A Super-resolution Perception-based Incremental Learning Approach for Power System Voltage Stability Assessment with Incomplete PMU Measurements

This paper develops a fully data-driven, missing-data tolerant method for post-fault short-term voltage stability (STVS) assessment of power systems against the incomplete PMU measurements. The super-resolution perception (SRP), based on a deep residual learning convolutional neural network, is employed to cope with the missing PMU measurements. The incremental broad learning (BL) is used to rapidly update the model to maintain and enhance the online application performance. Being different from the state-of-the-art methods, the proposed method is fully data-driven and can fill up missing data under any PMU placement information loss and network topology change scenario. Simulation results demonstrate that the proposed method has the best performance in terms of STVS assessment accuracy and missing-data tolerance among the existing methods on the benchmark testing system.

Automated summary

This paper presents a fully data-driven method for short-term voltage stability assessment of power systems with incomplete PMU measurements. The method uses a deep learning convolutional neural network to handle missing PMU measurements and employs incremental learning to update the model for better online performance. Unlike existing methods, this approach can fill missing data under various scenarios of PMU placement information loss and network topology changes. Simulation results demonstrate that the proposed method outperforms other methods in terms of accuracy and tolerance to missing data in STVS assessment.