Random Forest Regressor-Based Approach for Detecting Fault Location and Duration in Power Systems

Abstract

Power system failures or outages due to short-circuits or “faults” can result in long service interruptions leading to significant socio-economic consequences. It is critical for electrical utilities to quickly ascertain fault characteristics, including location, type, and duration, to reduce the service time of an outage. Existing fault detection mechanisms (relays and digital fault recorders) are slow to communicate the fault characteristics upstream to the substations and control centers for action to be taken quickly. Fortunately, due to availability of high-resolution phasor measurement units (PMUs), more event-driven solutions can be captured in real time. In this paper, we propose a data-driven approach for determining fault characteristics using samples of fault trajectories. A random forest regressor (RFR)-based model is used to detect real-time fault location and its duration simultaneously. This model is based on combining multiple uncorrelated trees with state-of-the-art boosting and aggregating techniques in order to obtain robust generalizations and greater accuracy without overfitting or underfitting. Four cases were studied to evaluate the performance of RFR: 1. Detecting fault location (case 1), 2. Predicting fault duration (case 2), 3. Handling missing data (case 3), and 4. Identifying fault location and length in a real-time streaming environment (case 4). A comparative analysis was conducted between the RFR algorithm and state-of-the-art models, including deep neural network, Hoeffding tree, neural network, support vector machine, decision tree, naive Bayesian, and K-nearest neighborhood. Experiments revealed that RFR consistently outperformed the other models in detection accuracy, prediction error, and processing time.

Atmospheric Boundary Layer Wind Profile Estimation Using Neural Networks, Mesoscale Models, and LiDAR Measurements

“… Decision tree regressor [ 20 ]: a method based on questions that narrows or restricts the range of possible values for the predictions by splitting the data into subsets. Random forest regressor [ 21 ] is an ensemble-based regression that trains many individual, uncorrelated decision trees with small depth. The assumption underpinning this technique is that several low-complex decision trees result in a more robust and consistent model by averaging all the output predictors of their individual trees.…”

“…Random forest regressor [ 21 ] is an ensemble-based regression that trains many individual, uncorrelated decision trees with small depth. The assumption underpinning this technique is that several low-complex decision trees result in a more robust and consistent model by averaging all the output predictors of their individual trees.…”

Estimador de Fluxo em Tempo Real

“…Random Forest é um modelo baseado em árvores de decisão, utilizando um conjunto de árvores aleatórias com o objetivo de obter o melhor desempenho, onde o resultado em cada árvore será utilizada no resultado final [El Mrabet et al 2022]. O algoritmo busca as melhores decisões com os dados de treino e onde inseri-los dentro da estrutura, fazendo com que dada condic ¸ão se siga por um ramo ou por outro no caso contrário.…”

Compare Linear regression, Decision Tree Regressor, and Random Forest Regressor based on python, a restaurant company on Kaggle as a case

“…When applying the Random Forest Regressor to the field of renewable energy, the average prediction accuracy was about 93% [7]. Overall, the Random Forest Regression (RFR) model consistently outperforms other models and is well-suited for real-time situational awareness deployments that identify the location and duration of failures while addressing missing data [8].…”