An Optimization Method for Coordinated Preventive Control of Transient and Small-Signal Stability Based on CNN

An optimization method for coordinated preventive control of transient and small-signal stability based on convolutional neural network (CNN) sensitivity analysis was presented in the paper to improve the developing speed of preventive control measures. For transient instability situation and poor or negative damping low frequency oscillation modes (.i.e., the damping ratios were less than a threshold), first, an optimization model with transient and small-signal stability constraints was established; second, the sensitivities of the critical clearing time (CCT) and the damping ratios to control variables (the active power of adjustable generators) were calculated based on CNN models of CCT and damping ratio prediction and then a quadratic programming model was obtained by linearizing the constraints through sensitivities; finally, the adjustment amounts of generator active power were obtained by solving the quadratic programming model. Several iterations were needed to make the CCT and damping ratios meet specific requirements. Analysis results of CEPRI 36-bus case showed that the effective control measures can be obtained by the presented method.