Classification of smart grid stability prediction using cascade machine learning methods and the internet of things in smart grid

Önder, Mithat; Doğan, Muhsin Uğur; Polat, Kemal

doi:10.1007/s00521-023-08605-x

Cited by 11 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, random subspace ensemble methods are classification algorithms that create multiple subsets of the original feature set and train a classifier on each subset. The idea behind this approach is to reduce the variance of the classification model by introducing diversity among the classifiers ( Ho, 1998 ; Tremblay, Sabourin & Maupin, 2004 ; Demir, AM & Sengur, 2020 ), Önder, Dogan & Polat (2023) …”

Section: Methodsmentioning

confidence: 99%

A novel approach to recognition of Alzheimer’s and Parkinson’s diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image

Alhudhaif

2024

PeerJ Computer Science

View full text Add to dashboard Cite

Background Artificial intelligence technologies have great potential in classifying neurodegenerative diseases such as Alzheimer’s and Parkinson’s. These technologies can aid in early diagnosis, enhance classification accuracy, and improve patient access to appropriate treatments. For this purpose, we focused on AI-based auto-diagnosis of Alzheimer’s disease, Parkinson’s disease, and healthy MRI images. Methods In the current study, a deep hybrid network based on an ensemble classifier and convolutional neural network was designed. First, a very deep super-resolution neural network was adapted to improve the resolution of MRI images. Low and high-level features were extracted from the images processed with the hybrid deep convolutional neural network. Finally, these deep features are given as input to the k-nearest neighbor (KNN)-based random subspace ensemble classifier. Results A 3-class dataset containing publicly available MRI images was utilized to test the proposed architecture. In experimental works, the proposed model produced 99.11% accuracy, 98.75% sensitivity, 99.54% specificity, 98.65% precision, and 98.70% F1-score performance values. The results indicate that our AI system has the potential to provide valuable diagnostic assistance in clinical settings.

show abstract

Section: Methodsmentioning

confidence: 99%

A novel approach to recognition of Alzheimer’s and Parkinson’s diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image

Alhudhaif

2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…In several works, K-means algorithm [17] was applied to the simulated electrical grid data and identify a stable/unstable system in an unsupervised way. On the other hand, various supervised classification methods such as Decision Tree (DT) [22,33], Support Vector Machine (SVM) [29,12,25,28], Artificial A new optimized ELM method was proposed for power system transient stability prediction using synchrophasors Chen et al [9] A real-time transient stability status method was suggested based on CELM Zhou et al [10] A hierarchical method was represented for transient stability prediction based on the confidence of ensemble classifier using SVMs Malbasa et al [11] An AL technique was proposed for monitoring the voltage stability in transmission systems Echeverria et al [12] A methodology was designed for real-time transient stability of Electric Power Systems using predictive-SIME method Mahdi and Gene [13] An ANN-based methodology was proposed for predicting the power system stability directly after clearing the fault Arzamasov et al [14] Several data-mining methods had been used to solve fixed input and equality issues Gupta et al [15] A continuous OMS for power system had been implemented to predict stability based on PMU measurements at all the generator buses Zhou et al [16] A CNN ensemble method was proposed to generate the transient stability predictor from time series trajectories Barocio et al [17] An unsupervised method was used to identify coherent groups, detect disturbance events, and determine the stability of the system. Moldovan and Salomie [18] A machine learning methodology was proposed to predict smart grid stability using features extraction, selection, and classification Raz et al [19] A regression tree-based approach had been employed to predict the power system stability margin and detect impending system Zhu et al [20] A HDLM had been developed to efficiently both quantitative and qualitative online transient stability prediction Alazab et al [1] A MLSTM model had been designed to predict the stability of the smart grid network.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Mostafa et al [27] It develops a potential framework of big data analytics and renewable power utilities. Önder et al [28] It proposed five different cascade classifiers to classify smart grid data.…”

Section: Literature Reviewmentioning

confidence: 99%

Machine Learning Approaches To Predict The Stability of Smart Grid

Satu,

Khan

2024

Preprint

View full text Add to dashboard Cite

The smart grid is a modern solution to generate, distribute, and use energy effectively and efficiently. Ensuring the stability of the smart grid is critical to guarantee safe and consistent operation. This study proposes a machine learning model to identify smart grid stability more efficiently. To accomplish this, we collected the electrical grid stability dataset from a public machine learning repository and analyzed the correlation of individual features. Different feature selection and transformation techniques were employed to generate subsequent feature sets. Then, various classification techniques were applied to the primary and its subsets to identify the best machine-learning model for predicting smart grid stability more efficiently. The results indicated that MLP showed the highest accuracy (97.06%) for the Z-score transformed data set using Grid Search Optimization. This study demonstrates the potential of using machine learning to predict smart grid stability accurately and efficiently, providing a critical tool for improving the reliability, efficiency, and sustainability of the energy industry.

show abstract

“…Furthermore, the findings show that the suggested approach greatly lowers false positives and is feasible for real-time use. Önder et al [16], the authors applied cascading of ML algorithms and achieved good results. The results shown that cascade methods outperformed conventional ML methods.…”

Section: Introductionmentioning

confidence: 99%

An efficient smart grid stability prediction system based on machine learning and deep learning fusion model

Lakshmanarao,

Srisaila,

Srinivasa Ravi Kiran

et al. 2024

IJEECS

View full text Add to dashboard Cite

<span>A smart grid is a modern power system that allows for bidirectional communication, driven mostly by the idea of demand responsiveness. Predicting the stability of the smart grid is necessary for improving its dependability and maximizing the efficacy and regularity of electricity delivery. Predicting smart grid stability is difficult owing to the various elements that impact it, including consumer and producer engagement, which may contribute to smart grid stability. This research work proposes machine learning (ML) and deep learning (DL) approaches for predicting smart grid sustainability. Five ML algorithms, namely support vector machine (SVM), decision tree (DT), K-nearest neighbor (KNN), random forest (RF), and logistic regression (LR), were applied for the prediction of smart grid stability. Later, the stacking ensemble and voting ensemble of ML algorithms were also applied for prediction. To further increase accuracy, a novel fusion model with DL artifical neural networks (ANN) and ML SVM was applied and achieved an accuracy of 98.92%. The experiment results show that the proposed model outperformed existing models for smart grid stability prediction.</span>

show abstract

Classification of smart grid stability prediction using cascade machine learning methods and the internet of things in smart grid

Cited by 11 publications

References 50 publications

A novel approach to recognition of Alzheimer’s and Parkinson’s diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image

A novel approach to recognition of Alzheimer’s and Parkinson’s diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image

Machine Learning Approaches To Predict The Stability of Smart Grid

An efficient smart grid stability prediction system based on machine learning and deep learning fusion model

Contact Info

Product

Resources

About