Abstract: With the continuous expansion of distributed renewable energy and energy storage integration, real-time dispatching of active distribution networks faces increasingly stringent requirements. To improve the operational economy and security of active distribution networks, this paper proposes a real-time optimal dispatching method based on a genetic algorithm. By constructing a source–load–storage collaborative model and introducing adaptive genetic operators, an accelerated convergence strategy, and a rolling optimization with closed-loop correction mechanism, dynamic optimal dispatching of active distribution networks is realized. Simulation tests are conducted using an improved IEEE 33-bus system as the case study. The results show that the proposed method can reduce operating costs and network losses, improve renewable energy accommodation and dispatching real-time performance, and demonstrate good robustness.