Search

Real-time coordination of distributed energy resources is increasingly complex because distribution grids now operate with high variability, bidirectional power flows, and rapidly changing local constraints. Digital twins, graph neural networks, state estimation, and uncertainty-aware dispatch provide complementary capabilities for managing this complexity. This article proposes a layered digital-twin architecture that combines state estimation, graph neural network analytics, and uncertainty-aware dispatch for real-time DER coordination. The objective is to describe an architecture that is conceptual, modular, and suitable for active distribution network operation. The architecture is designed conceptually, with layers for physical grid mirroring, measurement fusion, topology-aware learning, and robust dispatch. A validation strategy is positioned as a future pathway rather than as an experimental contribution. The proposed architecture modularizes the DER coordination task into interoperable layers with distinct responsibilities and interfaces. Three tables are used to define the architecture layers, applicable GNN functions, and uncertainty-handling mechanisms. The architecture provides a blueprint for next-generation distribution management systems that require real-time observability, learning-based analytics, and robust decision support. It is intended to guide future implementation, simulation, and field validation.

Distribution-grid congestion is becoming more difficult to anticipate as photovoltaic generation, batteries, electric vehicles, and flexible demand reshape feeder power flows. Graph neural networks provide a natural way to represent feeders, but a conceptual framework is needed to connect topology, physics, and flexibility signals coherently. This conceptual research article proposes a physics-informed graph neural network framework for forecasting distribution-line congestion and voltage violations. The framework is designed to produce hourly congestion probabilities over a 24-hour horizon. The proposed model represents buses as graph nodes and lines or transformers as graph edges, while DER flexibility signals are encoded as forward-looking node attributes. Physical consistency is introduced through power-flow residuals, voltage-bound penalties, and thermal-limit penalties in the learning objective. Rather than reporting experimental results, the article specifies the architecture, input requirements, loss formulation, benchmarking logic, and explainability design required for future empirical validation. The framework is intended to guide implementation on realistic feeder datasets. The proposed PINN-GNN is expected to improve congestion awareness by combining electrical topology, flexibility availability, and physics-informed regularization. Its explainability layer is designed to help operators identify which lines, buses, or DER resources most influence a forecasted congestion event.

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.

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).

Energy efficiency in industrial systems remains a major challenge, as conventional data-driven models are often constrained by limited precision and insufficient data. Integrating the physical laws that govern energy systems can enhance performance and ensure greater physical plausibility; however, such models often struggle with loss computation and often overlook dynamic interactions among subsystems, leading to excessive simplification and reduced real-world utility. Accordingly, this study explores a theoretical framework for constructing a conservation-law-guided neural network to improve energy-efficiency forecasting in industrial processes. The framework embeds physical principles directly into floating nodes built upon a long short-term memory (LSTM) architecture, enabling the model to capture relationships among process variables more effectively. At the same time, gradient aggregation enhances both fluidity and interpretability. Performance was assessed through two large-scale industrial case studies—vinyl chloride monomer production and detergent powder manufacturing—where the proposed model achieved notable gains in prediction accuracy and overall reliability, delivering test prediction improvements of 12.2% and 5.87% compared to previously published approaches. Compared with methods that rely on network architecture modifications, the proposed model demonstrated superior reliability and reproducibility in energy-efficiency forecasts. Furthermore, the model effectively identified energy inefficiencies, resulting in a 4.21% decrease in energy use and a corresponding reduction of 377.35 tons in carbon emissions.

Advanced control strategies have been applied to manage variable power output in standalone microgrids, reducing the risk of frequency instability and power-quality deterioration. Nevertheless, a key difficulty arises: these computationally intensive techniques, when used without stability checks, may fail to cope with the fast dynamics of real-world conditions, particularly under communication delays. This research proposes a versatile real-time solution for frequency regulation that relies on an artificial neural network (ANN) confined to stable operating regions. The proposed method combines stabilizing PID controllers—derived via small-signal analysis—with an automated optimization of ANN weights and reinforcement learning (RL)-guided constraint selection. Initially, stabilizing PID controllers are developed using the stability boundary locus approach and the Mikhailov criterion, with explicit consideration of communication delays. Subsequently, controller parameters are fine-tuned in real time via an automated search for optimal coefficient sets, using a constrained ANN to keep frequency deviations within a predefined parameter space. The framework is further strengthened by an RL-based tuning mechanism trained on an interpolated stability boundary curve, guaranteeing both stability and enhanced performance. This unique integration of ANN, RL, and sophisticated PID tuning represents a significant advancement in addressing frequency control challenges in isolated AC microgrids. Experimental results demonstrate that the proposed approach surpasses conventional techniques thanks to its reduced parameter search domain. Specifically, it achieves greater reductions in both transient and steady-state frequency deviations compared to semi-constrained and unconstrained alternatives. The enhanced performance metrics and stability assessments confirm that the method delivers superior system behavior and robustness under varying operating conditions.

