A Bayesian Network approach for risk assessment to a spatially distributed power infrastructure in a GIS environment

• Autorzy: Quan L. B. , Garrè L. , Yang Y.
• Języki publikacji: EN

Abstrakty

EN

One of the most important applications of spatial data regards the ability to inform decision makers on spatially distributed and disaggregated hazards and risks, thus enhancing strategic decision making on how to manage and limit risks for a given area or region and prioritize investments. However, a full risk based adaptation assessment inside a Geographical Information System (GIS) can be cumbersome, since some complex tasks cannot be carried out directly. One example of these tasks involves Bayesian probabilistic analysis and decision making, which is a fundamental component of risk analysis, yet requires dedicated tools/software which usually do not belong to a standard GIS portfolio. For this reason, exploring the various capabilities of a GIS platform in connection with a Bayesian Network (BN) software is essential. The objective is to have an effective tool for knowledge representation and reasoning under the influence of uncertainty that can be displayed in a spatial manner. A case study using this tool was performed to assess the risk levels faced by the electrical distribution system of Long Island because of storm events as the Sandy Storm.

Słowa kluczowe

EN

risk assessment; geographical information system; GIS; Bayesian networks; Power Grids

• Wydawca: Polskie Towarzystwo Bezpieczeństwa i Niezawodności
• Czasopismo: Journal of Polish Safety and Reliability Association
• Rocznik: 2015
• Tom: Vol. 6, No. 3
• Strony: 127--132
• Opis fizyczny: Bibliogr. 13 poz., rys.

Twórcy

autor

Quan L. B.

• DNV GL Strategic Research and Innovation, Veritasveien 1, Høvik, Norway

autor

Garrè L.

• DNV GL Strategic Research and Innovation, Veritasveien 1, Høvik, Norway

autor

Yang Y.

• DNV GL Strategic Research and Innovation, Veritasveien 1, Høvik, Norway

Bibliografia

• [1] Charniak, E. (1991). Bayesian Network without tears. Artificial Intelligence magazine, vol. 12, no. 4, pp. 50-63.
• [2] Druzdzel, M.J. (1999). SMILE: Structural Modeling, Inference, and Learning Engine and GeNIe: A development environment for graphical decision-theoretic models (Intelligent Systems Demonstration). Proc. of the 16th National Conference on Artificial Intelligence, pp. 902903, AAAI Press/The MIT Press, Merlo Park, CA.
• [3] Greiner C. J., Solvik J., Yang Y., & Langel T. (2012). Risk related to large scale implementation of wind power into a regional power transmission system, in ESReDA Conference 2012, Risk and Reliability for Wind Energy and other Renewable Sources, Glasgow, UK.
• [4] Hengl T. (2009). A practical guide to geostatistical mapping. University of Amsterdam, Amsterdam.
• [5] Jensen, F.V. & Nielsen, T.D. (2007). Bayesian Networks and Decision Graphs. Springer Verlag, New York, NY.
• [6] Li, L., Wang, J., Leung, H. & Jiang, C. (2010). Assessment of catastrophic risk using Bayesian Network constructed from domain knowledge and spatial data. Risk Analysis.
• [7] Mensah, A. F. & Duenas-Osorio, L., (2013). Probabilistic outage prediction model with Bayesian networks for electric power systems subjected to hurricane events, in ICOSSAY 2013, New York, NY.
• [8] O’Brien, J.S., Julien, P.Y., & Fullerton, W.T. (1993). Two-dimensional water flood and mudflow simulation. J. Hydraul. Eng., 119(2), pp. 244-261.
• [9] Office of Electricity Delivery and Energy Reliability, U.S. Department of Energy, (2013). Comparing the Impacts of Northeast Hurricanes on Energy Infrastructure.
• [10] QGIS Development Team. (2015). QGIS Geographic Information System. Open Source Geospatial Foundation Project. http://qgis.osgeo.org. 2015.
• [11] Rengers, N., Soeters, R. & van Westen, C.J. (1992). Remote sensing and GIS applied to mountain hazard mapping. In: Episodes, 15(1992)1, pp. 36-46.
• [12] Weber, P., Medina-Oliva, G., Simon, C. & Iung, B. (2009). Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas. Engineering applications of Artificial Intelligence, vol. 25(4), pp. 671-682.\
• [13] Yates, D., Quan Luna, B., Rasmussen, R., Bratcher, D., Garre, L., Chen, F., Tewari, M. & Friis-Hansen, P. (2014). Stormy Weather: Assessing Climate Change Hazards to Electric Power Infrastructure: A Sandy Case Study. Power and Energy Magazine, IEEE, vol.12, no.5, pp. 6675. doi: 10.1109/MPE.2014.2331901.