The Effect of Lead-Time Weather Forecast Uncertainty on Outage Prediction Modeling
Abstract
:1. Introduction
2. Study Area and Data
3. Methods
3.1. Numerical Experiment
3.2. Outage Prediction Model
3.3. Performance Evaluation Error Metrics
4. Results
4.1. OPM Model Evaluation
4.2. Weather and Outage Forecast Uncertainties
5. Discussion
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Appendix A. Explanatory Variables
Variables | Abbreviation | Description | Units |
---|---|---|---|
Duration of wind at 10 m above 5 m/s | wgt5 | Weather | h |
Duration of wind at 10 m above 9 m/s | wgt9 | Weather | h |
Duration of wind at 10 m above 13 m/s | wgt13 | Weather | h |
Duration of wind at 10 m above 18 m/s | wgt18 | Weather | h |
Continuous hours of wind above 5 m/s | Cowgt5 | Weather | h |
Continuous hours of wind above 9 m/s | Cowgt9 | Weather | h |
Continuous hours of wind above 13 m/s | Cowgt13 | Weather | h |
Continuous hours of wind above 18 m/s | Cowgt18 | Weather | h |
Maximum wind speed at 10 m height | Max Wind Speed | Weather | m/s |
Maximum wind gust | Max Gust | Weather | m/s |
Maximum precipitation rate | Max Precipitation Rate | Weather | mm/h |
Maximum temperature | Max Temperature | Weather | K |
Mean wind at 10 m height | Mean Wind Speed | Weather | m/s |
Mean wind gust | Mean Gust | Weather | m/s |
Mean precipitation rate | Mean Precipitation Rate | Weather | mm/h |
Mean temperature | Mean Temperature | Weather | K |
Total accumulated precipitation | Tot Precipitation | Weather | mm |
Percentage of miscellaneous forest | percXFrst | Land cover | % |
Percentage of deciduous forest | percDecid | Land cover | % |
Percentage of developed area | percDevel | Land cover | % |
Count of electric poles | ploes | Infrastructure | count |
Count of reclosers | reclosers | Infrastructure | count |
Count of total assets including poles, reclosers, and others | totAssets | Infrastructure | count |
Average tree canopy percentage around overhead power lines | Avg_treeCanopy | Tree Canopy | % |
Leaf area index (leaf area/ground area) | LAI | Vegetation | m2/m2 |
Appendix B. Performance Evaluation Error Metrics
References
- Berg, R. Tropical Cyclone Report: Hurricane Ike (al092008), 1–14 September 2008; National Hurricane Center: Miami, FL, USA, 2009.
- Smith, A.; Lott, N.; Houston, T.; Shein, K.; Crouch, J.; Enloe, J. US Billion-Dollar Weather & Climate Disasters: 1980–2017; NOAA National Centers for Environmental Information: Asheville, NC, USA, 2016.
- Duffey, R.B.; Ha, T. Predicting electric power system restoration. In Proceedings of the 2009 IEEE Toronto International Conference Science and Technology for Humanity (TIC-STH), Toronto, ON, Canada, 26–27 September 2009; pp. 666–668. [Google Scholar]
- Duffey, R. Power restoration following major events and disasters. Int. J. Disaster Risk Sci. 2019, 10, 134–148. [Google Scholar] [CrossRef] [Green Version]
- Liu, H.; Davidson, R.A.; Apanasovich, T.V. Statistical Forecasting of electric power restoration times in hurricanes and ice storms. IEEE Trans. Power Syst. 2007, 22, 2270–2279. [Google Scholar] [CrossRef]
- Lubkeman, D.; Julian, D.E. Large scale storm outage management. In Proceedings of the Eighth IEEE International Symposium on Spread Spectrum Techniques and Applications-Programme and Book of Abstracts (IEEE Cat. No.04TH8738), Sydney, NSW, Australia, 30 August–2 September 2004; Institute of Electrical and Electronics Engineers (IEEE): Piscataway, NJ, USA; pp. 16–22. [Google Scholar]
