PMU Based Data Driven Approach For Online Dynamic Security Assessment in Power Systems

Jaiswal, Prajwal Kumar; Das, Sayari; Panigrahi, Bijaya Ketan

doi:10.1109/isap48318.2019.9065968

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) The RF model with the current features is trained based on cross-validation, and the importance score of each feature and the performance evaluation index of the RF model are calculated. The RF model can measure the feature importance according to the Gini index or the error of the out-of-bag samples; the latter was chosen in this study (Jaiswal et al, 2019). The R-squared error (R 2 ) was chosen to evaluate the model performance, the value of R 2 was in the range (0, 1), and the model performed better when R 2 tended to 1 (Alimi et al, 2020).…”

Section: Feature Selection Based On the Rfecv Algorithmmentioning

confidence: 99%

“…Yun used the static voltage stability margin as a severity index of the possible state of a power system for voltage safety risk assessment and introduced a support vector machine (SVM) to achieve a rapid calculation of severity while optimizing the parameters of the SVM by the genetic algorithm (Yun et al, 2017). To improve the computational speed of the dynamic risk assessment of power systems, Jaiswal classified the contingencies into two categories, namely, security and insecurity, and trained a random forest (RF) with voltage magnitude and phase, current magnitude, real power, and reactive power as features and the contingency categories as labels (Jaiswal et al, 2019). Liu applied iterative random forests to calculate the severity of possible system states for dynamic security risk assessment of power systems (Liu et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online load-loss risk assessment based on stacking ensemble learning for power systems

Wang,

Sun,

Dan

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Power systems faces significant uncertainty during operation owing to the increased integration of renewable energy into power grids and the expansion of the scale of power systems, these factors lead to higher load-loss risks; therefore, realization of a fast online load-loss risk assessment is crucial to ensuring the operational safety and reliability of power systems. This paper presents an online load-loss risk assessment method for power systems based on stacking ensemble learning. First, a traditional load-loss risk assessment method based on power flow analysis was constructed to generate risk samples. The label of the sample is load-loss risk assessment index and the features are multiple operational variables of the power system. And the recursive feature elimination using cross validation (RFECV) was adopted for feature selection. Second, four different machine learning models, including support vector regression (SVR), extremely randomized trees (ET), extreme gradient boosting (XGBoost) and elastic network (EN) were used to form a stacking ensemble learning model for sample training. Moreover, to further improve the model performance, the particle swarm optimization (PSO) algorithms was used for parameter optimization. Finally, based on this model, the online load-loss risk assessment of a power system was realized. The application of the proposed method on IEEE test systems demonstrated that the proposed method was more accurate than methods based on individual machine learning models, from which the stacking was designed, while still maintaining a significant advantage in terms of runtime compared to the traditional risk assessment method.

show abstract

Section: Feature Selection Based On the Rfecv Algorithmmentioning

confidence: 99%