Search

Smart meters generate high-resolution data that can feed forecasting models for a range of distribution network applications. However, the literature remains fragmented across forecasting methods, data structures, and operational use cases. No comprehensive taxonomy links forecasting model characteristics to the distinct requirements of grid flexibility, microgrid management, and congestion control. This limits the ability of researchers and system operators to choose models according to data availability, forecast horizon, and grid function. This article develops a taxonomy of smart-meter forecasting models for distribution-level operation. The taxonomy maps model categories, data inputs, forecast horizons, and application domains into a structured classification framework. A systematic literature review of 27 peer-reviewed journal articles published from 2017 to 2024 was conducted. Models were classified by mathematical structure, data requirements, forecast horizon, and relevance to grid flexibility, microgrid energy management, and congestion control. The taxonomy organises forecasting approaches into classical time series, conventional machine learning, deep learning, hybrid and ensemble, and probabilistic forecasting categories. Six tables support the review method, model classification, smart-meter data mapping, application suitability analysis, full taxonomy, and research gap assessment. The taxonomy provides a structured decision-support tool for selecting and designing forecasting models for specific distribution grid tasks. It highlights gaps in cross-domain transferability, real-time deployment, benchmarking, data integration, and operational validation.

Microgrids need real-time energy management that integrates accurate load and solar forecasts with efficient battery dispatch while preserving battery lifetime. Forecast uncertainty can increase unnecessary grid imports, battery cycling, and curtailment when operational decisions rely on single-source prediction. This paper proposes a real-time forecasting and dispatch framework combining a hybrid load–solar prediction model with a degradation-aware battery scheduling strategy. The objective is to improve short-horizon operational decisions while reducing avoidable battery ageing. A hybrid forecasting model uses distinct methods for load and solar components. The dispatch strategy minimises operational cost while incorporating a degradation penalty derived from a cycle-life model. The framework is tested on representative microgrid data against persistence, statistical, and non-degradation dispatch benchmarks. The hybrid forecaster reduces prediction error compared to single-model approaches, and the degradation-aware dispatch extends estimated battery life by 8.6% while maintaining near-optimal economic performance. The framework also reduces unnecessary charge–discharge reversals during periods of volatile photovoltaic output. The integrated real-time system offers a practical, computationally light solution for microgrid operators, balancing cost, accuracy, and battery health. Its design supports deployment in campus, community, and commercial microgrids with limited computational infrastructure.

Renewable-rich microgrids face operational complexity from variable generation, storage dynamics, flexible loads, and the need for human oversight. A layered architecture can manage this complexity by separating functions while preserving coordination. Existing microgrid control architectures often entangle forecasting, scheduling, demand response, and supervisory control. This can make energy management systems brittle, difficult to maintain, and insufficiently accommodating of operator override. This article proposes a layered architecture that cleanly separates forecasting, battery scheduling, demand response, and operator override functions. The aim is to support modular design, resilient operation, and transparent human supervisory control. The architecture is developed conceptually using established ideas from microgrid energy management, hierarchical control, renewable integration, storage scheduling, demand response, and human-in-the-loop supervision. No experiments are conducted, and no quantitative results are presented. The architecture comprises four layers with defined functions, inputs, outputs, decision horizons, and interfaces. A validation plan is reserved for the second part of the article, while this part establishes the architecture logic and the forecasting layer. The proposed architecture offers a blueprint for building modular, resilient, and human-centred microgrid energy management systems. It is intended as a conceptual reference model for future implementation, testing, and refinement.

Day-ahead distribution-grid operation requires anticipating customer demand, renewable generation, network loading, and available demand-side flexibility. Smart-meter data provide a practical basis for identifying recurring consumption patterns and embedding those patterns into operational scheduling. This article presents an original forecasting-optimization decision-support system for day-ahead distribution-grid operation. The system integrates smart-meter clustering, renewable prediction, and flexible load scheduling to support distribution system operators. The proposed system processes smart-meter profiles into consumer clusters, predicts day-ahead photovoltaic and wind generation from weather-driven features, and schedules flexible loads through constrained optimization. The decision-support workflow is designed to produce feeder-level schedules, expected voltage conditions, congestion indicators, and operator-facing recommendations. The clustering module identifies consumer groups with different peak timing, ramping behavior, and flexibility availability. The integrated DSS is structured to reduce peak loading, improve voltage profiles, and lower operational cost compared with a baseline day-ahead plan without forecast-informed scheduling. The proposed DSS offers a practical framework for data-driven distribution-grid operation. It supports renewable integration by translating forecasts and customer flexibility into actionable schedules for day-ahead planning.