- Arif, A.; Wang, Z. Distribution Network Outage Data Analysis and Repair Time Prediction Using Deep Learning. In Proceedings of the 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), Boise, ID, USA, 23–28 June 2018; Institute of Electrical and Electronics Engineers (IEEE): Piscataway, NJ, USA; pp. 1–6. [Google Scholar]
- Eskandarpour, R.; Khodaei, A. Machine learning based power grid outage prediction in response to extreme events. IEEE Trans. Power Syst. 2016, 32, 3315–3316. [Google Scholar] [CrossRef]
- Eskandarpour, R.; Khodaei, A. Leveraging accuracy-uncertainty tradeoff in SVM to achieve highly accurate outage pre-dictions. IEEE Trans. Power Syst. 2017, 33, 1139–1141. [Google Scholar] [CrossRef]
- He, J.; Cheng, M.X. Machine learning methods for power line outage identification. Electr. J. 2021, 34, 106885. [Google Scholar]
- He, J.; Cheng, M.X.; Fang, Y.; Crow, M.L. A machine learning approach for line outage identification in power systems. In Proceedings of the 4th International Conference on Machine Learning, Optimization, and Data Science, LOD 2018, Volterra, Italy, 13–16 September 2018; Springer Science and Business Media LLC: Berlin, Germany, 2019; pp. 482–493. [Google Scholar]
- Reilly, A.C.; Tonn, G.L.; Zhai, C.; Guikema, S.D. Hurricanes and Power System Reliability-The Effects of Individual Decisions and System-Level Hardening. Proc. IEEE 2017, 105, 1429–1442. [Google Scholar] [CrossRef]
- Owerko, D.; Gama, F.; Ribeiro, A. Predicting Power Outages Using Graph Neural Networks. In Proceedings of the 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Anaheim, CA, USA, 26–29 November 2018; pp. 743–747. [Google Scholar]
- Nateghi, R.; Guikema, S.D.; Quiring, S. Comparison and validation of statistical methods for predicting power outage durations in the event of hurricanes. Risk Anal. 2011, 31, 1897–1906. [Google Scholar] [CrossRef]
- Nateghi, R.; Guikema, S.; Quiring, S. Power outage estimation for tropical cyclones: Improved accuracy with simpler models. Risk Anal. 2014, 34, 1069–1078. [Google Scholar] [CrossRef] [PubMed]
- Liu, H.; Davidson, R.A.; Apanasovich, T.V. Spatial generalized linear mixed models of electric power outages due to hurricanes and ice storms. Reliab. Eng. Syst. Saf. 2008, 93, 897–912. [Google Scholar] [CrossRef]
- Kabir, E.; Guikema, S.D.; Quiring, S.M. Predicting thunderstorm-induced power outages to support utility restoration. IEEE Trans. Power Syst. 2019, 34, 4370–4381. [Google Scholar] [CrossRef]
- Wanik, D.; Anagnostou, E.; Hartman, B.; Frediani, M.; Astitha, M. Storm outage modeling for an electric distribution net-work in northeastern USA. Nat. Hazards 2015, 79, 1359–1384. [Google Scholar] [CrossRef]
- Cerrai, D.; Wanik, D.W.; Bhuiyan, A.E.; Zhang, X.; Yang, J.; Frediani, M.E.B.; Anagnostou, E.N.; Bhuiyan, M.E. Predicting storm outages through new representations of weather and vegetation. IEEE Access 2019, 7, 29639–29654. [Google Scholar] [CrossRef]
- Davidson, R.A.; Liu, H.; Sarpong, I.K.; Sparks, P.; Rosowsky, D.V. Electric power distribution system performance in Carolina Hurricanes. Nat. Hazards Rev. 2003, 4, 36–45. [Google Scholar] [CrossRef]
- Dehghanian, P.; Zhang, B.; Dokic, T.; Kezunovic, M. Predictive risk analytics for weather-resilient operation of electric power systems. IEEE Trans. Sustain. Energy 2019, 10, 3–15. [Google Scholar] [CrossRef]
- Mason, B.J. Numerical weather prediction. Contemp. Phys. 1986, 27, 463–472. [Google Scholar] [CrossRef]
