Low frequency oscillations (LFOs) in power systems usually fall into two types, i.e., forced oscillations and natural oscillations. Waveforms of the two are similar, but the suppression methods are different. Therefore, it is important to accurately identify LFO type. In this paper, a method for discriminating LFO type based on multi-dimensional features and a feature selection algorithm combining ReliefF and minimum redundancy maximum relevance algorithm (mRMR) is proposed. Firstly, 53 features are constructed from six aspects—time domain, frequency domain, energy, correlation, complexity, and modal analysis—which comprehensively characterize the multidimensional features of LFO. Then, the optimal feature subset with greater relevance and less redundancy is extracted by ReliefF-mRMR. In order to improve the classification performance, a modified Support Vector Machine (SVM) with Genetic Algorithm (GA) optimizing the key parameters is adopted, which is conducted in MATLAB. Finally, in 179-bus system, the samples of LFOs are generated by the Power System Analysis Toolbox (PSAT) and the accuracy of the LFO type identification model is verified. In ISO New England and East China power grid, it is proven that the proposed method can accurately identify LFO type considering the influences of noise, oscillation mode, and data incompletion. Hence, it has good robustness, noise immunity, and practicability.
Detection of Periodic Forced Oscillations in Power Systems Using Multitaper Approach
