The rapid integration of distributed energy resources (DERs) such as photovoltaics (PV), wind turbines, and energy storage systems has transformed modern power systems, with hosting capacity optimization emerging as a critical challenge. This paper presents a novel Hybrid Proximal Policy Optimization-Wasserstein Generative Adversarial Network (PPO-WGAN) framework designed to address the temporal-spatial complexities and uncertainties inherent in renewable-integrated distribution networks. The proposed method combines Proximal Policy Optimization (PPO) for sequential decision-making with Wasserstein Generative Adversarial Networks (WGAN) for high-quality scenario generation, enabling robust hosting capacity enhancement and operational efficiency. Simulation results demonstrate a hosting capacity improvement of up to 128.6% in high-penetration scenarios (90% renewable), with average operational cost reductions of 22%. Voltage deviations are minimized to within ±5% of nominal levels, while energy losses are reduced by 18%. Scenario quality, evaluated using the Wasserstein metric, achieved convergence with an average score of 0.95 after 80 iterations, highlighting the WGAN’s ability to generate realistic and diverse scenarios. This study advances the state of the art in distribution network optimization by integrating machine learning techniques with robust mathematical modeling. The PPO-WGAN framework enhances scalability, ensures grid stability, and promotes efficient renewable integration, providing a robust foundation for future applications in modern power systems.

This study presents a novel sensitivity-driven distributionally robust optimization framework designed to enhance hosting capacity in renewable-powered distribution networks through targeted flexibility resource deployment. The proposed approach integrates temporal sensitivity mapping with robust optimization techniques to prioritize resource allocation across high-sensitivity nodes, addressing uncertainties in renewable energy generation and load demand. By leveraging a dynamic interaction between sensitivity scores and temporal system conditions, the framework achieves efficient and resilient operation under extreme variability scenarios. Key methodological innovations include the incorporation of a social force model-based sensitivity mapping technique, a layered optimization approach balancing system-wide and localized decisions, and a robust uncertainty set to safeguard performance against distributional shifts. The framework is validated using a synthesized test system, incorporating realistic renewable generation profiles, load patterns, and energy storage dynamics. Results demonstrate a significant improvement in hosting capacity, with system-wide enhancements of up to 35% and a 50% reduction in renewable curtailment. Moreover, sensitivity-driven resource deployment ensures efficient utilization of flexibility resources, achieving a peak allocation efficiency of 90% during critical periods. This research provides a comprehensive tool for addressing the challenges of renewable integration and grid stability in modern power systems, offering actionable insights for resource allocation strategies under uncertainty. The proposed methodology not only advances the state-of-the-art in sensitivity-based optimization but also paves the way for scalable, resilient energy management solutions in high-renewable penetration scenarios.