Abstract: With the large-scale integration of distributed power sources into the grid, the fault recovery issues of active distribution networks have become more complex and important. This paper proposes a fault recovery strategy for active distribution networks based on the GLP-MOWAA algorithm. Firstly, the characteristics and objectives of fault recovery in active distribution networks are analyzed, establishing a multi-objective optimization model aimed at maximizing the active power of fault recovery loads, maximizing the output of distributed energy resources, and minimizing the number of switch operations. Then, to address the problem of high dependency on the initial population in the MOWAA algorithm, GLP theory is introduced to improve the algorithm. By leveraging the uniformity and good distribution characteristics of GLP, the method for generating the initial population is optimized, enhancing the global search capability and convergence speed of the algorithm. Finally, the IEEE 33-node distribution system is used as a case study for simulation verification. The results show that the improved MOWAA algorithm can solve the multi-objective optimization problem of fault recovery in active distribution networks in a shorter time than the original algorithm, significantly reducing fault isolation and power restoration time.