Online prediction and active control of regional transient frequency security of interconnected system based on model-data driven method

With the expansion of power grid scale, the online prediction and control of transient frequency is very important for the system security. Some known and unknown factors are ignored in traditional prediction analysis methods based on physical model, which leads to the inevitable error in calculation results. This paper proposes a model-data integration driven method for transient frequency prediction. In the model part, a multi region frequency response model was established, and the disturbance region was considered as the weak link of system frequency variation from the spatial dimension. In the data-driven part, the long short-term memory network based on particle swarm optimization is used to obtain the error between the calculated results of the model-based method and the truth value, and the model-based method and the data-driven method are integrated through the parallel mode. The final transient frequency security indicators result is the superposition of the calculated results of the two methods. Based on the TFSI prediction results, an active load shedding control strategy was constructed, which can act before the traditional load shedding frequency threshold. The performance of TFSI prediction and active load shedding control was verified on the modified New England 10-generator 39-bus system and 197-bus system in China. The TFSI prediction results show that the proposed method is more accurate and faster than other integration methods, and it is robust in both data loss and unknown scenarios. And, the constructed active load shedding control strategy has better frequency dynamics compared to traditional load shedding strategies based on fixed frequency thresholds.