In the process of increasing the service capacity of digital infrastructure, the complex data generated by data terminals grows rapidly, which puts forward higher requirements for complex data task scheduling preprocessing. In this paper, based on particle swarm algorithm and improved artificial fish swarm algorithm, a hybrid particle swarm multi-objective optimization scheduling algorithm applicable to task scheduling and processing of complex data sets is designed. Then we design a reasonable expression method for the particle position and adaptation value algorithm in the multiobjective optimization algorithm, and put forward the pre-search strategy of the particle swarm algorithm to improve the search performance of the particles in the algorithm. Finally, the algorithm is equipped to construct a task scheduling and processing model for complex data sets. The results show that the hybrid particle swarm optimization algorithm established in this paper outperforms the comparison model in terms of load balancing and processing time, and is able to keep the system CPU utilization between 0.350-0.491 in the simulation experimental environment. It is also found that the application of the task scheduling and processing model in this paper can increase the power of photovoltaic and wind power generation in the grid system and reduce the operating cost of the grid system. This study provides an effective reference method for the processing of data and task scheduling in various types of complex systems, and brings new ideas and directions for research in related fields.