Search

Reaching carbon neutrality by 2050 will require transmission system operators to accommodate unprecedented levels of variable solar and wind generation while preserving system reliability. To address this systemic constraint, Réseau de Transport d’Électricité (RTE), together with the research community, introduced Learn To Run A Power Network (L2RPN), a crowd-sourced competition designed to accelerate the integration of intermittent renewable sources into grid operations. L2RPN relies on 16 years of weekly scenarios (832 in total) modeled on a 118-node network under realistic operational constraints, framing real-time grid management as a Markov Decision Process. The six competing teams approached the problem by designing autonomous agents that combined heuristics, optimization, data scaling, supervised learning, and reinforcement learning techniques. We deliver a comprehensive assessment of all six teams’ performances under the competition’s stringent framework. Furthermore, we conduct an extensive examination of the publicly released winning solution, which ensures consistent decision-making across scenarios, performs real-time multimodal actions in less than 5 seconds, and achieves efficient topology control through action-space reduction and a neural policy that predicts beneficial grid actions with over 80% accuracy. Concurrently, we trained a neural alert module using 315,000 samples generated from leading agents, obtaining 93.9% recall in identifying hazardous states and enabling agents to anticipate potential failures. Ultimately, this study highlights both the potential and current limitations of AI in real-time grid operation, while establishing a transparent foundation for developing more robust and trustworthy systems to support the energy transition.

Monthly electricity demand exhibits both persistent upward trends and recurring seasonal patterns, which together pose major obstacles to reliable forecasting. This research, therefore, introduces a single-variable time-series prediction strategy that uses the Hodrick-Prescott (HP) filter to decompose the demand sequence into a smooth trend component and a seasonal component. The trend is modeled using an autoregressive integrated moving-average (ARIMA) model, while recurrent neural networks (RNNs) are employed to capture recurring seasonal behavior. The complete forecast results from combining the two separate predictions. Model effectiveness is tested on Guangzhou’s monthly total electricity usage records. When benchmarked against established techniques, including Holt-Winters, Seasonal ARIMA, and error-trend-seasonal (ETS), the developed HP_RNN_ARIMA combined approach lowers mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE) in the ranges of approximately 9.70% to 35.66%, 14.18% to 35.06%, and 20.01% to 41.92%, respectively. Compared with individual neural network models such as backpropagation (BP), RNNs, and long short-term memory (LSTM), the new model reduces MAPE, RMSE, and MAE by 9.05%-44.02%, 20.88%-51.74%, and 29.53%-56.23%, respectively. Compared with alternative hybrid techniques, the reductions in these error measures range from 3.60% to 33.39%, 4.27% to 36.67%, and 4.43% to 44.87%. The model also attains the best scores on Willmott’s index (WI) and Legates and McCabe’s index (LMI), demonstrating stronger agreement with observed values. Overall, decomposing the series with the HP filter and modeling the resulting components independently yields a clear improvement in forecast quality. 

This paper introduces and assesses two innovative ordinal classification approaches for forecasting wind speed across three horizons: 1h, 4h, and 8h. To tackle the issue, wind speed values are categorized into four discrete classes, which are vital for effective wind farm operations. Each class conveys key information about wind farm output, ranging from very low wind speeds to extreme wind speeds and their associated generation scenarios, thereby supporting operational decisions by wind farm managers. Ordinal classifiers prove more appropriate than nominal ones for this task. The central goal of the study is to evaluate recently developed ordinal classifiers for wind speed forecasting, with particular emphasis on extreme wind conditions that frequently lead to turbine shutdowns. The analysis relies on hourly wind speed records from a wind farm in Spain, along with predictor variables derived from the European Centre for Medium-Range Weather Forecasts Reanalysis v5 (ERA5). The proposed techniques consist of an Artificial Neural Network (ANN) employing the Cumulative Link Model as its ordinal output mechanism (MLP-CLMO), which prioritizes overall effectiveness, and an ANN refined through a soft labeling strategy grounded in triangular distributions (MLP-TO), which performs particularly well for extreme class predictions. The findings show that both methods outperform other nominal and ordinal techniques across evaluation metrics that properly address the data’s imbalance and ordinal characteristics. MLP-CLMO outperforms MLP-TO across general and ordinal performance, whereas MLP-TO shows stronger performance in predicting the extreme class.