Photovoltaic systems contribute substantially to electrical grid capacity, yet the intermittent nature of solar resources and uncertainties in output make grid balancing and reserve allocation challenging. Accurately forecasting solar production begins with reliably estimating clear-sky irradiance levels. While broadband atmospheric turbidity parameters can capture reductions in clear-sky conditions, the precision of these models hinges on data capturing current and future aerosol concentrations and water vapor levels. Obtaining such information requires observations that are both temporally and spatially proximate, given the high variability in turbidity. Unfortunately, these kinds of measurements are available in near real time only at a small—and shrinking—set of locations. This study introduces an innovative approach to infer time-dependent, site-specific turbidity levels using more widely accessible data from pyranometers or monitored PV system outputs. The technique leverages a long short-term memory (LSTM) recurrent neural network to isolate the turbidity-related component embedded within global irradiance (or PV power-derived) records, overcoming the natural suppression of this signal. Designed for near real-time implementation, the method supports solar forecasting needs. Evaluation focuses on two aspects: (1) its capacity to replicate turbidity values calculated historically from beam irradiance observations during clear-sky periods; and (2) its effectiveness when supplying turbidity estimates (via persistence forecasts based on daily averages) as inputs to clear-sky models.

Improving energy efficiency in the petrochemical sector is vital for reducing energy use and mitigating environmental harm. A reliable model for energy efficiency can provide important guidance for decision-making on operational process adjustments. In real-world settings, however, the varying sampling frequencies common in petrochemical facilities make conventional methods for estimating energy efficiency less dependable and more challenging to apply to multirate datasets. To address this, the present study introduces a multi-channel convolutional neural network framework that leverages transfer learning of model parameters to enhance energy efficiency forecasting despite irregular sampling rates. The multi-channel design enables the extraction of distinct temporal patterns by applying convolutions across the time axis of the data. At the same time, transfer learning enables the model to adapt and capture novel input behaviors after initial training. The effectiveness of this approach for both predicting energy efficiency and evaluating potential savings was demonstrated through its implementation in a vinyl chloride monomer manufacturing scenario. Results indicate that the suggested model surpasses standard benchmark approaches and conventional CNN architectures in predictive precision and consistency, achieving an R² value of 0.97. Incorporating transfer learning helps maintain robust performance without major declines and improves the model’s flexibility for continuous, real-time energy monitoring. In addition, an analysis of energy discrepancies identified substantial conservation opportunities, resulting in an average annual reduction in energy use of 7.25% and a corresponding decrease of 5,709 tons in CO₂ emissions.

This study investigates the prediction of fine-grained electricity peak demand using coarser-resolution data. Specifically, it addresses whether sparse high-resolution monitoring can inform forecasts of future high-resolution peaks when detailed measurements are unavailable, a question of particular importance for network operators evaluating the replacement of costly monitoring systems with predictive models. We develop models capable of estimating half-hourly maxima and minima from one-minute interval electricity load data using inputs aggregated to 30-minute intervals. Our methodology combines generalized additive models (GAMs) and deep neural networks (DNNs), both widely applied in load forecasting. The analysis includes an in-depth assessment of input feature importance, focusing on load patterns, meteorological variables, and seasonal trends. The proposed approach achieved first place in a data competition organized by Western Power Distribution (WPD), a UK electricity distribution operator. Beyond the competition, we conduct an extended evaluation over an additional 11 months, confirming that our combined model significantly outperforms the benchmark in out-of-sample root mean squared error (RMSE), achieving a 57.4% reduction compared to the competition reference.