Smart-meter load forecasting is essential for distribution-grid operation, flexibility scheduling, congestion management, and renewable integration. However, centralizing household-level smart-meter records can expose private behavioral patterns and reduce consumer trust. This article proposes a federated forecasting framework for accurate smart-meter load prediction across heterogeneous distribution feeders. The framework enables multiple feeders to collaboratively train forecasting models without transferring raw household consumption data. The proposed framework combines feeder-local temporal neural networks, federated aggregation, feeder-aware personalization, and optional differential privacy. It is validated through simulation on multi-feeder smart-meter datasets with different customer mixes, photovoltaic penetration levels, missing-data rates, and load variability. The framework achieves forecasting accuracy close to a centralized privacy-free benchmark while outperforming local-only and non-personalized federated baselines under strong feeder heterogeneity. Differential privacy introduces a controlled accuracy penalty that remains acceptable for day-ahead and intra-day feeder operation. The proposed federated forecasting framework provides a practical privacy-preserving solution for distribution system operators that need accurate load forecasts across diverse feeders. The results indicate that collaborative learning can preserve household privacy while improving feeder-level prediction accuracy.

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.

Electric vehicle charging imposes new operational stress on distribution grids, especially where local transformer capacity and feeder voltage margins are limited. Grid-edge intelligence could enable charging decisions to be made closer to the physical constraints that shape those impacts. Existing EV charging control architectures often depend on centralized optimization, cloud-side visibility, or stable communication paths. Such designs can create privacy, latency, and resilience gaps when local operating conditions change rapidly. This article proposes a layered grid-edge intelligence architecture for distributed EV charging control. The architecture integrates local forecasting, federated model updates, and resilience-aware coordination into a unified system design. The architecture is developed conceptually through functional layers, interfaces, data flows, and operational workflows. Implementation scenarios and validation stages are outlined to guide future simulation, hardware-in-the-loop testing, and field deployment. The proposed architecture defines local forecasting nodes, a federated update layer, and resilience coordination functions that interact through structured protocols. Five tables are specified across the full manuscript to summarize model roles, coordination strategies, resilience mechanisms, deployment scenarios, and validation procedures. The architecture offers a blueprint for grid-edge EV charging management that balances intelligence, privacy, and resilience. It is intended to support future practical implementation rather than report experimental results.

Foundation models are transforming artificial intelligence by enabling pre-training, adaptation, and reuse across heterogeneous tasks. Their application in energy systems is emerging rapidly, creating a need for systematic synthesis across forecasting, control, and decision-support settings. This systematic review identifies, categorizes, and evaluates the use of foundation models in energy-system forecasting, grid-edge control, and smart-grid decision support. It focuses on how large language models, pre-trained transformers, multi-modal models, and emerging time-series foundation models are adapted for energy tasks. A PRISMA-guided search of peer-reviewed literature from 2017 to 2025 resulted in 30 included studies. Models were classified by architecture, fine-tuning method, data modality, and application domain. The review finds that large language models dominate decision-support applications, while pre-trained transformers and time-series foundation models are most developed in forecasting. Grid-edge control applications remain nascent, with most studies addressing planning, diagnostics, or dispatch rather than closed-loop physical deployment. Foundation models hold significant promise for smart grids, but critical gaps remain in real-time control, safety assurance, privacy, and evaluation. A research agenda is proposed to guide rigorous, trustworthy, and operationally relevant deployment.

