/10.1049/icp.2023.0985

MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS. / Venkatasubramanian, Balaji V.; Lotfi, Mohamed; Mancarella, Pierluigi et al.
27th International Conference on Electricity Distribution, CIRED 2023. Institution of Engineering and Technology, 2023. p. 2908-2912.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS

AU - Venkatasubramanian, Balaji V.

AU - Lotfi, Mohamed

AU - Mancarella, Pierluigi

AU - Águas, André

AU - Javadi, Mohammad

AU - Carvalho, Leonel

AU - Gouveia, Clara

AU - Panteli, Mathaios

PY - 2023

Y1 - 2023

N2 - Distribution networks are vulnerable to natural hazards which can cause major social and economic consequences. Identifying vulnerable areas and developing operational strategies, such as dispatching mobile energy systems, can help mitigate the effects of extreme events. Conventional approaches, mainly N-1/N-2 contingency security analysis, are efficient but they do not fully provide a comprehensive picture of the stochastic nature of the hazard impact. Stochastic approaches are more accurate but in general they are computationally expensive and hence not practical for the resilient operational decision-making of distribution system operators. Therefore, this paper develops a novel framework based on an adjacency-resource matrix (ARM) and an unsupervised machine learning algorithm to first identify vulnerable nodes. Next, these vulnerable nodes are utilized in the mitigation stage in order to minimize the expected energy not served (EENS) against a natural hazard. The efficiency of the proposed framework is tested on a 125-node Portuguese distribution system.

AB - Distribution networks are vulnerable to natural hazards which can cause major social and economic consequences. Identifying vulnerable areas and developing operational strategies, such as dispatching mobile energy systems, can help mitigate the effects of extreme events. Conventional approaches, mainly N-1/N-2 contingency security analysis, are efficient but they do not fully provide a comprehensive picture of the stochastic nature of the hazard impact. Stochastic approaches are more accurate but in general they are computationally expensive and hence not practical for the resilient operational decision-making of distribution system operators. Therefore, this paper develops a novel framework based on an adjacency-resource matrix (ARM) and an unsupervised machine learning algorithm to first identify vulnerable nodes. Next, these vulnerable nodes are utilized in the mitigation stage in order to minimize the expected energy not served (EENS) against a natural hazard. The efficiency of the proposed framework is tested on a 125-node Portuguese distribution system.

UR - http://www.scopus.com/inward/record.url?scp=85173664419&partnerID=8YFLogxK

U2 - 10.1049/icp.2023.0985

DO - 10.1049/icp.2023.0985

M3 - Conference contribution

AN - SCOPUS:85173664419

SP - 2908

EP - 2912

BT - 27th International Conference on Electricity Distribution, CIRED 2023

PB - Institution of Engineering and Technology

T2 - 27th International Conference on Electricity Distribution, CIRED 2023

Y2 - 12 June 2023 through 15 June 2023

ER -

MACHINE LEARNING-BASED IDENTIFICATION AND MITIGATION OF VULNERABILITIES IN DISTRIBUTION SYSTEMS AGAINST NATURAL HAZARDS

Abstract

Conference

Bibliographical note

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this