Power System Transient Stability Assessment Using Stacked Autoencoder and Voting Ensemble

Abstract

Increased integration of renewable energy sources brings new challenges to the secure and stable power system operation. Operational challenges emanating from the reduced system inertia, in particular, will have important repercussions on the power system transient stability assessment (TSA). At the same time, a rise of the “big data” in the power system, from the development of wide area monitoring systems, introduces new paradigms for dealing with these challenges. Transient stability concerns are drawing attention of various stakeholders as they can be the leading causes of major outages. The aim of this paper is to address the power system TSA problem from the perspective of data mining and machine learning (ML). A novel 3.8 GB open dataset of time-domain phasor measurements signals is built from dynamic simulations of the IEEE New England 39-bus test case power system. A data processing pipeline is developed for features engineering and statistical post-processing. A complete ML model is proposed for the TSA analysis, built from a denoising stacked autoencoder and a voting ensemble classifier. Ensemble consist of pooling predictions from a support vector machine and a random forest. Results from the classifier application on the test case power system are reported and discussed. The ML application to the TSA problem is promising, since it is able to ingest huge amounts of data while retaining the ability to generalize and support real-time decisions.

Artificial Intelligence Techniques for Power System Transient Stability Assessment

“…Transmission lines (TLs) are modeled as three-phase Π-section blocks. A high level of familiarity with MATLAB/ Simulink is a prerequisite for composing and working with these power system models [16].…”

“…Hence, using parallel and multiprocessing capabilities has been explored to reduce the run times needed for creating these datasets. A number of papers have proposed different parallel execution models for reducing the simulation run times [16,23]. Furthermore, the authors in [24] proposed a synthetic synchrophasor generated data as a replacement for real-time PMU measurements.…”

“…Hang et al employed principal component analysis [28]. Several papers proposed different kinds of autoencoders (stacked, denoising, variational), e.g., [8,16,29,30]. Mi et al in [22] proposed a special bootstrap method and the random selection of variables in the training process for tackling the curse of dimensionality.…”

“…These data need to be processed by means of a previously discussed pipeline. Figure 5 graphically presents an example of a data processing pipeline for power system transient assessment data coming from simulations of a benchmark test case [16]. It features statistical processing of systematic simulations data, followed by the train/test dataset split and data scaling process, and concluded with a dimensionality reduction.…”

A Critical Review of Data-Driven Transient Stability Assessment of Power Systems: Principles, Prospects and Challenges

“…The key idea of ensemble learning is to combine multiple learners into an algorithm model with stronger generalization performance by combining strategies. To analyze transient stability problems, a complete machine learning-based TSA model is proposed for TSA by using a denoising stacked autoencoder and a voting ensemble classifier [35]. A variational Bayes multiple kernel learning (VBpMKL)-based TSA model is built using multi-feature fusion through combining feature spaces corresponding to each feature subset, it can improve the accuracy and reliability of classification [36].…”