AI-Driven Sustainability and Resiliency in Grid-of-Microgrids: Pre- and Post-event Strategies

A Systematic Review of Challenges in the Implementation and Integration of Decentralized Microgrids

Decentralized microgrids are necessary for global decarbonization, making the grid more resilient and expanding universal access. But a complicated web of interconnected challenges makes it very hard for them to be widely commercialized. This systematic review thoroughly examines these deployment challenges within technical, economic, social, environmental, and policy frameworks. While employing dual-lens analytical methodology, 105 peer-reviewed publications and reports published from 2014 onwards were aggregated from ScienceDirect, Google Scholar, and Academia. The results show that complicated inverter control requirements, non-detection zones in islanding, and power quality degradation make it much harder to deploy technology. The high upfront capital costs of battery energy storage systems and the lack of local peer-to-peer electricity marketplaces make it hard for local residents to make investments, especially in low-income areas. To promote real energy democracy, social integration needs to get past behavioral resistance, “NIMBYism,” and a history of uncertainty in institutions. The unsustainable mining of vital minerals and the impending catastrophe of technological waste create significant ecological contradictions. Also, old, centralized regulatory frameworks and the absence of common interoperability standards make these administrative problems much worse. A cross-regional analysis reveals significant geographic disparities: Europe and North America focus on the digital integration of prosumers and the reinforcement of legacy grids against severe weather, whereas emerging economies in Africa and South Asia contend with fundamental rural electrification amid inadequate infrastructure. This assessment provides a strategic path to fill these research gaps. It focuses on AI-driven predictive controllers, circular economy frameworks for batteries that have already been used, and the harmonization of grid codes around the world.

Self-Managing Energy Systems for Isolated Areas: A Technological Review of Solutions, Challenges, and Future Op-portunities

Advanced Metering Infrastructure in Microgrids: Architecture, Challenges, and Future Directions

Advanced Metering Infrastructure (AMI) is a key enabler of digital and intelligent power systems, particularly in microgrid environments. However, existing research often addresses AMI from fragmented perspectives, limiting a comprehensive understanding of its role within integrated and data-driven energy systems. This paper presents a structured analysis of AMI based on a bibliometric and thematic review of recent literature, identifying the main research trends, technological drivers, and emerging directions in the field. The results reveal a transition of AMI toward a data-centric platform that supports real-time monitoring, bidirectional energy management, and intelligent decision-making. Key domains include cybersecurity, data analytics, communication systems, and distributed energy integration, while emerging technologies such as artificial intelligence and the Internet of Energy play a critical role in future developments. Finally, the paper outlines key challenges and provides strategic recommendations to support the effective deployment of AMI in microgrids, contributing to the development of resilient and sustainable energy systems.

The Artificial Intelligence–Power Grid Nexus for Sustainability: AI–Power Grid Sustainability Nexus: Challenges and Path Forward

Artificial intelligence (AI) has shown significant promise in improving power grid sustainability; however, a co-evolutionary framework is needed for sustainable AI and sustainable grid operation. There is a need for “Grid friendly AI', that guarantees a sustainable power grid. AI is expected to increasingly rely on resilient and reliable energy infrastructure, while simultaneously serving as a critical enabler for the optimization, predictive control, and decarbonization of sustainable power grids. AI technologies are being leveraged to improve grid flexibility, enhance forecasting accuracy, enable real-time decision-making for resiliency, and support greater integration of distributed energy resources. Conversely, the exponential growth of AI workloads, particularly large-scale training and inference, poses escalating energy and carbon demands, necessitating the development of cleaner, smarter, and more adaptive power infrastructures to sustain digital systems. This article explores the nexus between AI and the power grid through the lens of sustainability. We first examine how AI can potentially help accelerate the transition to clean energy, enabling greater penetration of renewable and sustainable energy, improved demand-side flexibility, and more efficient grid operations. We then investigate the increasing energy footprint of AI itself and propose strategies to power data centers and compute-intensive workloads with sustainable electricity. We asked the question- “What can the AI-power grid community do at the intersection of AI and power to make things more sustainable?". These include geographically aligning AI infrastructure with renewable generation, leveraging edge and federated AI to reduce energy consumption, and employing carbon-sensitive workload scheduling. In addition, we discuss pressing challenges at this nexus, including limited data accessibility, lack of interoperability standards, model explainability requirements, and evolving regulatory frameworks. To address these, we present a forward-looking architecture for aligning AI development with power grid evolution, grounded in co-design principles, energy-aware AI practices, sustainable digital infrastructure, and collaborative policy making. Achieving a sustainable, intelligent future will depend on viewing AI and power systems not as isolated domains, but as dynamically co-evolving systems, wherein AI contributes to grid decarbonization, and the grid, in turn, enables environmentally responsible AI. However, AI needs to become more efficient - it is not just about allowing unbridled growth of AI, but of Green AI.

