This chapter presents the digital twin as a transformative technology in the operation, planning, and management of microgrids. A digital twin creates a dynamic, virtual representation of a physical system, enabling real-time data exchange, advanced simulation, and predictive analytics. It allows operators to test design options, forecast demand and generation, detect anomalies, and optimise performance in a risk-free digital environment. The chapter outlines the core architecture and stages of digital twin implementation, including system modelling, adaptation, service interaction, and communication protocols. Enabling technologies—such as Internet of Things (IoT), artificial intelligence (AI), big data, and edge computing—support its real-time capabilities and applications across forecasting, control, maintenance, and resilience. Use cases from industry, including GE, Siemens, and ABB, demonstrate its practical deployment. The chapter also explores how digital twins enhance cybersecurity, situational awareness, and microgrid self-healing during high-impact events. Furthermore, it details the integration of machine and deep learning methods (e.g., convolutional neural networks (CNN), long short-term memory networks (LSTM), generative adversarial networks (GANs)) for long-term planning and intelligent decision support. By offering comprehensive system insight and predictive power, digital twins represent a critical innovation for future-ready microgrid systems, with applications ranging from operator training and predictive maintenance to resilience planning and policy simulation.