Prioritizing Power Outages Causes in Different Scenarios of the Global Business Network Matrix by Using BWM andTOPSIS
Preprints and early-stage research may not have been peer reviewed yet.
Abstract and Figures
Power outage is one of the significant problems for electricity distribution companies. Power outages cause customer dissatisfaction and reduce distribution companies' profits and revenues. Therefore, the electricity distribution companies are trying to moderate the leading causes of the outage. However, the dynamics of environmental conditions create uncertainties that require prioritizing the solutions to outages causes in different situations. Therefore, this study presents a scenario-based approach to prioritizing power outage causes. Four case studies have been conducted in four cities of Kerman province in Iran. First, the prioritization criteria and causes of the outage were identified using literature and interviews with experts in this field. Then, the Global Business Network matrix was used to create four possible scenarios. Then, the Best-Worst method and TOPSIS method were applied to weight the prioritizing criteria and prioritize the causes of the outages in different scenarios. The results showed that working in the power network limit zone, as one of the causes of outage in Sirjan and Jiroft cities, has the most priority. Also, the collision of external objects, birds, and annoying trees should be considered by managers as the leading causes of outages in Bam and Kahnuj cities.
Figures - uploaded by Armin Mokhtari
Author content
All figure content in this area was uploaded by Armin Mokhtari
Content may be subject to copyright.
... In addition to this, this paper uses the entropy-based TOPSIS method when making multi-objective decisions on multiple scenarios [38][39][40][41][42][43][44][45][46][47][48]. The methodology used has the following advantages when performing the analysis: The entropy weight method can determine the weight of the indicators by calculating the information entropy of each indicator, and then provide a basis for multi-objective evaluation. ...
... Moridi et al. went on to improve the bad effects of blackouts by studying the factors that affect them. The article analyzes the influencing factors through the best-worst and TOPSIS methods, and the results show that working in grid-restricted areas is the main cause of power outages in urban areas [39]. Liu et al. went on to explore the influence of wind environment factors in building design by investigating the optimal wind environment for building complexes in different seasons. ...
China is committed to reaching peak carbon by 2030 and carbon neutrality by 2060. The goals of reducing energy consumption and building a “beautiful China” are being urgently pursued in China. The building studied in this paper is located in the city of Turpan, where the problem of excessive energy use among buildings is significant due to the region’s hot summers and cold winters. Additionally, the fact that the office building studied in this paper has an east–west orientation is significant: the building’s main façade is oriented to the west, comprising a large area of single-layer glass curtain wall. Based on this, this paper proposes optimization strategies from two perspectives of renovation and new construction. Four design options are proposed at the retrofit level: glazed circular curtain wall; glazed enclosed curtain wall; west-facing double-glazed curtain wall circulation combined with south-facing light from the east; recycling of windows on the inside of the exterior glass curtain wall. These suggestions focus on retrofitting the glass curtain wall on the west elevation of the building. Two design options are proposed at the new-build level: west-facing south-oriented light and west-facing north-oriented light. These suggestions were primarily built around the idea of changing the orientation of the windows on the west elevation. The results show that the optimal solution is to implement the west-facing double-glazed curtain wall circulation combined with south-facing light from the east. This program shows a 64.14% reduction in heating energy consumption, a 77.12% reduction in cooling energy consumption, and a 69.67% reduction in total energy consumption. The above research has improved the deficiencies in the performance-based energy efficiency retrofit of office buildings in the region and provided new ideas and suggestions for policymakers and designers to build energy-efficiency retrofits in the early stages.
... Moreover, Mahmood et al. [36] presented the Aczel-Alsina operators for BCFSs. Further, some fundamental techniques and methods are described in the following, for instance, Schweizer-Sklar operators [37], the VIKOR technique [38], the SWARA-COPRAS technique [39], renewable energy resources [40], a best-worst technique [41], decision-making technique [42], DEMATEL-ISM integration method [43], IFSs and their applications [44], BHARAT decision-making model [45], Hamy mean operators [46], Aczel-Alsina operators [47], analysis of decision accuracy in DEMATEL technique [48], Einstein operators [49], MADM technique based on vague sets [50], Bonferroni mean operators [51], decision-making strategy [52,53], fuzzy soft code [54], Fermatean fuzzy sets [55], analysis of convexity based on hyper-soft sets [56], Pythagorean fuzzy linear programming [57], analysis of hybrid model based on IFS [58], the parsimonious spherical fuzzy sets [59,60], the AHP model [61], linear programming [62] and the aggregation operators [63]. ...
