AI-Driven Terminal Access Optimization and Resource Allocation Model under High-Penetration of Renewable Energy

Against the backdrop of a high proportion of renewable energy being integrated into the power system, the dynamics of terminal device access and the uncertainty of energy supply pose severe challenges to traditional resource allocation mechanisms. This paper proposes a collaborative model for AI-driven terminal access optimization and resource allocation. By integrating deep reinforcement learning and a dynamic priority assessment mechanism, the model achieves adaptive access control of terminal devices and elastic allocation of computing resources in scenarios with distributed energy fluctuations. The model design adopts a hierarchical decision-making architecture. The upper layer predicts the supply – demand status of regional renewable energy based on the LSTM network, while the lower layer dynamically adjusts the terminal access strategy and resource allocation weights through a multi – agent collaborative algorithm. Simulation experiments based on the NREL renewable energy dataset show that in scenarios where the fluctuation amplitude of wind and solar power output exceeds 40%, compared with traditional heuristic algorithms, this model can increase resource utilization by 22.1%, raise the task completion rate to 93.7%, and keep the decision – making delay stable within the 200ms threshold.