Search

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.

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.

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.

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.

Grid intelligence increasingly depends on artificial intelligence, yet operational data remains distributed across utilities, microgrids, and electric vehicle aggregators. Federated foundation models offer a pathway for shared learning while preserving privacy, operational autonomy, and data sovereignty. Existing grid AI architectures are not designed to federate foundation models across multiple stakeholder classes with different data assets, control objectives, and regulatory obligations. The resulting fragmentation limits the ability of the power sector to build reusable intelligence across distribution, local energy systems, and mobile flexibility resources. This article proposes a scalable grid-intelligence architecture that federates a foundation model across distribution utilities, microgrid operators, and EV aggregators. The architecture integrates actor-specific layers with a shared federated foundation model layer and a governance/security layer. The article develops a conceptual architecture using layered functions, interface descriptions, model-update flows, and governance responsibilities. Validation pathways are outlined as design checks, staged pilots, and operational readiness assessments without presenting empirical results. The architecture defines how each actor contributes local knowledge, receives model improvements, and preserves control over proprietary data. The tables summarize utility, microgrid, and governance functions that support scalable, privacy-respecting federation. The proposed architecture offers a blueprint for collaborative AI in the power grid. It enables shared intelligence across diverse grid stakeholders while keeping raw data local and governance responsibilities explicit.

Autonomous control is transforming distribution grids, but governance mechanisms have not kept pace. Without built-in explainability, traceability, human oversight, and safety limits, autonomous systems risk becoming opaque and unaccountable. This article proposes a layered governance architecture that integrates explainable control, audit logs, human override, and safety constraints into a unified framework for autonomous distribution grids. The objective is to clarify how trustworthy autonomy can be designed before deployment rather than repaired after failure. The architecture is designed conceptually, with four interacting layers that address distinct governance needs. Implementation scenarios and a validation checklist are used to illustrate how the framework can guide planning, procurement, and regulatory review. The architecture defines clear roles and interfaces for each layer, ensuring that autonomous decisions remain transparent, auditable, overridable, and safe. Two tables summarize the layer responsibilities and provide a governance assessment checklist for future use. The proposed architecture offers a blueprint for building trustworthy autonomous distribution grids that meet emerging regulatory and societal expectations. It emphasizes governance as a design requirement rather than an external compliance burden.

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.