<![CDATA[The escalating integration of distributed energy resources and the urgency of decarbonization targets have exposed the limitations of conventional, centrally managed electrical distribution networks. This paper synthesizes findings from twenty-three studies to examine how digital twin technology and edge artificial intelligence can be combined to form a carbon-aware intelligent distribution network. The problem addressed concerns the inability of legacy supervisory control and data acquisition architectures to deliver the millisecond-scale responsiveness, emission transparency, and adaptive reconfiguration required by high-penetration renewable grids. A layered conceptual framework is proposed, integrating field sensing, edge inference, digital twin synchronisation, and carbon-weighted reinforcement learning control. Evidence drawn from the literature indicates that hybrid edge-cloud architectures reduce control-loop latency from several hundred milliseconds to below 100 milliseconds relative to cloud-only deployment, while safe deep reinforcement learning controllers for Volt-VAR optimisation converge within 300 to 500 training episodes and reduce voltage violations substantially. Carbon emission flow modelling combined with temporally shifted, carbon-aware scheduling is shown to yield emission reductions ranging from approximately 10 per cent to more than 25 per cent when co-optimised with digital twin state estimation. The synthesis further identifies bandwidth reduction of up to 82 per cent and inference accuracy gains of nearly 5 percentage points for hybrid configurations. Implications include improved grid resilience, measurable decarbonization, and a pathway toward regulatory-compliant, self-optimising distribution networks, with future work directed toward standardised digital twin interoperability and federated edge learning.]]>
Copyrights © 2024