The model of bipolar complex fuzzy linguistic set is a very famous and dominant principle to cope with vague and uncertain information. The bipolar complex fuzzy linguistic set contained the positive membership function, negative membership function, and linguistic variable, where the technique of fuzzy sets to bipolar fuzzy sets are the special cases of the bipolar complex fuzzy linguistic set. In this manuscript, we describe the model of Aczel-Alsina operational laws for bipolar complex fuzzy linguistic values based on Aczel-Alsina t-norm and Aczel-Alsina t-conorm. Additionally, we compute the Aczel-Alsina power aggregation operators based on bipolar complex fuzzy linguistic data, called bipolar complex fuzzy linguistic Aczel-Alsina power averaging operator, bipolar complex fuzzy linguistic Aczel-Alsina power weighted averaging operator, bipolar complex fuzzy linguistic Aczel-Alsina power geometric operator, and bipolar complex fuzzy linguistic Aczel-Alsina power weighted geometric operator with some dominant and fundamental laws such as idempotency, monotonicity, and boundedness. Moreover, we initiate the model of the Weighted Aggregates Sum Product Assessment technique with the help of consequent theory. In the context of geographic information systems and spatial information systems, coupling aims to find out the relationships among different components within a geographic information system, where coupling can occur at many stages, for instance, spatial coupling, data coupling, and functional coupling. To evaluate the above dilemma, we perform the model of multi-attribute decision-making for invented operators to compute the best technique for addressing geographic information systems. In the last, we deliberate some numerical examples for comparing the ranking results of proposed and prevailing techniques.
... In the decision analysis section, this paper uses the entropy-based Topsis method [84][85][86][87][88][89][90][91][92][93] when making decisions on the optimization scheme. The method has the following advantages: The entropy weighting method can confirm the weighting information of the target indicators by analyzing the entropy value of the target indicators of each scenario, which in turn can provide a reference for the multi-objective assessment later. ...
The White Paper on Peak Carbon and Carbon Neutral Action 2022 states that China is to achieve peak carbon by 2030 and carbon neutrality by 2060. Based on the “3060 dual-carbon” goal, how to improve the efficiency of energy performance is an important prerequisite for building a low-carbon, energy-saving, green, and beautiful China. The office performance building studied in this paper is located in the urban area of Turpan, where the climate is characterized by an extremely hot summer environment and a cold winter environment. At the same time, the building is oriented east–west, with the main façade facing west, and the main façade consists of a large area of single-layer glass curtain wall, which is affected by western sunlight. As a result, there are serious problems with the building’s energy consumption, which in turn leads to excessive carbon emissions and high life cycle costs for the building. To address the above problems, this paper analyzes and optimizes the following four dimensions. First, the article creates a Convolutional Neural Network (CNN) prediction model with Total Energy Use in Buildings (TEUI), Global Warming Potential (GWP), and Life Cycle Costs (LCC) as the performance objectives. After optimization, the R² of the three are 0.9908, 0.9869, and 0.9969, respectively, thus solving the problem of low accuracy of traditional prediction models. Next, the NSGA-II algorithm is used to optimize the three performance objectives, which are reduced by 41.94%, 40.61%, and 31.29%, respectively. Then, in the program decision stage, this paper uses two empowered Topsis methods to optimize this building performance problem. Finally, the article analyzes the variables using two sensitivity analysis methods. Through the above research, this paper provides a framework of optimization ideas for office buildings in extremely hot and cold regions while focusing on the four major aspects of machine learning, multi-objective optimization, decision analysis, and sensitivity analysis systematically and completely. For the development of office buildings in the region, whether in the early program design or in the later stages, energy-saving measures to optimize the design have laid the foundation of important guidelines.
... BWM presents a method rooted in pairwise comparisons for addressing MCDM problems (Rezaei 2015). This approach was developed to overcome the shortcomings, such as inconsistency, observed in multi-criteria decision-making techniques that depend on matrices for pairwise comparisons (Shahi Moridi et al. 2023). The BWM method establishes weights for a group of decision criteria by comparing the best and worst criteria with all others through a binary assessment (Ghanbari ). ...
