The rising frequency of large-scale, destructive wildfires has significantly affected not only natural ecosystems but also critical infrastructure, human lives, and properties. Given the devastating and often irreversible environmental and financial consequences, researchers from diverse fields are actively seeking solutions to improve resilience against wildfires. Fire suppression, one of the most effective strategies to mitigate wildfire damage, relies heavily on rapid and high-fidelity forecasting of fire spread. These predictions are essential for planning evacuations by state or local emergency management agencies, implementing preemptive de-energization strategies for electric utilities, and coordinating fire containment efforts by firefighting teams. However, a significant bottleneck across all these planning processes is the significant computational burden imposed by high-resolution wildfire modeling, the demand for improved predictive accuracy, and the need to integrate diverse and large-scale datasets. Since response time is crucial for wildfire risk management, this paper proposes a deep learning-based surrogate model to predict fire spread in just a fraction of a second. We developed and trained a convolutional neural network (CNN) model that efficiently predicts wildfire propagation. The proposed model demonstrates high efficiency, achieving an F1 score of 0.92. The contributions of this paper are twofold: (1) a fast, high-resolution CNN model that can support wildfire-related public safety power shutoff (PSPS) planning for electric utilities, and (2) a practical tool for firefighting and evacuation teams to support rapid and data-informed risk assessment.

• Converting data centres from air-to-chip (ATC), to liquid-to-chip (LTC) could reduce peak energy demand per kWhr of compute by 6%–14% • Annual energy consumption, carbon emissions, and power usage efficiency (PUE) may be improved by 4%–13% per kWhr of compute by data centre conversion from ATC to LTC • Increasing fluid differential and supply temperatures for LTC systems can eliminate the need for high energy use refrigerant compressor chillers in Australian and Asian climates. • Applying the novel control method to increase fluid differential temperatures from 5°C to 10°C based on I.T. kW measurement for LTC data centres could improve total data centre efficiency between approximately 3%∼6%, reduce PUE from a range of 1.22∼1.25 to 1.18 and potentially reduce central plant energy 18∼28%. The rapid and large-scale development of data centres to manage computational demand is resulting in potential strain on electrical energy and water utilities globally. New methods for minimising the peak power demand and annual energy of data centres that can be adapted to the different ambient conditions of various geographic locations are urgently needed. This study applies a novel advanced method of energy savings by differential temperature control via I.T. kW load measurement, to the conversion of data centres from conventional air-to-chip (ATC) cooling, to new liquid-to-chip (LTC) cooling. The novel method potentially assists elimination of energy-intensive chillers in favour of free cooling, reduces peak power demand and annual energy consumption for temperate to tropical ambient conditions. A new energy model was developed in Design Builder TM and EnergyPlus TM and was validated by onsite measurements at a state-of-the-art data centre in Melbourne, Australia and utilised to predict and optimize the improvement in energy efficiency by controlling differential temperature. The results indicate that converting from ATC cooling to LTC cooling could reduce the total peak power demand by 6%∼14% and reduce the annual energy consumption, carbon emissions and power usage efficiency by 4%∼13%. Application of the advanced control method to increase differential temperature from 5°C to 10°C for LTC systems, predicted reduction of the PUE from a range of 1.22∼1.25 to 1.18, potentially contributing an 18∼28% reduction in central plant energy.

Integrated audit intelligence: A multi-task learning model for classification and opinion generation in power systems

Electric utilities face a growing challenge in maintaininglow-costand reliable electricity amidst emerging pressures for socio-environmentalsustainability and reduction of greenhouse gas (GHG) emissions. Inthis work, we introduce an approach for generation expansion planning(GEP) that prioritizes sustainability objectives by implementing planningstrategies that constrain future generation options based on socio-environmentalindicators. Capacity expansion decisions under each strategy are thensimulated and evaluated under a wide range of possible futures. Usingthe Temoa energy system optimization model, we adopt a unique myopicforesight approach in which cost-optimal capacity expansion decisionsare locked-in based on forecasts of the future, before actual valuesare revealed. We demonstrate this approach for a case study in theYukon, Canada, by identifying robust strategies with respect to cost,reliability, GHG emissions, ecological sustainability, and socialsustainability. In our case study, more flexible strategies, suchas restricting the development of diesel generation but not othertypes of thermal generation, improve socio-environmental outcomesat relatively low risk to system cost. Conversely, more restrictivestrategies, such as avoiding all projects with potentially negativesocial or ecological impacts, risk substantially increasing systemcosts and may even have the opposite intended effect by inducing relianceon emergency diesel generators.