Reliable forecasting of electric vehicle (EV) charging time is vital for improving driver convenience and enabling smart, real-time charge scheduling. The present work introduces a comprehensive dynamic prediction system for EV charging duration that integrates four complementary modules: data preparation, pattern identification, baseline forecasting, and adaptive error adjustment. Raw measurements from the Battery Management System (BMS) are first cleaned and scaled to correct for missing or erroneous entries. A specially designed convolutional autoencoder tailored for EVs (EV-CAE) then extracts features across multiple time scales, after which K-Means clustering groups the sessions into characteristic charging profiles. Drawing on these profile assignments, the baseline forecasting stage computes an initial estimate of remaining charging time using past session records and the assigned cluster label. For improved resilience to changing circumstances, an adaptive correction layer is incorporated; it blends linear regression, logarithmic fitting, ratio-based scaling, and neural-network-driven refinement to update the forecast during the session continuously. Validation on authentic EV field datasets reveals that the overall architecture delivers a clear gain in forecast quality. In particular, activating the adaptive correction layer increases the coefficient of determination (R²) from 0.948 to 0.960. It maintains consistent accuracy even when charging curves vary unexpectedly or when operating in cold-weather conditions. These outcomes highlight the framework’s readiness for deployment and its engineering relevance in next-generation intelligent EV charging infrastructure.

The present study proposes an original hybrid technique that combines H-∞ filtering with an adaptive linear neuron (ADALINE) architecture to estimate flicker components in power distribution networks. By taking advantage of the H-∞ filter’s strong immunity to uncertainty and noise, the approach first recovers the voltage envelope; subsequently, the ADALINE identifies with high precision the relative magnitudes (ΔVi/Vt) of the flicker constituents located at the discrete frequencies specified by IEC standards within that envelope. The resulting cooperation yields fast, reliable time-domain estimation that converges quickly and maintains performance even under heavy noise, thereby resolving the principal weaknesses of most frequency-domain solutions. In contrast to established procedures, this combined framework effectively processes complex power-system disturbances without requiring prior knowledge of noise statistics or prolonged learning phases. Performance evaluation relies on simulations aligned with IEC Standard 61000-4-15, reinforced by statistical metrics, Monte Carlo runs, and actual field recordings. Comparative outcomes reveal markedly better precision, greater tolerance to disturbances, and substantially lower computational requirements than estimators based on the Fast Fourier Transform (FFT) or the Discrete Wavelet Transform (DWT).

A virtual power plant (VPP) serves as a promising solution by aggregating distributed energy resources (DERs) and fulfilling the prosumer’s requirements for power availability, quality, and reliability. This study presents the optimized scheduling of an interconnected VPP within a multi-area framework, with tie-line connections and various renewable resources. The scheduling process begins with a day-ahead (hourly) interval, then advances to an hour-ahead interval (intra-hour and real-time), specifically using 15-minute and 5-minute time steps for the proposed VPP in the multi-area setting. The problem features two primary objective functions: net profit (to be maximized) and emissions (to be minimized). Given the involvement of renewables in the energy portfolio and the inherent complexity of the problem, the suggested multi-area VPP is evaluated using an advanced nature-inspired metaheuristic algorithm. Additionally, the formulation is extended to a multi-objective framework, with various scheduling approaches implemented to simultaneously lower emissions and enhance overall profit margins by boosting cumulative system profits. Moreover, an extensive numerical assessment across different optimization horizons demonstrates fast convergence and low computational time in achieving the optimal solution. 

The rising priority placed on energy conservation, together with the adoption of renewable sources, has grown essential to sustainable practices across today’s university campuses. This research introduces an intelligent green energy management framework (SGEMS) that integrates machine learning predictions with reinforcement learning (RL) to enhance energy utilization and photovoltaic output on an eco-conscious campus. Leveraging historical records from three campus structures, the study developed a forecasting engine capable of projecting near-term electricity demand and solar yield. When paired with RL, the XGBoost method achieved markedly better accuracy in estimating consumption and production levels than competing algorithms, with root mean square errors (RMSEs) of 14.72, mean absolute errors (MAEs) of 12.00, and mean absolute percentage errors (MAPE) of 2.18%. The work also describes an accessible, browser-based dashboard that enables live energy oversight and supports timely decision-making, empowering facility managers to anticipate deficits and regulate consumption more intelligently. Overall, the presented methodology provides an adaptable blueprint that enables campuses to reduce dependence on utility grids, improve efficiency, and serve as a reference model for subsequent eco-friendly campus programs.

