Abstract: The green and low-carbon park consists of a large number of distributed power sources, which are characterized by miniaturization and discretization. Compared to continuous variables, discrete variables have finite and intermittent values, leading to a larger and more complex search space for optimization problems. Algorithms need to traverse more possibilities when searching for the optimal solution. In this paper, the particle swarm optimization algorithm is utilized to implement coordinated optimization for the power grid planning of the green and low-carbon park. A multi-objective optimization function is constructed with the objectives of minimizing the investment cost of grid construction, minimizing system network loss, and minimizing environmental external costs, while considering constraints such as power capacity and energy storage configuration.The particle swarm optimization algorithm is employed to solve the multi-objective function and constraints. Continuous and discrete variables are normalized and mapped to a unified interval, automatically avoiding combinations of discrete variable values that violate the constraints. This reduces the number of possibilities that need to be traversed, and combines a penalty function mechanism to ensure constraint satisfaction, achieving coordinated optimization of power grid planning for the green and low-carbon park. Simulation results show that this method achieves a clean energy consumption rate of 98.2%, reduces carbon emissions to 12.3 t/month (75% reduction compared to the comparative method), and maintains a network loss rate below 2%. It provides a scalable technical path for the planning of high-proportion renewable energy parks.

    Key words: green and low-carbon park; power grid planning; coordination optimization; grid loss; particle swarm optimization algorithm