Smart-grid forecasting requires models that can reason across heterogeneous temporal, environmental, and structural information. Existing forecasting architectures often treat load sequences, weather context, and grid topology as separate modeling inputs rather than as jointly learnable forecasting evidence. This article proposes a foundation-model architecture for multi-horizon smart-grid forecasting. The architecture is designed to integrate smart-meter sequences, weather context, and grid-topology tokens within a unified transformer framework. The proposed architecture could encode smart-meter data through patch-based or convolutional sequence tokenization. Weather information would be represented through learned meteorological embeddings, while feeder topology could be incorporated through graph-derived or learnable topology tokens. The design specifies how heterogeneous tokens may be fused through cross-modal attention and routed toward horizon-specific forecasting heads. It also outlines an evaluation strategy based on pre-training across diverse feeders and fine-tuning on held-out forecasting tasks. The architecture offers a conceptual blueprint for generalizable smart-grid forecasting systems. Further validation would be required to determine whether unified tokenization improves transferability across feeders, substations, and regional grid configurations.

Reliable short-term forecasting of solar radiation is crucial to ensuring the smooth operation and optimal scheduling of photovoltaic (PV) power systems. At present, cutting-edge encoder–decoder frameworks that leverage satellite remote sensing imagery are the dominant strategy for accomplishing this task. Yet these approaches reveal clear weaknesses, particularly when using longer prediction windows. Under extended horizons, the resulting maps commonly display blurred spatial patterns and noticeable inaccuracies in radiation levels. Such flaws substantially undermine forecast sharpness and trustworthiness, rendering them inadequate for applications requiring very high accuracy. To address these shortcomings, we introduce GAN-Solar — a novel post-processing architecture for improving short-term solar radiation predictions that leverages Generative Adversarial Networks (GANs). The framework adopts a conditional ED-AttUNet as its generator. A carefully designed discriminator equipped with residual blocks, stepwise resolution reduction, and auxiliary conditional signals is trained to separate genuine from synthetic radiation fields. Through this competitive training — steered by a composite loss and a discriminator acting as an adaptive quality metric — the model progressively sharpens prediction fidelity. Evaluations of real summer solar radiation datasets show that GAN-Solar delivers substantial gains in output quality. Compared with the plain ED-AttUNet baseline, it reduces the Root Mean Square Error by about 3.2% and increases the Structural Similarity Index from 0.84 to 0.87. Overall, the method effectively corrects for texture smearing and intensity warping, yielding noticeably crisper, more faithful solar radiation maps.

Precise prediction of load profiles—most notably the accurate identification of peak demand—remains difficult owing to the highly variable and unpredictable patterns of energy use. This work evaluates three forecasting approaches: Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and a hybrid ensemble combining SVR, Gated Recurrent Units (GRU), and Linear Regression (LR) to generate 24-hour-ahead load forecasts. Individual load categories—household (HH), heat pump (HP), and electric vehicle (EV)—were treated together using full one-year consumption records. The research focuses on improving the reliability of load-profile predictions by comparing LSTM, SVR, and the proposed ensemble across HH, HP, and EV demand patterns. An innovative correction procedure is presented that refreshes the forecast every 8 hours, thereby improving forecast trustworthiness. Results underscore the value of deep learning techniques for better anticipating electricity demand, with particular strength in recognizing peak events, which in turn supports smoother and more cost-effective power system management. Both graphical assessments and quantitative validation metrics were analyzed, covering model behavior during off-peak hours, peak hours, and across the complete daily cycle. Across the tested approaches, LSTM delivered marginally stronger overall metrics in the majority of cases and demonstrated especially good performance at detecting peaks. That said, the hybrid model slightly outperformed LSTM when predicting EV-specific power demand, achieving an on-peak mean absolute percentage error (MAPE) of 21.45%, compared with 29.24% (SVR) and 22.02% (LSTM). Even so, graphical inspection clearly illustrated LSTM’s superior peak-capturing ability. This advantage was also evident in the on-peak mean absolute percentage error (MAPE) and symmetric mean absolute percentage error (SMAPE) values, where LSTM improved by roughly 3–5% relative to both SVR and the hybrid model. In the final application, LSTM was used to forecast next-day load profiles based on real measurements collected from four separate grid areas and consistently demonstrated excellent peak-detection capability, with MAPE below 10% across most of those datasets.

