Data-driven prediction method for characteristics of voltage sag based on fuzzy time series

Wang, Ying; Yang, Min-hui; Zhang, Huaying; Wu, Xueke; Hu, Weisheng

doi:10.1016/j.ijepes.2021.107394

Cited by 12 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the duration of sag mainly depends on the setting value of the protection device [10], it is not predicted in this paper. It can be observed from Table A1 that there is a common input data attribute with a consistent description in the simulated and measured data.…”

Section: Model Parametersmentioning

confidence: 97%

“…[9], the authors used measured data to predict the voltage sag frequency index of non-monitoring points. The authors in [10] used homologous aggregation and fuzzy c-means theory to reduce the redundancy of the measured data and predict the residual voltage. The aforementioned prediction methods based on monitoring data need long monitoring times and low amounts of monitoring data, which lead to poor prediction accuracies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Residual Voltage Data-Driven Prediction Method for Voltage Sag Based on Data Fusion

et al. 2022

View full text Add to dashboard Cite

Voltage sag is the most serious power quality problem in the three-phase symmetrical power system. The influence of multiple factors on the voltage sag level and low computational efficiency also pose challenges to the prediction of residual voltage amplitude of voltage sag. This paper proposes a voltage sag amplitude prediction method based on data fusion. First, the multi-dimensional factors that influence voltage sag residual voltage are analyzed. Second, these factors are used as input, and a model for predicting voltage sag residual voltage based on data fusion is constructed. Last, the model is trained and debugged to enable it to predict the voltage sag residual voltage. The accuracy and feasibility of the method are verified by using the actual power grid data from East China.

show abstract

Section: Model Parametersmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

A Residual Voltage Data-Driven Prediction Method for Voltage Sag Based on Data Fusion

et al. 2022

View full text Add to dashboard Cite

show abstract

“…They modeled the measured events (from 2005 -01 to 2008 -06) as an advanced fuzzy time series. Recently in the literature, data-driven approaches based on the Hidden Markov Model (HMM) proposed to address different forecast problems related to voltage sags in an electric system rather than at only one site [14,15]. An HMM is a statistical model used to describe a sequence of observations in which the underlying system state is hidden and can only be inferred through observations.…”

Section:  mentioning

confidence: 99%

“…The measured sags data were modeled as fuzzy time series in [15], and the sag prediction was based on a singlelayer HMM to describe the relationship between the observed electrical states (i.e., the voltage sags), and the hidden states (i.e., disturbance factors). Sags were forecasted at one site and at 23 sites, respectively using the measurements for one year and two consecutive years.…”

Section:  mentioning

confidence: 99%

Measured Rare Voltage Sags and Clusters of Sags: Prediction Models Driven by the Intermittence Indices

Casolino,

de Santis,

Di Stasio

et al. 2024

IEEE Open J. Power Energy

View full text Add to dashboard Cite

The field measurement campaigns have revealed that voltage sags also occur as clusters and not only as rare phenomena. The clusters of sags represent a stochastic process due to their time dependence; the rare satisfy the requirements for a Poisson distribution process. To forecast both kinds of sags using the statistics of the measurements, different approaches are required. In this study, a general method for predicting both types of sags is proposed with a procedure that can be implemented automatically. The method uses intermittent indices to distinguish between the sites that have a prevalent number of rare sags and the sites where rare sags and clusters occurred. Based on this means of identification, the technique offers two distinct models for predicting each kind of sag. The final goal is to implement the procedure in a measurement system that can automatically pre-analyze the recorded sags and choose the best technique for prediction depending on the type of sag. The first results were satisfying with forecast errors reduced in comparison with those obtained without the proposed procedure.

show abstract

“…The learning rate is a hyperparameter that controls the degree to which the model is changed according to the estimated error each time the model weight is updated [38,39]. An appropriate learning rate is essential to find the optimal weights of the model [40].…”

Section: Learning Ratementioning

confidence: 99%

Time Series Forecasting Fusion Network Model Based on Prophet and營mproved LSTM

Liu¹,

Yu²,

Zhao³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Time series forecasting and analysis are widely used in many fields and application scenarios. Time series historical data reflects the change pattern and trend, which can serve the application and decision in each application scenario to a certain extent. In this paper, we select the time series prediction problem in the atmospheric environment scenario to start the application research. In terms of data support, we obtain the data of nearly 3500 vehicles in some cities in China from Runwoda Research Institute, focusing on the major pollutant emission data of non-road mobile machinery and high emission vehicles in Beijing and Bozhou, Anhui Province to build the dataset and conduct the time series prediction analysis experiments on them. This paper proposes a P-gLSTNet model, and uses Autoregressive Integrated Moving Average model (ARIMA), long and short-term memory (LSTM), and Prophet to predict and compare the emissions in the future period. The experiments are validated on four public data sets and one self-collected data set, and the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) are selected as the evaluation metrics. The experimental results show that the proposed P-gLSTNet fusion model predicts less error, outperforms the backbone method, and is more suitable for the prediction of time-series data in this scenario.

show abstract

Data-driven prediction method for characteristics of voltage sag based on fuzzy time series

Cited by 12 publications

References 32 publications

A Residual Voltage Data-Driven Prediction Method for Voltage Sag Based on Data Fusion

A Residual Voltage Data-Driven Prediction Method for Voltage Sag Based on Data Fusion

Measured Rare Voltage Sags and Clusters of Sags: Prediction Models Driven by the Intermittence Indices

Time Series Forecasting Fusion Network Model Based on Prophet and營mproved LSTM

Contact Info

Product

Resources

About