This study focuses on optimizing the lifecycle management of distribution network (DN) using digital twin (DT) technology. By constructing a Distributed Network Digital Twin (DNDT) and its comprehensive evaluation system (DNDT-ES), the research aims to facilitate the intelligent transformation of distribution network planning, construction, and operation and maintenance (O&M). The study employs multidimensional data integration, advanced simulation, and real-time data analysis methods. Data on distribution network (DN) operations is collected using IoT devices such as drones and sensors. This data is then processed using big data techniques and AI algorithms. The research progresses DNDT from a basic “digitalization” phase to an advanced “co-intelligence” phase, achieving precise perception and prediction of the distribution network (DN)‘s state. The study successfully established the DNDT-ES, significantly enhancing the capabilities of intelligent monitoring, fault diagnosis, and predictive maintenance of DN. Verification through multiple typical application scenarios, such as fault alarms, performance degradation analysis, and load forecasting, demonstrated DNDT’s effectiveness in improving O&M efficiency and reducing fault risks. This provides scientific evidence for the safe, economical, and efficient operation of DNs. This research integrates cutting-edge technologies such as DT, big data, and AI, bringing revolutionary changes to DN management. The introduction and implementation of the DNDT-ES not only enriches the application cases of DT in the power industry but also offers a practical technical pathway for intelligent and refined management of DNs. It plays a crucial role in promoting the digital transformation and sustainable development of the power industry.