Sustainable competitive advantage, a cornerstone of strategic management, encompasses a business's enduring capability to maintain long-term financial superiority over its competitors. The business should optimize its operations by reducing costs and improving efficiency to attain a sustainable competitive advantage. In the present study, the Activity-Based Costing (ABC) system was implemented to calculate the unit costs of a hotel operating in Turkey, and the expenses were allocated to the overnight costs using the Full-Consistency Method (FUCOM) technique. FUCOM is designed to determine room costs in a hotel business accurately. Expert evaluations were simulated to interpret the results statistically. Also, the Best–worst method (BWM) is used to compare the results. The results of this study hold significant implications for decision-makers, implementers, stakeholders, and theoretical contributions to hotel operations. The proposed model will enable hotels to identify room costs and realistically achieve a sustainable competitive edge. The proposed system is also suitable for implementation by other enterprises operating in the service sector.
... There are various mathematical techniques that can be classified as MCDM methods and used for irrigation district evaluation, such as the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) [20], Bayesian Network (BN) models [21], Data Envelopment Analysis (DEA) [22], the Variable Fuzzy Set (VFS) [23], the Weighted Average Method [24], the Project Pursuit Model [25], VIse Kriterijumski Optimizacioni Racun (VIKOR) [26], and the Best-Worst Method (BWM) [27]. Among these methods, TOPSIS is a decisionmaking technique for multiple-objective decision analysis that was proposed by Hwang and Yoon [28,29] and has been successfully applied in many fields, including, but not limited to, electrical network management [30], assessments [31,32], human resource management [33], supplier selection [34], and carbon regulation [35,36]. Here, an emphasis is placed on the quantifiable difference between the evaluation object's state at a specific time and the ideal state, which can be effectively handled by TOPSIS [37,38]. ...
Irrigation districts are a pivotal infrastructure of agricultural water conservancy engineering. Implementing modernization will be the main task of large-scale irrigation districts for a considerable amount of time in the future. In this study, four typical large-scale irrigation districts in North China were investigated: the Renmin Shengliqu, Weishan, Shijin, and Zuncun irrigation districts. The concept of a modern irrigation district was deconstructed to establish an evaluation index system which includes four second-level indicators, twelve third-level indicators, and thirty fourth-level indicators. A hybrid approach based on AHP and OWA was used to quantify indicator weights used in group decision making. TOPSIS was introduced to measure the modernization level of the four irrigation districts. An obstacle factor diagnosis model was applied to search for key obstacle factors that will affect the modernization and improvement of the irrigation districts. The results showed that (1) the modernization levels of the Renmin Shengliqu, Weishan, Shijin, and Zuncun irrigation districts in 2020 and 2025 were 0.3916 and 0.5755, 0.3748 and 0.5396, 0.4493 and 0.6012, and 0.2343 and 0.6166, respectively. The evaluation results indicate that the four irrigation districts are still in the beginning phase (or even preparation phase) of the modernization process. (2) Eight indicators were identified as the main common obstacle factors for the four evaluated irrigation districts, including the irrigation water-use efficiency factor, the coverage proportion of information technology, the proportion of efficient water conservation irrigation areas, and so on. (3) There are two effective methods to enhance the modernization level of the four irrigation districts: improving water resource utilization efficiency and strengthening the management system with an emphasis on informatization. The present study can enrich the theoretical evaluation of irrigation districts and provide a scientific basis for the modernized construction and management of irrigation districts in China.
... As vision technology develops, AIML is incorporated into the anticipated system model to mitigate risky aspects of monitoring settings. The front end of an AIML system performs dependent functions, while the rear end is employed for independent functions thanks to a connection between two processing units [20][21][22][23][24][25][26][27][28]. Equation (14) is used to detect the motion of unmanned aircraft in AIML. ...
In this study, unidentified flying machines are built with real-time monitoring in mid-course settings for obstacle avoidance in mind. The majority of the currently available methods are implemented as comprehensive monitoring systems, with significant success in monitored applications like bridges, railways, etc. So, the predicted model is developed exclusively for specific monitoring settings, as opposed to the broad conditions that are used by the current approaches. Also, in the design model, the first steps are taken by limiting the procedure to specific heights, and the input thrust that is provided for take up operation is kept to a minimum. Due to the improved altitudes, the velocity and acceleration units have been cranked up on purpose, making it possible to sidestep intact objects. In addition, Advanced Image Mapping Localization (AIML) is used to carry out the implementation process, which identifies stable sites at the correct rotation angle. Besides, Cyphal protocol integration improves the security of the data-gathering process by transmitting information gathered from sensing devices. The suggested system is put to the test across five different case studies, where the designed Unmanned aerial vehicle can able to detect 25 obstacles in the narrow paths in considered routs but existing approach can able to identify only 14 obstacle in the same routes.