AI-Driven Integrated Energy Systems: Emerging Trends, Research Gaps, and Global Roadmap

The review integrates disparate knowledge on forecasting, optimal scheduling, degradation-aware control, and resilience enhancement across power, heat, mobility, and water–energy–food nexuses, drawing on 153 recent studies covering batteries, hydrogen, thermal storage, and sector-coupled microgrids. Digital-twin and surrogate-based optimisation, deep and reinforcement learning for multi-energy dispatch, physics-informed and hybrid models, and privacy-preserving or federated analytics that respect data sovereignty while facilitating cross-asset learning are all covered by a single classification. While pointing out enduring gaps in cross-regional validation, cyber-secure implementation, and socially just deployment in vulnerable grids, the analysis quantifies typical performance gains reported for AI-enabled storage coordination, such as reductions in unmet load, curtailed renewable generation, operating cost, and emissions. Drawing from these observations, the paper lays out a three-phase global roadmap for AI-IES in energy storage from 2030 to 2050. These phases move from reliable pilots and benchmark datasets to human-centric, interoperable ecosystems and, finally, autonomous, resilience-optimized, and justice-oriented infrastructures. The roadmap provides practical advice for researchers, system operators, regulators, and investors looking to match AI innovation with net-zero, reliability, and equity targets in future integrated energy systems. It does this by connecting algorithmic decisions to technology pathways for batteries, power-to-hydrogen, long-duration storage, and hybrid storage architectures. The review offers a state-of-the-art, comprehensive basis for co-designing algorithms, market designs, and regulatory protections that expedite bankable, real-world AI-IES deployments across various regions worldwide by specifically bridging AI methodologies, storage technologies, and multi-scale planning horizons.

Artificial Intelligence in Smart Grids and Power-Electronic- Interfaced Microgrids: A Systematic Literature Review of Energy Management, Optimisation, and Cybersecurity

The increasing penetration of distributed energy resources, variable renewable generation, battery energy storage systems, electric vehicles, and power-electronic interfaces is changing the way modern smart grids and microgrids are operated, protected, and controlled. This systematic literature review follows the PRISMA 2020 framework and examines 87 original research papers, complemented by a supplementary synthesis of 18 contextual studies that provide bibliometric, historical, and conceptual perspectives on the evolution of AI in smart grids. The primary studies are organized into six thematic clusters: energy management and forecasting; cybersecurity and intrusion detection; renewable energy integration and microgrid management; fault detection, diagnosis, and grid stability; explainable and trustworthy artificial intelligence; and emerging technologies, including digital twins, blockchain, the Internet of Things, edge computing, and federated learning. The review shows that deep learning, reinforcement learning, and ensemble machine learning are increasingly used for load forecasting, demand response, converter-interfaced renewable integration, intrusion detection, and operational optimization. However, the literature remains uneven. Fault detection, converter-aware protection, and real-time stability assessment receive considerably less attention than energy management and cybersecurity, despite their importance for inverter-based resources, grid-forming converters, electric-vehicle charging systems, and battery interfacing. Four critical gaps are identified: limited cross-grid generalizability, weak validation under realistic converter and protection constraints, insufficient adversarial robustness of AI-enabled defense systems, and limited explainability in real-time safety-critical applications. The paper provides a structured taxonomy, identifies deployment barriers, and proposes research directions for trustworthy AI in power-electronic-rich smart grids and microgrids.