The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations

Carbonera, Luis Felipe Bianchi; Bernardon, Daniel Pinheiro; Karnikowski, Douglas de Castro; Farret, Felix A.

doi:10.1002/2050-7038.12538

Cited by 8 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an alternative approach, the researchers presented numerous innovative PSS structures to increase power system stability, such as multi-input PSS [32], fuzzy logic-based PID PSS [33],multi-band PSS [34], Decentralized nonlinear model predictive control [35], a nonlinear autoregressive model with exogenous input neural network [36]. In comparison to the power system stabilizer, these proposed approaches have proved the ability to dampen power system oscillations.…”

Section: B Literature Reviewmentioning

confidence: 99%

Optimal Tuning of Power System Stabilizers for a Multi-Machine Power Systems Using Hybrid Gorilla Troops and Gradient-Based Optimizers

et al. 2023

View full text Add to dashboard Cite

This work discusses the production of a novel hybrid algorithm by combining the gorilla troops optimizer (GTO) with the gradient-based optimizers (GBO) approach. The novel approach is called GTO-GBO, it is offered as a useful tool for optimizing the power system stabilizer (PSS) used in the IEEE four-generator, two-area multi-machine power system subjected to a three-phase short-circuit fault. MATLAB/Simulink software was utilized to carry out the assessments. The suggested approach is initially evaluated using multiple benchmark functions with unimodal and multimodal properties. The results are then compared to other competing algorithms (artificial ecosystem optimizer, artificial rabbits optimizer, Coati Optimization Algorithm, and northern goshawk optimization). The comparisons with various algorithms reveal the developed hybrid GTO-GBO algorithm's considerable promise. This demonstrates the GTO-GBO algorithm's improved balance of global and local search stages. The proposed GTO-GBO algorithm's performance is also evaluated by developing an optimum performing PSS for further examination, allowing observation of its capabilities for difficult real-world engineering challenges. To illustrate the applicability and superior performance of the suggested hybrid algorithm for such a complicated real-world engineering problem, the PSS damping controller is formulated as an optimization problem, and the developed GTO-GBO algorithm is used to search for optimal controller parameters. The latter case's findings are compared to the competitive optimization algorithms where the GTO-GBO demonstrates the efficiency and robustness of this suggested optimization algorithm to enhance power system stability.

show abstract

Section: B Literature Reviewmentioning

confidence: 99%

Optimal Tuning of Power System Stabilizers for a Multi-Machine Power Systems Using Hybrid Gorilla Troops and Gradient-Based Optimizers

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The network consists of recurrent feedback from other network layers and is used in the input layer. An in-depth explanation of the network can be found in [72]. Like the ARIMA model, NARX was also applied to establish a baseline performance for the proposed model.…”

Section: Prediction Of Waste Generation Using Narx Modelmentioning

confidence: 99%

An Ensemble Learning Based Classification Approach for the Prediction of Household Solid Waste Generation

Namoun

Tufail

Alrehaili

et al. 2022

Sensors

View full text Add to dashboard Cite

With the increase in urbanization and smart cities initiatives, the management of waste generation has become a fundamental task. Recent studies have started applying machine learning techniques to prognosticate solid waste generation to assist authorities in the efficient planning of waste management processes, including collection, sorting, disposal, and recycling. However, identifying the best machine learning model to predict solid waste generation is a challenging endeavor, especially in view of the limited datasets and lack of important predictive features. In this research, we developed an ensemble learning technique that combines the advantages of (1) a hyperparameter optimization and (2) a meta regressor model to accurately predict the weekly waste generation of households within urban cities. The hyperparameter optimization of the models is achieved using the Optuna algorithm, while the outputs of the optimized single machine learning models are used to train the meta linear regressor. The ensemble model consists of an optimized mixture of machine learning models with different learning strategies. The proposed ensemble method achieved an R2 score of 0.8 and a mean percentage error of 0.26, outperforming the existing state-of-the-art approaches, including SARIMA, NARX, LightGBM, KNN, SVR, ETS, RF, XGBoosting, and ANN, in predicting future waste generation. Not only did our model outperform the optimized single machine learning models, but it also surpassed the average ensemble results of the machine learning models. Our findings suggest that using the proposed ensemble learning technique, even in the case of a feature-limited dataset, can significantly boost the model performance in predicting future household waste generation compared to individual learners. Moreover, the practical implications for the research community and respective city authorities are discussed.

show abstract

“…The NARX method is applied to model this compressor. The NARX network models the discrete nonlinear system by applying both the delayed input and output data [33, 34]. Compressor identification in NARX structure is determined using the overall structure expressed as follows:

\begin{matrix} right center left3pttrue \\ y (t) & = & f true(y (t goodbreak- 1) true, y (t goodbreak- 2) true, \dots true, y (t goodbreak- d_{y}) true, x (t) true, \\ left x (t goodbreak- 1) true, x (t goodbreak- 2) true, . \dots true, x (t goodbreak- d_{x}) true) \end{matrix}

where x and y are the input and output vectors of the system, respectively, and the and dx and dy are the time delays of the network at the input and output, respectively.…”

Section: Compressor Narx Modelingmentioning

confidence: 99%

“…The NARX method is applied to model this compressor. The NARX network models the discrete nonlinear system by applying both the delayed input and output data [33,34]. Compressor identification in NARX structure is determined using the overall structure expressed as follows:…”

Section: Compressor Narx Modelingmentioning

confidence: 99%

System identification using NARX and centrifugal compressor control through the intelligent, active method—Case study: K‐250 centrifugal compressor

Khosravi

Chatraei

Shahgholian

et al. 2022

Asian Journal of Control

View full text Add to dashboard Cite

Surge and constant pressure are some of the most critical issues in compressor control. In this paper, the problem of the surge and constant pressure in the presence of environmental disturbances is solved. Proposed design for control system based on proportional-integral controllers, adaptive neuro-fuzzy inference system (FIS), and particle swarm optimized neural fuzzy and for modeling neural network strategy fuzzy nonlinear automatic regression with external input is used. Based on this, for modeling, practical and real data are extracted from the K-250 compressor of Isfahan Steel Company. In the adaptive neuro-fuzzy inference system-particle swarm optimization (ANFIS-PSO)

show abstract

The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations

Cited by 8 publications

References 27 publications

Optimal Tuning of Power System Stabilizers for a Multi-Machine Power Systems Using Hybrid Gorilla Troops and Gradient-Based Optimizers

Optimal Tuning of Power System Stabilizers for a Multi-Machine Power Systems Using Hybrid Gorilla Troops and Gradient-Based Optimizers

An Ensemble Learning Based Classification Approach for the Prediction of Household Solid Waste Generation

System identification using NARX and centrifugal compressor control through the intelligent, active method—Case study: K‐250 centrifugal compressor

Contact Info

Product

Resources

About