Cloud Computing has gained substantial popularity due to its ability to offer diverse and dependable computing services suited to clients demands. Given the rapid expansion of this technology, an increasing number of IT service providers are competing to deliver cloud services that are both of excellent quality and cost-efficient, in order to best meet the requirements of their clients. With the extensive range of options available, selecting the best Cloud Service Provider (CSP) has become a challenging dilemma for the majority of cloud clients. When evaluating services offered by many CSPs, it is important to consider multiple attributes. Efficiently addressing the selection of the best CSP involves tackling a challenging Multi-Attribute Decision Making (MADM) problem. Several MADM techniques have been proposed in academic literature for evaluating CSPs. However, the persisting problems of inconsistency, uncertainty, and rank reversal remain unresolved. In this paper the authors present a hybrid MADM framework to rank eight CSPs using nine Quality of Service (QoS) attributes. In order to achieve this objective, Fermatean fuzzy sets-full consistency method (FFS-FUCOM) is combined with Grey-Relational-Analysis and the Technique-for-Order-Preference-by-Similarity-to-Ideal-Solution (Grey-TOPSIS) technique. The framework successfully resolved the A. K. Al-Mashhadani, et al. / Quality of Service Attributes 2 aforementioned problems. Sensitivity analysis is conducted to assess the stability and robustness of the results produced by the proposed framework. The sensitivity analysis results indicate that the proposed framework offers an accurate and robust solution. A systematic ranking test is undertaken to ensure that the results are ranked in a systematic manner. Additionally, a comparative analysis is carried out with the most relevant study.
Cloud Computing has gained substantial popularity due to its ability to offer diverse and dependable computing services suited to clients demands. Given the rapid expansion of this technology, an increasing number of IT service providers are competing to deliver cloud services that are both of excellent quality and cost-efficient, in order to best meet the requirements of their clients. With the extensive range of options available, selecting the best Cloud Service Provider (CSP) has become a challenging dilemma for the majority of cloud clients. When evaluating services offered by many CSPs, it is important to consider multiple attributes. Efficiently addressing the selection of the best CSP involves tackling a challenging Multi-Attribute Decision Making (MADM) problem. Several MADM techniques have been proposed in academic literature for evaluating CSPs. However, the persisting problems of inconsistency, uncertainty, and rank reversal remain unresolved. In this paper the authors present a hybrid MADM framework to rank eight CSPs using nine Quality of Service (QoS) attributes. In order to achieve this objective, Fermatean fuzzy sets-full consistency method (FFS-FUCOM) is combined with Grey-Relational-Analysis and the Technique-for-Order-Preference-by-Similarity-to-Ideal-Solution (Grey-TOPSIS) technique. The framework successfully resolved the aforementioned problems. Sensitivity analysis is conducted to assess the stability and robustness of the results produced by the proposed framework. The sensitivity analysis results indicate that the proposed framework offers an accurate and robust solution. A systematic ranking test is undertaken to ensure that the results are ranked in a systematic manner. Additionally, a comparative analysis is carried out with the most relevant study.
Power systems as critical infrastructure are an integral part of human society and are therefore of paramount importance to modern life. Vulnerabilities in the system, that are revealed either by accidental or deliberate events, can cause large losses of power supply with sever social and economic consequences. A tool that identifies the vulnerabilities in a power system can provide the operators the means to support reliable power system operations. This paper presents a methodology for power system vulnerability assessment that couples an AC based cascading failure simulation model and a meta-heuristic optimization procedure. The objectives of the assessment is to (1) rank the most important branches in the transmission grid, and (2) identify sets of branches if simultaneously tripped will cause the cascade with highest intensity. The first objective is achieved by ranking the criticality of the branches using two criteria (i) the impact that each branch failure has on the DNS and (ii) the frequency of line overload. The second objective is achieved by hard linking an AC based cascading failure simulation model and a meta-heurist based optimization procedure. The methodology allows the generation and the identification of vulnerability scenarios, and therefore, provides insights that can be used by operators in developing strategies to minimize the effects of accidental and deliberate events. The algorithm developed for the purpose of this study is applied to the IEEE 118-bus test system and the Swiss power grid. The results demonstrate the capability of the proposed methodology for assessing power system vulnerability.