Corporate transition plans (TPs) are increasingly recognized as crucial for evaluating the credibility of corporate climate commitments. However, robust and transparent methods to assess the alignment of disclosed TPs with carbon budgets remain limited. Here, we introduce an open-source methodology-the production asset-based planning approach (APA)-which uses asset-level data to estimate potential CO2 emission trajectories. We apply APA to ten electric utilities and ten steel companies and find that only three companies' disclosed TPs appear broadly compatible with Paris-aligned benchmarks. Furthermore, our estimates suggest that 12% of electric utility assets and 42% of steel assets may require reinvestment before 2030, indicating a risk of carbon lock-in. Applying this method can support more robust evaluation of TPs and enable stakeholders to hold corporations accountable to reduce CO2 emissions in line with the Paris climate targets even if corporate disclosure is not available.

This article aimed to assess occupational exposure to power-frequency electromagnetic fields (EMFs) at various sites of electrical infrastructure in Jordan, including high-voltage (HV) substations, a thermal power plant and a photovoltaic station. Field measurements were taken under steady-state operating conditions and compared with occupational exposure guidelines recommended by the International Commission on Non-Ionizing Radiation Protection (ICNIRP) and the Institute of Electrical and Electronics Engineers (IEEE) Standard. The magnetic flux densities at the three sites were all below these guidelines. The electric field strengths at some HV substations occasionally exceeded the ICNIRP occupational reference levels but remained below the IEEE guideline levels. The results provide insight into EMF hotspots, the most hazardous sites and effective ways to avoid EMF exposure in power system environments. These measures include implementing engineering controls, administrative controls and personal protective equipment to reduce workers’ exposure to EMFs, thereby improving workplace safety and EMF risk management policies.

Energy transition buildings: A representative case study of refurbished single household shifted to full electric utilities combined with PV, wind and battery storage

ABSTRACT This paper traces the recent history of utility resource planning in Atlanta to understand the construction of regulatory systems that influence affordability and constraints on public participation in energy planning. In response to the energy crises of the 1970s, states adopted requirements for long-term integrated resource planning at regulated electric utilities. Integrated resource planning encouraged least-cost planning for new generation and energy efficiency while requiring public deliberation before utilities made any investments they might try to recover from ratepayers. Since 1991 when Georgia first mandated integrated resource planning, Atlanta has adopted increasingly aggressive sustainability policies that aim to mitigate climate change and address racialized disparities in energy affordability that contribute to displacement from the gentrifying city. In contrast to these ambitions, the regulated monopoly utility that serves the city has used its planning mandate to facilitate industrial boosterism. Drawing on interviews with environmental advocates, archival documents, and newspaper sources, this paper analyzes integrated resource planning as a form of regional industrial planning and looks retrospectively through the proposed build out of energy generation to power data centres to argue that energy planning must be reimagined to address racialized disparities in energy affordability and provide reparative investment in residential energy systems.

Forecasting the monthly electricity consumption of residential users is a critical task for improving energy planning, demand management, and the efficient integration of renewable energy sources into the electrical system. This study predicts the consumption of a single residential user based on historical data, including monthly consumption and average temperature records from November 2018 to December 2024. Five forecasting approaches are compared: moving averages, ARIMA, standard Random Forest, Random Forest with lag variables, and Random Forest with hyperparameter optimization using RandomizedSearchCV. The models performance is evaluated using MAE, MSE, and RMSE metrics over the last 12 months of the analyzed period, with 95% confidence intervals calculated via bootstrapping for both the validation phase and the estimation for January 2025. The results show that Random Forest models with lag variables and hyperparameter optimization outperform traditional methods such as moving averages and ARIMA in terms of accuracy. Additionally, the use of confidence intervals provides a more robust assessment of prediction reliability. It is concluded that the combined use of machine learning techniques, selection of relevant historical variables, and uncertainty quantification methods offers an effective tool for anticipating residential electricity consumption behavior. This approach can be valuable for electric utilities and policymakers seeking datadriven, reliable, and reproducible decisions.