Amid the ongoing acceleration of urban development, tertiary sector consumption and household electricity demand have emerged as the dominant components of overall municipal power consumption. Such loads are highly sensitive to unpredictable factors such as occupant behavior and meteorological conditions, which often lead to irregular deviations from expected trends and, consequently, considerable prediction inaccuracies. The present study introduces an integrated prediction approach to improve forecast precision for city-wide electricity demand, particularly across intervals characterized by anomalous consumption shifts. Initially, a systematic metric is developed to detect and quantify these irregular load excursions by analyzing the residual series obtained through decomposition of the raw load sequence. Next, a data-expansion strategy grounded in Generative Adversarial Networks is developed to synthetically augment the otherwise sparse set of anomalous instances, thereby enriching the dataset available for model training. Lastly, the sophisticated TimesNet architecture is adopted to effectively model the intricate, nonlinear dynamics observed in load behavior throughout periods of unusual variation. Validation experiments performed on real-world consumption records from Chongqing, China, substantiate the performance gains achieved by the suggested framework.

A new method for generating time series simulations of electricity price scenarios is introduced. The “Time Series Simulation Conditional Generative Adversarial Network” (TSS-CGAN) produces short-term scenarios of electricity prices. Specifically, the network can output a 24-dimensional vector that reflects the typical dynamics of electricity markets. This approach can serve as an alternative to conventional financial-mathematical techniques, such as statistical factor models, for modeling the price distribution around a given forecast. The dataset spans 3 years from 2020 to 2023. The empirical analysis focuses on the EPEX SPOT market in Europe. An electricity price scenario consists of the prices for the hourly contracts from a day-ahead auction on the EPEX SPOT power exchange. The model takes multivariate time series as input features, including point forecasts of electricity prices along with fundamental data on generation and load profiles. The TSS-CGAN architecture integrates the principles of Conditional Generative Adversarial Networks with 1D Convolutional Neural Networks and Bidirectional Long Short-Term Memory units. Model performance is assessed using both qualitative and quantitative measures. For evaluation purposes, 10,000 simulations are generated for a test period. Qualitative assessment examines whether the model correctly captures and reproduces key electricity market-specific patterns. The quantitative evaluation involves comparing standard error metrics against benchmark models such as DeepAR, Prophet, and Temporal Fusion Transformer, analyzing quantile ranges and error distributions, and conducting a sensitivity analysis. The findings demonstrate that the TSS-CGAN surpasses benchmark models like DeepAR by lowering the continuous ranked probability score by 50% while effectively accounting for market-specific factors, such as the generation of intermittent renewable energies, and responding appropriately to variations in the relevant variables.

Swift technological progress has heightened the importance of managing charging demand and refining travel routes for electric vehicle (EV) fleets, particularly in urban settings. Sensors based on IoT, embedded in charging stations and vehicles, supply live information about driver charging routines, road congestion, vehicle positioning, and surrounding conditions—greatly strengthening forecasting and optimization techniques. This continuous stream of IoT data powers the combined deep learning architecture, GNN-ViGNet, to predict upcoming EV charging requirements. An analysis of readings from 400,000 IoT devices distributed across charging points and EVs in Texas was performed to reveal typical charging behavior. These devices continuously log key indicators, including user charging preferences, current traffic levels, and diverse external conditions. Data refinement was achieved through Frequency-Aware Dynamic Range Scaling, together with sophisticated preprocessing techniques including Categorical Encoding. Ultimately, the GNN-ViGNet framework delivered a prediction accuracy of 98.9%. Beyond conventional metrics such as Root-Mean-Square Error (RMSE) and Mean Squared Error (MSE), the research introduced the Forecast Accuracy Rate (FAR) and the Charging Load Variation Index (CLVI) to provide a more comprehensive evaluation of predictive capability. The work introduces both an advanced forecasting system and a novel hybrid Coati–Northern Goshawk Optimization (Coati–NGO) technique designed for route planning. Real-time route modifications become possible thanks to live IoT feeds that include congestion updates, vehicle coordinates, and remaining battery capacity. The Coati–NGO algorithm combines the broad search strength of Coati Optimization (COA) with the refined exploitation strength of Northern Goshawk Optimization (NGO). Compared against Particle Swarm Optimization (919 km) and the Firefly Algorithm (914 km), it substantially reduced the total distance traveled to 511 km. Moreover, this combined method exhibited quicker convergence, consistently locating high-quality solutions by the 100th iteration. Overall, the presented EV fleet management system leverages continuous IoT inputs to improve charging network performance, reduce operating expenses, and enhance operational effectiveness—delivering an adaptable, realistic framework suitable for city-wide electric mobility.