Due to the importance of electrical grid reliability, analysis and evaluation of human error in the maintenance of electrical networks should be also considered seriously. The root causes of these errors must be identified and prioritized to plan for human error reduction. One of the objectives of the present study is to identify and predict these roots for power transmission maintenance groups from organizational, job position, communication, individual, and supervision aspects along with the relationships between these factors. In particular, this paper demonstrates that supervisor behavior as an external factor has a significant effect on maintenance personnel error. For this reason, special attention has been paid to identifying and controlling human factors from a supervisory point of view in this study. This paper also provides a method for detecting the extent of the expected influence of these roots on each personnel, since human error has a random nature. This is done based on the law of mathematical expectation. Finally, a method is suggested to rank roots based on greater effectiveness and evaluate personnel with higher error expectations. The proposed method is a combination of intermediate methods, Shannon entropy, and technique for order of preference by similarity to ideal solution (TOPSIS). The origins of the four human errors between 2014 and 2018 related to the two experts of Fars Electricity Maintenance Contractor Company are compared by the proposed method.
This paper presents the use of multi-criteria decision-making (MCDM) for the evaluation of smart cities. During the development of the method, the importance of the decision-making approach in the linear ordering of cities was presented. The method of using the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) was proposed for the preparation of ranking. The method was verified by the application in the measurement of energy performance in smart cities. The authors conducted a literature review of research papers related to urban energy and MCDM published in the period from 2010 to 2020. The paper uses data from the World Council on City Data (WCCD). The research conducted allowed for the identification of the most popular MCDM techniques in the field of urban energy such as TOPSIS, AHP and DEA. The TOPSIS technique was used to organize and group the analyzed cities. Porto took the top position, whereas Buenos Aries was the last.
Recent natural disasters such as hurricanes Harvey and Maria have caused great disruption to the electric grid system.
Additionally, government authorities have set ambitious goals to reduce greenhouse gas emissions. Thus, there is a growing interest in making the electric power systems more resilient while reducing their carbon footprint. In this work, a methodology to design a resilient and eco-friendly microgrid is presented. First, the input parameters of the model are defined; second, simulation of different
microgrid configurations are performed in HOMER Grid software; third, the outputs of the model are analyzed; and finally, a microgrid configuration is selected based on economic, environmental, and resilience criteria. The considered microgrids consist of PV, battery, natural gas generator, and the electric load of an office building that consumes an average of 2 MWh per day. Different component sizes were used to determine the configuration with the lowest generator size to provide power during a two-day outage in the summer peak load. Environmental and economic analysis were performed to show the tradeoffs between different system design goals. The results indicate that installing a microgrid in an office building with a 600 kW PV array and 2.8 MWh lithium-ion battery can avoid the release of up to 287 tons of CO2 per year. The same microgrid configuration can endure a two-day blackout during the highest electric demand in the hurricane season without the need of a polluting backup generator. From this study, it was concluded that the optimal microgrid configuration depends on specific needs. Additionally, based on current technology costs, large PV systems with small batteries are economically more attractive than the base case configuration.
Households’ demand for electricity continues to increase. This trend per se should indicate increased disutility from power outages. Additionally, batteries and other back-up systems have been improved, and the frequency and duration of outages have been reduced in many countries. By comparing the results from two stated preference studies on Swedish households’ willingness to pay (WTP) to avoid power outages in 2004 and 2017, we investigate whether the WTP has changed. The WTP is assessed for power outages of 1- and 4 -h durations, and whether it is planned or unplanned. We find three main differences: (i) the proportion of households stating zero WTP to avoid power outages decreased significantly from 2004 to 2017, meaning that more households are willing to pay to avoid a power outage in 2017 than in 2004; (ii) the overall WTP was considerably higher in 2017 than in 2004, but (iii) the conditional WTP, that is, WTP for those that have a positive WTP for an outage, has decreased. These results have implications for how regulators incentivize and regulate electricity suppliers, because the results suggest that a reliable supply of electricity is of greater importance now than what the literature has suggested.
