Equivalent Inertia Estimation Method in New Power System Based on DTW and CNN-BiLSTM

With the access of a high proportion of renewable energy units to the power grid, the equivalent inertia of the power system continues to decrease, and the frequency stability of the system is seriously deteriorated. To this end, this paper proposes a new power system equivalent inertia estimation method based on dynamic time warping (DTW) and convolutional neural network and bi-directional long short-term memory network (CNN-BiLSTM). Firstly, a system equivalent inertia estimation model based on CNN-BiLSTM is established. The model integrates the spatial feature extraction capability of CNN and the temporal feature extraction capability of BiLSTM to improve the accuracy of inertia estimation. In addition, in order to select buses that can characterize the system frequency, a frequency difference index algorithm based on dynamic time warping is proposed. The bus with the minimum frequency difference is taken as the system frequency bus, and the system equivalent inertia is estimated based on the frequency data of the bus. Finally, the effectiveness of the proposed method is verified by building an improved IEEE 39-bus system model. The results show that the proposed method has a high equivalent inertia estimation accuracy.