Research on Coordinated Optimization Control for Distributed Renewable Energy Integration into the Power Grid in Remote Mountainous Areas
Against the backdrop of low-carbon energy transition and rural revitalization, distribution grids in remote mountainous areas have long faced significant challenges - including poor voltage quality, high active power losses, and suboptimal renewable energy integration rates-due to complex terrain, dispersed loads, economic constraints, extensive power supply distances, and small conductor diameters. Additionally, the promotion of new energy vehicles in rural regions has created new requirements for coordinated charging infrastructure planning. To address these issues, this study proposes a coordinated optimization control method for integrating distributed renewable energy into grids in remote mountainous regions. The approach employs a Gaussian mixture model (GMM) combined with adaptive density clustering (ADC) algorithms to reduce data complexity and cluster temporal sequences, establishing representative operational scenarios that account for seasonal variations across spring/autumn and summer/winter periods. Furthermore, a two-layer optimization control model is developed for distributed renewable energy integration in such regions, with the Non-Dominant Ranking - Seagull Optimization Algorithm (NS-APO) applied to solve Pareto front analysis for the coupled mixed-integer nonlinear model. Simulation results demonstrate that the proposed method effectively balances economic viability and power quality assurance under investment constraints, providing theoretical foundations and technical pathways for enhancing renewable energy integration, improving power supply quality from basic access to optimal utilization, and advancing forward-looking planning of EV charging infrastructure in remote mountainous areas.