In order to mitigate the impact of DG (distributed generation) integration into distribution networks on grid safety and economic operation, it is necessary to optimize the planning of DG. Considering the uncertainties and correlations of wind and photovoltaic outputs, a bi-level planning model was established. The upper-level planning model was formulated with the objective function of minimizing the comprehensive costs, which included investment costs of DG, operation and maintenance expenses, active distribution network electricity purchase costs, micro gas turbine fuel costs, pollution control costs, and network loss costs. The lower-level operational model aimed to minimize the annual comprehensive operational costs for each scenario, subjected to constraints such as power balance, node voltage, branch capacity, and DG penetration rate. To address the issues of slow convergence speed and local optima in the whale optimization algorithm, three improvements were introduced: tent mapping, the incorporation of inertia weight, and a nonlinear convergence factor. The proposed improvements were validated through simulation case studies. The results demonstrate that the improved method enhances the performance of the whale optimization algorithm, thereby providing a more effective solution to the proposed model.