In the process of achieving the "dual carbon" strategic goals, low-carbon parks have become typical demonstration scenarios for efficient energy utilization and digital operation. As the core of energy management in the park, the main station system undertakes critical data exchange and control tasks. The security and operational efficiency of its identity authentication mechanism directly affect the stable operation of the entire system. Therefore, this article constructs a low-carbon park main station access identity authentication model based on deep belief networks. This model combines unsupervised feature extraction with supervised parameter tuning to improve the accuracy of identity recognition; Simultaneously adopting a lightweight structural design to reduce overall computational overhead. Experimental verification shows that the proposed model achieves better performance than traditional methods in multiple key indicators such as feature fusion, anomaly recognition, and energy consumption control.
Yin et al. (Thu,) studied this question.