Rapid urbanization and increasing energy demand have intensified environmental pressures, particularly in the transportation sector, which remains one of the largest contributors to greenhouse gas emissions. Although electric vehicles (EVs) represent a cleaner alternative, their widespread adoption in developing countries is constrained by insufficient and poorly planned charging infrastructure. This study introduces a hybrid Geographic Information System (GIS) and Fuzzy Analytical Hierarchy Process (F-AHP) framework for optimizing Electric Vehicle Charging Station (EVCS) site selection in West Java, Indonesia, a densely populated and hazard-prone region. Eighteen technical, environmental, social, and disaster-related criteria were evaluated through expert weighting and spatial overlay analysis to develop a disaster-integrated suitability map. The results show that only 5.02% (≈2079 km2) of the province is suitable for EVCS deployment, primarily concentrated in lowland urban areas such as Bogor, Bekasi, and Bandung, while 94.98% is unsuitable due to steep topography, active faults, and flood-prone zones. The integration of AHP and F-AHP enhances analytical precision by addressing uncertainty and expert subjectivity in complex decision-making environments. Theoretically, this research bridges a critical gap between sustainable mobility planning and disaster risk science by demonstrating the adaptability of fuzzy-based MCDM in resilient infrastructure development. Practically, the proposed model serves as a decision-support tool for policymakers, the national electric utility company, and the Ministry of Energy and Mineral Resources to guide spatially equitable and disaster-resilient EVCS deployment aligned with Indonesia’s net-zero emission targets.

The proposed research conceptually judges the inclusion of the Supervisory Control and Data Acquisition (SCADA) systems in engineering education at Tarlac State University College of Engineering (TSU-COE) based on the Commission on Higher Education (CHED) ACHIEVE Agenda (2025-2030) and the TSU Future-Proof Education Plan (2025-2035). The study uses a mixed-methodology design, which combines a qualitative documentary analysis, engineering design review, and two descriptive sur-veys with 19 academic stakeholders and 22 professionals working with electric distribution utilities to ex-amine the operational impact of SCADA on the reliability of the power system, as well as its strategic fit with existing higher education reform models. All the four pillars of the operation promoted by SCADA by utility practitioners included situational awareness and monitoring (composite mean = 4.63), automation and system response (M = 4.46), data analytics and predictive maintenance (M = 4.41), and cybersecurity and system continuity (M = 4.35). Respondents among academic people were confirmed that there was high strategic alignment with the digital transformation priority of the CHED ACHIEVE Agenda (WM = 4.58) and future accreditation preparedness (WM = 4.47). Nevertheless, a high exposure gap was found: 89.5% of faculty reported SCADA as one of the foundations of Industry 4.0, although only 31.6% of them had direct, hands- on experience. Based on these results, the paper offers a three-pillar conceptual model (Inputs-Processes-Outcomes) and a model of gradual development in laboratories to facilitate institutional implementation. The initial estimation of the costs of the implementation of the Bill of Materials shows that a full SCADA Trainer facility would cost around PHP 44.4 million. The results en-dorse the thesis statement that SCADA integration is not just a pedagogical addition but a strategic need to generate digitally adept graduates of engineering at the worldly competitive level in accordance with SDG objectives and national objectives of development.

Abstract Electrical power systems are a ubiquitous part of the Anthropocene. Wildlife interactions with these systems can be positive, for example when natural nesting substrates are limited, but are frequently negative, for example when nests catch fire or nesting individuals are electrocuted. Electrocution research focuses primarily on birds because they, especially large species, are particularly prone to electrocution. However, many other animals are also electrocuted. To explore non-avian electrocutions, we used crowdsourced data from Iran, where electric utility personnel frequently describe unusual incidents on electric industry-focused social media channels. In posts from January 2014 to December 2023, we identified 120 reports of non-avian electrocutions involving mammals (74%), reptiles (24%), amphibians (1%) and invertebrates (< 1%). Most (91%) incidents involved correctly operating electrical systems, indicating that the design of these electrical systems did not account for potential animal contacts. A few (9%) involved malfunctioning electrical components (overturned or energized power poles) that would also have been hazardous to humans. The greatest number of electrocutions occurred as a result of contact with low-voltage and ground-mounted equipment. For example, 220–600 V freestanding switchboards accounted for about one-third of electrocutions. Many of the documented incidents involved outages (n = 71), or outages together with fire ignitions (n = 8), indicating cascading effects on human populations and the environment. Mitigation measures to prevent these incidents are widely available, and should be used throughout the electrical system. Future research should document and quantify non-avian incidents beyond Iran, to better understand the impact of electrical systems on non-avian wildlife.