Sophisticated machine learning (ML) techniques have demonstrated superior performance over conventional methods across numerous forecasting tasks, particularly in electricity price forecasting (EPF). Nevertheless, the predictive capability of these ML models deteriorates markedly when encountering input data that differs significantly from the examples observed during training. This phenomenon frequently occurs in EPF due to shifts in market conditions, such as surges in fuel costs, higher integration of renewable energy sources, or modifications in regulatory frameworks and operational rules. While the decline in accuracy on unfamiliar data is problematic, an even greater difficulty lies in the inability to anticipate when the model will produce unreliable outputs. This lack of foresight exposes electricity market participants—including bidding agents and retailers—to considerable financial risks stemming from erroneous price predictions. Consequently, it is critical to determine whether a given model prediction can be relied upon in real time. To address this need, the present study introduces a trust evaluation algorithm for EPF applications grounded in explainable artificial intelligence (XAI) methods. The proposed algorithm computes trust scores that indicate the reliability of each new prediction generated by the model. These scores are constructed in two phases: first, a preliminary score is derived from the correlation between local and global explanations; second, the score is refined using SHapley Additive exPlanations (SHAP) values for individual features. Such score-based interpretations are more accessible and actionable for EPF practitioners, such as asset managers and traders, than conventional feature-based visualizations. The effectiveness of the algorithm is assessed using datasets from the Italian electricity market and the Electric Reliability Council of Texas (ERCOT). Empirical results reveal that the method achieves over 85% accuracy in recognizing reliable predictions when the incoming data distribution closely matches the training distribution. Under conditions of distributional shift, the algorithm maintains a comparable level of accuracy in correctly flagging unreliable predictions.

Recent advancements have sparked growing interest in exploiting collections of pre-trained models, known as model hubs, particularly within computer vision applications. In practice, this involves first identifying a suitable pre-trained source model and then tailoring it to the new target domain to bridge any mismatches. Despite this trend, investigations into optimal model choice and tailoring methods for renewable energy generation forecasts remain scarce. Specifically, prior research has not delved into varied selection or adaptation techniques tailored to different neural network structures. Furthermore, no existing analyses have systematically evaluated how the volume of available training data affects outcomes, nor have they incorporated seasonal variations into performance assessments. We bridge these research gaps through an initial in-depth study of model selection and adaptation within transfer learning frameworks for renewable power prediction. Inspired by cutting-edge advances in computer vision, the analysis draws on operational data from 667 wind farms and solar (photovoltaic) installations across six datasets. To generate robust error metrics, we simulate scenarios with varying volumes of training observations across seasons. Model selection is then appraised using both marginal likelihood estimates and resulting forecast inaccuracies under these constrained data regimes. In addition, four separate adaptation methodologies are rigorously compared. Building on and surpassing conventional approaches, we introduce Bayesian linear regression to model the output variable from deep features derived by a neural network backbone. This technique delivers superior results compared to standard baselines, even with only 7 days of local training data. It also shows that full network fine-tuning provides negligible gains unless at least 3 months of data are available. Beyond that, we demonstrate that aggregating predictions from multiple models into ensembles markedly improves the effectiveness of both selection and adaptation. Consequently, ensemble-based strategies achieve mean error levels with only 30 days of training data that would otherwise require a full year of observations. In the most representative datasets, this yields average errors of 9.8% for photovoltaic power and 14% for wind power, utilizing only seven days of site-specific training data.

In the context of dynamic pricing, reliable and precise demand-side electricity price forecasting is crucial for effective energy management. We propose a new electricity price forecasting model that delivers consistently accurate predictions. The underlying prediction framework decomposes the time series via a wavelet transform before applying Long Short-Term Memory for forecasting. Earlier research using this framework has consistently applied the same mother wavelet for decomposition, without variation. Nevertheless, this fixed approach struggles to adapt to the daily or seasonal fluctuations inherent in the time series. To address this limitation, we introduce periodic switching of the mother wavelet, effectively enabling flexible modification of the decomposition technique and yielding stable, high-accuracy electricity price forecasting. Experimental evaluation revealed that the model enhanced prediction accuracy by up to 42.8% relative to the version employing a fixed mother wavelet. The findings confirm that this flexible forecasting approach reliably produces highly accurate results.