The growing adoption of electric vehicles (EVs) and the expansion of their charging infrastructure offer substantial potential to advance sustainable mobility in smart cities. Nevertheless, the highly interconnected design of EV charging stations (EVCSs) renders this infrastructure vulnerable to multiple cybersecurity threats, such as false data injection, man-in-the-middle attacks, malware infections, and denial-of-service attacks. Moreover, financial threats—including fraudulent billing and credit card data theft—pose significant risks to EV users. In this study, we introduce a blockchain network built on Hyperledger Fabric tailored for EVCSs to address these vulnerabilities. The proposed network employs smart contracts to securely and transparently handle essential operations, including authentication, charging session oversight, and payment confirmation. By identifying and preventing unauthorized data alterations or access attempts, the blockchain framework enhances the robustness of EVCS networks. A before-and-after comparative evaluation of the implemented blockchain network illustrates its effectiveness in countering prevalent cyberattacks targeting EVCS infrastructure. The evaluation encompasses performance indicators derived from the Hyperledger Caliper benchmarking tool, revealing the solution’s minimal latency suitable for real-time applications and its capacity to scale in line with expanding EV infrastructure demands. Implementing this blockchain-augmented security solution is anticipated to boost user confidence and dependability in EVCS systems. 

In large cities with evolving infrastructure, optimizing water supply systems is critical. However, tackling these issues becomes considerably more difficult without a thorough understanding of the network layout and water-use patterns. This paper introduces a methodology based on geospatial data analysis to address two primary objectives. The first is the definition of service zones for infrastructure facilities to improve overall system manageability. The second is the development of an approach to determine the optimal locations for devices that collect and transmit hydraulic network parameters, ensuring their placement aligns with both water supply sources and the areas they serve. The research utilizes data from the water supply network of a city with a population of more than half a million, applying hierarchical clustering with Ward’s method to examine spatial distribution. Four territorial clusters were distinguished, each exhibiting distinct characteristics related to consumer density and water consumption volumes. The resulting cluster boundaries were compared with the system’s current service scheme, demonstrating consistency with the actual infrastructure. Clustering quality was additionally assessed using the silhouette coefficient, which confirmed the high precision and dependability of the selected method. The study illustrates the value of visualizing cluster boundaries in evaluating the even placement of pressure sensors throughout the urban water supply network. The findings indicate that combining geographic data with water consumption details not only supports efficient infrastructure planning and resource distribution but also lays the foundation for the digital transformation of the hydraulic network—an essential element of sustainable progress in contemporary smart cities.

This study explores the consequences of synchronized false data injection attacks (FDIAs) on voltage behavior in smart microgrids that rely on renewable-based distributed energy resources (DERs)—a cornerstone of modern smart city energy infrastructure. Employing both simulation-based and real-world experimental techniques, the work introduces a unified framework for analyzing and defending against coordinated threats, thereby safeguarding the reliable operation of renewable-integrated DERs, which are central to today’s urban power ecosystems. In the proposed scenario, multiple attackers independently select the most effective moments to execute two complementary cyberattacks, one producing undervoltage and the other causing overvoltage within the same smart microgrid. Each attack model is driven by an objective function that maximizes the severity of voltage deviations—either excessive undervoltage or harmful overvoltage—induced by its corresponding FDIA. Under this coordinated scheme, the adversaries construct a multi-objective optimization problem (MOOP) that simultaneously provokes significant voltage violations across the microgrid’s most exposed zones. Due to the competing objectives in this MOOP, a Pareto-front approach is applied to generate a set of non-dominated optimal solutions, along with a single best compromise solution (BCS). The potency of this combined FDIA strategy is substantiated through detailed simulation studies and laboratory-based experiments. Specifically, the well-known IEEE 13-node test feeder was reconfigured to represent a microgrid environment for the numerical simulations, while the physical validation utilized a small-scale hybrid photovoltaic/wind microgrid testbed featuring actual renewable generation sources. 

Decarbonizing buildings poses a significant challenge for urban areas. Determining which buildings should undergo retrofitting, along with the timing and methods, proves complex due to the intricate interplay between energy expenses and required investments. Although various tools have emerged in recent years to assist public and private decision-makers with these choices, none address the essential elements the authors consider. Consequently, this article introduces a newly developed tool for urban building retrofit. The tool uses a bottom-up approach, simulating each building individually while accounting for factors such as shading and neighboring structures. In a subsequent phase, three scenarios representing varying degrees of ambition were incorporated into the tool, enabling calculations of the resulting energy demand and emissions. As a further step, the initial investment and ongoing operational costs of these retrofitting scenarios were assessed through a comprehensive life cycle costing (LCC) framework. A robust, scalable framework was created and implemented to determine the LCC across multiple retrofitting scenarios in Montréal, with full details provided below.