Since the mid-1990s the changing electricity generation technology mix has been associated with electricity sector carbon dioxide emissions that are 32 percent lower than their 2005 levels. What role have wholesale power markets played in enabling this decarbonization? We examine this question using annual state-level data for 1990 to 2020. The institutional complexity of the history of wholesale power markets and regulatory restructuring informs our block treatment window difference-in-differences empirical strategy, in which we compare generation in restructured states to different control states across different time periods. Our results suggest that lower-carbon generating sources appear to be built in greater numbers in wholesale markets relative to the control states up to 2012, largely but not entirely due to the substitution of natural gas for other fossil fuel generation, namely coal. In more recent years, restructured states and control states look more similar in their generation mix. Our event study results support this conclusion. JEL Classification: L51, Economics of Regulation; L94, Electric Utilities; Q35, Hydrocarbon Resources; Q48, Energy: Government Policy; Q53, Air Pollution; Water Pollution; Noise; Hazardous Waste; Solid Waste; Recycling

As electric vehicle (EV) adoption increases, the resulting EV battery charging will increase demand on the electric power grid. Through EV managed charging (EVMC) programs, charging can be shifted in time to support electric grid reliability and reduce electricity costs. EVMC can offer an alternative to additional supply-side generation, but the costs of EVMC implementation must be understood to evaluate the cost-benefits of EVMC. This paper presents bottom-up, forward-looking (from 2025 through 2050) estimates of the incremental costs associated with different EVMC dispatch mechanisms available to electric utilities. The costs of enabling EVMC for a range of customer participation levels are presented in the form of supply curves, which provide per-EV costs for a targeted level of participation. The largest drivers of cost variation are assumptions about future charging flexibility paradigms described in four scenarios. These supply curves can be used to quantify the expected costs of EVMC programs and enable comparison with supply-side or other demand flexibility alternatives.

Using 5-minute locational marginal prices for approximately 16,500 locations in ERCOT over a 152-day period in the summer and fall of 2023, we find strong evidence of a merit order effect from increased wind and solar output. We also find that increased wind and solar output can affect the component of locational marginal prices arising from transmission constraints. Backing out thermal generation to accommodate increased solar and especially wind output made transmission constraints more likely to bind and, especially in peak periods, exacerbated the most severe transmission constraints. Growth in non-dispatchable capacity coupled with roughly constant dispatchable capacity thus has exacerbated operational problems arising from rapid load growth. At least one transmission constraint was binding for 78 percent of the periods in our sample. Transmission is most stressed during peak loads and least stressed under intermediate loads. Increased thermal generation generally alleviated transmission constraints, as did increased physical response capability. JEL Classification : L94, Electric Utilities; D22, Firm Behavior: Empirical Analysis; Q41, Energy: Demand and Supply; Prices

In this study, a systematic investigation into vehicle‐level energy‐flow measurement, multiphysics coupled simulation, and machine‐learning driven prediction was conducted for an electric sport utility vehicle under diversified ambient temperatures. A high‐resolution experimental platform incorporating multisource measurement units was developed, and comprehensive world light vehicle test cycle experiments were performed at temperatures of −7°C, 23°C, and 35°C. Based on these experiments, a high‐fidelity simulation model was established, seamlessly coupling battery electrochemical‐thermal processes, motor electromagnetic characteristics, transmission system dynamics, and vehicle kinematics. This model accurately reproduced the dynamic energy transfer characteristics across different subsystems, demonstrating excellent conformity to real‐world test results and thus providing a robust virtual platform for parameter optimization and sensitivity analyses. Ensemble surrogate models were subsequently employed to reconstruct intricate nonlinear input–output relationships captured by the multiphysics simulations. Among evaluated methods, extreme gradient boosting with 40 estimators significantly outperformed random forest and adaptive boosting (AdaBoost), exhibiting superior prediction accuracy (RMSE = 1.056, R 2 = 0.959, MAE = 0.773) and negligible residual drift, thereby confirming its excellent generalization capability. Future work will aim to enhance model adaptability to diverse electric‐vehicle architectures and operating conditions through the enrichment of training datasets and the application of transfer‐learning strategies.

Purpose Society faces significant challenges, including the climate crisis, energy crisis and war in Europe, where electric utilities play a crucial role. This paper aims to explore how employees at electric utilities unlearn and relearn in response to past and future crises and times of rapid change. Design/methodology/approach This study is based on seven focus group interviews with electric utility companies in Sweden in 2024–2025. It includes a total of 26 employees in various roles within the organizations. The interviews explore both the energy crisis experiences in 2022–2023 and future scenarios, focusing on opportunities and challenges related to the household customer segment. Findings Employees identify the need for new approaches, communication and collaboration within and between organizations. They reveal the complexity of ensuring a functioning electricity system while handling issues of sustainability, security and reliability amid changing expectations and new technical prerequisites. At the same time, uncertain boundaries between different stakeholders’ roles and responsibilities, lack of trust and limited analytical capacity constitute constraints for learning, complicating the ability to act. Originality/value Contributions include scrutinizing how socially critical actors navigate in and for an uncertain world. The authors show how employees learn in periods marked by crisis and rapid change and present four dimensions of multi-relational learning characterized by employees’ interactions: intra-organizational, inter-sectoral, cross-sectoral and citizen-organizational. Furthermore, the authors introduce the concept of “reactivation” to bring theoretical nuance, highlighting how relearning may involve mobilizing dormant or forgotten practices.