As Phasor Measurement Units (PMUs) become widely deployed, power systems can take advantage of the large amount of data provided by PMUs and leverage the advances in big data analytics to improve real-time monitoring and diagnosis. In this paper, we develop practical analytics that are not tightly coupled with the power flow analysis and state estimation, as these tasks require detailed and accurate information about the power system. We focus on power line outage identification, and use a machine learning framework to locate line outages. The same framework is used for the prediction of both single line and multiple line outages. We investigate a range of machine learning algorithms and feature extraction methods. The algorithms are designed to capture the essential dynamic characteristics of the power system when the topology change occurs abruptly. The proposed methods use only voltage phasor angles obtained by continuously monitoring the buses. We tested the proposed methods on their prediction performance under different levels of noise and missingness. It is shown that the proposed methods have better tolerance for noisy data and incomplete data when compared to the previous work that involves solving power flow equations or state estimation equations.
Power outage prediction for natural hazards usually relies on one of two approaches, statistical models or fragility-based methods. Statistical models have provided strong predictive accuracy, but only in an area-aggregated manner. Fragility-based approaches have not offered strong prediction accuracy and have been limited to systems for which system topology or performance models are available. In this paper, we create an algorithm that (1) generates a synthetic power system layout for any U.S. city based only on public data and then (2) simulates power outages at the level of individual buildings under hazard loading using fragility functions. This approach provides much more localized, building-level estimates of the likelihood of losing power due to a natural hazard. We validate our model by comparing the network properties and power outage events based on our approach with data from a real power system in Ohio. We find that our model relies on less input data comparing to statistical learning approaches yet can make accurate predictions, provided accurate fragility curves are available.
Weather events are a major source of disruptions to the electrical power grid. This study examines the occurrence and variability of major weather-related electrical power disruptions by utilizing multiple datasets. Our results show that weather is responsible for 50% of all events and 83% of customers affected by them. Thunderstorms are responsible for 47% of weather-related events, while winter storms and tropical cyclones contribute 31.5% and 19.5%, respectively. The median restoration cost for utilities during major storms was ∼$12 million, with a median restoration time of 117.5 hours (∼5 days). Tropical storms had the highest median number of customers affected, followed by thunderstorms and winter storms. Fewer mutual aid crews are utilized for thunderstorms than tropical or winter storms. The unique challenges that electrical utilities face from weather events are highlighted with case studies of Hurricane Harvey in Texas (2017), a 2011 snowstorm in the Mid-Atlantic, and severe thunderstorms in Alabama in 2011. We conclude by demonstrating that variations in the number of outage events (r=0.79) and customers affected (r=0.65) are primarily controlled by the number of storms. Weather-related power outages continue to be an important cause of power disruptions despite investments in storm outage prediction models and system hardening.
In this study, typhoon power outage models were developed to predict the number of customer outages and damaged poles in Xuwen, Guangdong, China using data from three typhoons: Rammasun, Kalmaegi and Mujigae. Our hold-out validation demonstrates that these models can accurately estimate the number of customer outages and damaged poles from typhoons. The mean relative error is 5.1% in the customer outage model and 9.6% in the pole damage model. This study has two key improvements over previous work. First, our models provide more accurate predictions through leveraging a variety of static and dynamic variables that characterize the typhoon hazard and local environmental conditions. Maximum gust wind speed, elevation, land cover and duration of strong winds are the four most important variables for both the customer and pole models. Second, we demonstrate that it is possible to provide skillful predictions of power outages at 1-km resolution. This is a significantly higher spatial resolution than past tropical cyclone power outage models. The models will be used to support improved decision making. The operational power outage forecasts will be used by the electrical utility for pre-positioning crews and materials and to notify customers who are likely to lose power.
This paper describes the development of two Outage Prediction Models (OPMs) for power outages caused by snow and ice storms on electric distribution networks, and their performance evaluation in the Northeastern United States. The first is a Machine Learning (ML) based model that is set up to predict power outages on a regular grid (4-km grid spacing). The second is a Generalized Linear Model (GLM) that is set up to predict total power outages at the town level. Both models are fed with Numerical Weather Prediction (NWP) outputs, satellite-derived leaf area index (LAI) and land cover data, and utility specified infrastructure and historical outage data. For both models the most important variables are the amount of assets on the territory, LAI, snow density, and – for the ice model – the amount of freezing rain. Results from cross-validation experiments based on 54 outage events spanning three orders of magnitude show median absolute percentage errors around 70% for both models. The GLM is able to predict extreme events (such as the devastating October 2011 nor’easter) better than ML models do, while ML models have better performance for lower impact events and present better characterization of the spatial distribution of power outages.