- Anthes, R.A. The general question of predictability. In Mesoscale Meteorology and Forecasting; Springer Science and Business Media LLC: Berlin, Germany, 1986; pp. 636–656. [Google Scholar]
- Ying, Y.; Zhang, F. Practical and intrinsic predictability of multiscale weather and convectively coupled equatorial waves during the active phase of an MJO. J. Atmos. Sci. 2017, 74, 3771–3785. [Google Scholar] [CrossRef]
- Grell, G.A.; Kuo, Y.-H.; Pasch, R.J. Semiprognostic Tests of Cumulus Parameterization Schemes in the Middle Latitudes. Mon. Weather Rev. 1991, 119, 5–31. [Google Scholar] [CrossRef] [Green Version]
- Lorenz, E.N. Predictability: A problem partly solved. In Proceedings of the Seminar on Predictability, Reading, UK, 4–8 September 1996. [Google Scholar]
- Kalnay, E. Atmospheric Modeling, Data Assimilation and Predictability; Cambridge University Press (CUP): Cambridge, UK, 2002. [Google Scholar]
- Klasa, C.; Arpagaus, M.; Walser, A.; Wernli, H. An evaluation of the convection-permitting ensemble COSMO-E for three contrasting precipitation events in Switzerland. Q. J. R. Meteorol. Soc. 2018, 144, 744–764. [Google Scholar] [CrossRef]
- Schwartz, C.S. Medium-range convection-allowing ensemble forecasts with a variable-resolution global model. Mon. Weather Rev. 2019, 147, 2997–3023. [Google Scholar] [CrossRef]
- Slingo, J.; Palmer, T. Uncertainty in weather and climate prediction. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2011, 369, 4751–4767. [Google Scholar] [CrossRef]
- Yang, J.; Astitha, M.; Monache, L.D.; Alessandrini, S. An analog technique to improve storm wind speed prediction using a dual NWP model approach. Mon. Weather Rev. 2018, 146, 4057–4077. [Google Scholar] [CrossRef]
- Yang, J.; Astitha, M.; Schwartz, C.S. Assessment of storm wind speed prediction using gridded Bayesian regression applied to historical events with NCAR’s real-time ensemble forecast system. J. Geophys. Res. Atmos. 2019, 124, 9241–9261. [Google Scholar] [CrossRef]
- Global Weather Corporation. Delivering Globally-Available, High-Quality Road-Weather Information. Available online: https://globalweathercorp.com/images/pdf/new-pdf-march-2020/GWC_White_Paper_RoadWX_Quality_May2018.pdf (accessed on 21 March 2021).
- GWC PointWX. Available online: https://globalweathercorp.com/pointwx.html (accessed on 21 March 2021).
- Homer, C.; Dewitz, J.; Jin, S.; Xian, G.; Costello, C.; Danielson, P.; Gass, L.; Funk, M.; Wickham, M.; Stehman, S.; et al. Conterminous United States land cover change patterns 2001–2016 from the 2016 national land cover database. ISPRS J. Photogramm. Remote Sens. 2020, 162, 184–199. [Google Scholar] [CrossRef]
- Myneni, R.B.; Hoffman, S.; Knyazikhin, Y.; Privette, J.L.; Glassy, J.; Tian, Y.; Wang, Y.; Song, X.; Zhang, Y.; Smith, G.R.; et al. Global products of vegetation leaf area and fraction absorbed PAR from year one of MODIS data. Remote Sens. Environ. 2002, 83, 214–231. [Google Scholar] [CrossRef] [Green Version]
- Coulston, J.W.; Jacobs, D.M.; King, C.R.; Elmore, I.C. The Influence of Multi-season Imagery on Models of Canopy Cover. Photogramm. Eng. Remote Sens. 2013, 79, 469–477. [Google Scholar] [CrossRef] [Green Version]
- USGS. NLCD Tree Canopy. 2019. Available online: https://www.usgs.gov/center-news/nlcd-readies-improvements-upcoming-release-2019-product-suite?qt-news_science_products=1#qt-news_science_products (accessed on 21 March 2021).