ABSTRACT With federal climate and energy policy largely gridlocked, statelevel renewable portfolio standards (RPSs) were the central tool adopted in the United States on climate change for decades. RPSs vary by state and change over time, providing an opportunity to improve our understanding of which types of actors get a voice in policy debates over climate solutions in local newspapers. To do this, we built a fifty-state database of 1,522 articles about RPSs and conducted named entity recognition to identify the people, organizations, and interest groups mentioned in those articles. We find that electricity utilities have the greatest voice in local newspaper stories on RPSs, especially when Republicans hold power in a state. Utilities receive greater coverage than either Democratic or Republican politicians, and are mentioned about four times as often as other non-political actors, such as civil society organizations. “Earned media” is a primary way utilities are able to receive media visibility, especially for implementing renewables projects. This research suggests that utilities' perspectives dominate over civil society organizations in coverage of key climate solutions in U.S. states, potentially influencing public opinion and the policy landscape.

Accurate and reliable forecasting is critical for sustainable energy grid planning, as fluctuating demand, market volatility, and policy uncertainty pose significant challenges to both operational and financial stability. This paper proposes a novel AI-based hybrid forecasting framework that integrates Facebook Prophet, for interpretable long-term trend and seasonality decomposition, with Long Short-Term Memory (LSTM) networks, for modelling nonlinear short-term residual dynamics. This design explicitly addresses the dual requirement of transparency and high predictive accuracy in complex, non-stationary energy systems. The framework is evaluated using 18 years of historical financial data from Tenaga Nasional Berhad (TNB), Malaysia’s largest electricity utility, as a representative large-scale grid operation case study. Performance is benchmarked against ARIMA, standalone Prophet, and standalone LSTM models using RMSE, MAE, MAPE, and SMAPE, with statistical significance assessed via the Diebold–Mariano test and robustness examined under varying forecast horizons and noise perturbations. Results show that the proposed hybrid Prophet–LSTM model achieves up to 15% lower RMSE and MAPE than the best-performing baseline while maintaining stable performance under adverse conditions. The findings demonstrate that the proposed framework provides a robust, interpretable, and modular decision-support tool for utility operators, energy planners, and policymakers, enabling improved financial optimisation, tariff planning, and operational resilience in sustainable energy grid systems.

This paper is intended to observe the diplomatic relationship between Ethiopia and Somaliland since 1994: status, opportunities, and challenges. The study found that the relationship between Ethiopia and Somaliland exists within a political context expounded by Ethiopia's de jure statehood and Somaliland's de facto status. Additionally, Ethiopia was the first country to allow Somaliland to open a mission office in Addis Ababa in 1994, and it also established the General Consulate in Hargeisa in 2002. Currently, Hargeisa is home to several mission offices, including those from Turkey, the UAE, Britain, and other countries. The study identified Ethio-Somaliland opportunities to increase trade between the two sides and to create an investment exchange. For instance, this presents a significant opportunity for both sides because Somaliland has an 856 km coastline, while Ethiopia is a large and densely populated landlocked country. This situation allows Ethiopia to diversify its port options in neighboring countries to meet its demand, and it also represents a major economic opportunity for the expansion of Berbera port, which has received $442 million in foreign direct investment (FDI) from Emirates Dubai Port World (DP World). The study also highlights that there is future opportunity and hope related to the Grand Ethiopian Renaissance Dam (GERD) because Somaliland is hopeful that as soon as this dam becomes finished, it will acquire cheap and non-environmental-hazard electricity utilities. Ethiopia’s vision also includes selling electricity to Somaliland when the dam is completed so as to earn foreign currency. The study also touches on the fact that since the Horn of Africa region is unstable, the challenges surrounding Ethiopia and Somaliland include terrorism, extremism, human trafficking, informal trade, and illegal immigrants. Similar to other parts of the world, both sides are always alert to the risks their countries face, as is the region's relationship with hardliner terrorist groups. Additionally, although there is a trade imbalance and a deficit on the Somaliland side, both sides indicated that the expansion of Berbera port is complete; Ethiopia will use it more for its export and import goods than it currently does, which will help to balance the trade between the two countries.