Abstract: challenges，including complex task prioritization，limited resource availability，and dynamic environmental changes. To address these challenges，a dynamic scheduling strategy based on a hybrid optimization algorithm is proposed. The strategy constructs a multi- objective optimization scheduling model that integrates objective functions for minimizing task completion time, maximizing resource utilization，and minimizing task delay rate，while incorporating constraints such as resource capacity and task dependencies. In terms of algorithm design，the strategy employs a greedy algorithm to generate high-quality initial solutions，utilizes an improved genetic algorithm as the core optimization mechanism，and incorporates reinforcement learning and particle swarm optimization to enhance global search capability and dynamic adaptability. Experimental results demonstrate that，whether in static or dynamic scenarios，the hybrid optimization algorithm exhibits significant advantages across different task scales in key metrics such as task completion time， resource utilization，and task delay rate.