A physical mechanism enabled neural network for power system dynamic security assessment

Data-driven artificial intelligence technologies have become increasingly interesting tools in power system security assessment. However, their inherent mechanism of inexplicability and unreliability now limits their scalability in power systems. To address this problem, this paper proposes a neural network design method empowered by physical mechanisms for power system security assessment. It incorporates the geometric characteristics of dynamic security regions into the network training process and constructs the connection between the network structure and the system's unstable mode, which can perform security assessment with a neural network efficiently while ensuring physical plausibility. Furthermore, a credibility evaluation mechanism is established to ensure the credibility of the neural network predictions and reduce misclassifications. Finally, the effectiveness of the proposed method is verified on test systems. The methods and considerations in building a neural network with interpretable structures and credible predictions can provide a reference for machine intelligence applied in other industrial systems.