- Watson, P.L.; Cerrai, D.; Koukoula, M.; Wanik, D.W.; Anagnostou, E. Weather-related power outage model with a growing domain: Structure, performance, and generalisability. J. Eng. 2020, 2020, 817–826. [Google Scholar] [CrossRef]
- Yang, F.; Wanik, D.W.; Cerrai, D.; Bhuiyan, A.E.; Anagnostou, E.N. Quantifying Uncertainty in Machine Learning-Based Power Outage Prediction Model Training: A Tool for Sustainable Storm Restoration. Sustainability 2020, 12, 1525. [Google Scholar] [CrossRef] [Green Version]
- Yang, F.; Watson, P.; Koukoula, M.; Anagnostou, E.N. Enhancing weather-related power outage prediction by event severity classification. IEEE Access 2020, 8, 60029–60042. [Google Scholar] [CrossRef]
- Touzani, S.; Granderson, J.; Fernandes, S. Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy Build. 2018, 158, 1533–1543. [Google Scholar] [CrossRef] [Green Version]
- Natekin, A.; Knoll, A. Gradient boosting machines, a tutorial. Front. Neurorobot. 2013, 7, 21. [Google Scholar] [CrossRef] [Green Version]
- Jin, S.; Homer, C.; Yang, L.; Danielson, P.; Dewitz, J.; Li, C.; Zhu, Z.; Xian, G.; Howard, D. Overall methodology design for the United States national land cover database 2016 products. Remote Sens. 2019, 11, 2971. [Google Scholar] [CrossRef] [Green Version]
- Yang, W.; Tan, B.; Huang, D.; Rautiainen, M.; Shabanov, N.; Wang, Y.; Privette, J.; Huemmrich, K.; Fensholt, R.; Sandholt, I.; et al. MODIS leaf area index products: From validation to algorithm improvement. IEEE Trans. Geosci. Remote Sens. 2006, 44, 1885–1898. [Google Scholar] [CrossRef]
- Gao, F.; Morisette, J.T.; Wolfe, R.E.; Ederer, G.; Pedelty, J.; Masuoka, E.; Myneni, R.; Tan, B.; Nightingale, J. An Algorithm to Produce Temporally and Spatially Continuous MODIS-LAI Time Series. IEEE Geosci. Remote Sens. Lett. 2008, 5, 60–64. [Google Scholar] [CrossRef]
Variables | Importance |
---|---|
Max Gust | 17.68 |
Max Temperature | 11.72 |
poles | 10.24 |
totAssets | 8.69 |
Mean Gust | 6.53 |
Total Precipitation | 6.32 |
reclosers | 5.81 |
percDevel | 3.59 |
Mean Temperature | 3.54 |
Max Wind Speed | 3.30 |
LAI | 2.71 |
Max Precipitation Rate | 2.64 |
percDecid | 2.43 |
wgt9 | 2.33 |
Mean Wind Speed | 2.19 |
Mean Precipitation Rate | 2.12 |
Avg_treeCanopy | 2.11 |
percXFrst | 1.73 |
wgt5 | 1.20 |
Cowgt5 | 1.15 |
Cowgt9 | 0.77 |
wgt13 | 0.75 |
Cowgt13 | 0.25 |
wgt18 | 0.16 |
Cowgt18 | 0.04 |
Model | AEQ25 | AEQ50 | AEQ75 | APEQ25 | APEQ50 | APEQ75 | MAPE | NCRMSE | NSE |
---|---|---|---|---|---|---|---|---|---|
OPM | 7 | 15 | 33 | 12% | 28% | 46% | 38% | 68% | 0.54 |
Model | AE Q50 | MAPE | NCRMSE | NSE |
---|---|---|---|---|
0H-ahead | 18 | 49% | 72% | 0.48 |
1D-ahead | 18 | 50% | 84% | 0.29 |
2D-ahead | 22 | 51% | 86% | 0.24 |
3D-ahead | 18 | 48% | 87% | 0.22 |
4D-ahead | 21 | 54% | 86% | 0.22 |
5D-ahead | 24 | 60% | 87% | 0.21 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yang, F.; Cerrai, D.; Anagnostou, E.N. The Effect of Lead-Time Weather Forecast Uncertainty on Outage Prediction Modeling. Forecasting 2021, 3, 501-516. https://doi.org/10.3390/forecast3030031
Yang F, Cerrai D, Anagnostou EN. The Effect of Lead-Time Weather Forecast Uncertainty on Outage Prediction Modeling. Forecasting. 2021; 3(3):501-516. https://doi.org/10.3390/forecast3030031
Chicago/Turabian StyleYang, Feifei, Diego Cerrai, and Emmanouil N. Anagnostou. 2021. "The Effect of Lead-Time Weather Forecast Uncertainty on Outage Prediction Modeling" Forecasting 3, no. 3: 501-516. https://doi.org/10.3390/forecast3030031