Three-phase congestion prediction utilizing artificial neural networks

Fainti, Rafik; Alamaniotis, Miltiadis; Tsoukalas, Lefteri H.

doi:10.1109/iisa.2016.7785422

Cited by 9 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another aproach is to use ANN for congestion prediction in electricity grids. Fainti et al used an ANN trained by the Levenberg-Marqardt algorithm with implemented Bayesian regularization in order to predict congestion on each of the three phases of a power distribution line [19]. Alali et al trained two ANNs to get the probability of a congested line in the first model (using complex bus voltage, bus active-and reactive power) and the source of congestion (the causing bus) in the second one [20].…”

Section: Introductionmentioning

confidence: 99%

“…In order to predict possible congestions occuring in the distribution grid, injections into grid also have to be predicted. The injections can be simulated by modeling RE injection and load separately [18], using meteorological information and information about consumption for phase prediction [19]. Focusing on congestion prediction in [20] they used active and reactive power of each bus as input features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Renewable Curtailment in Distribution Grids Using Neural Networks

Memmel¹,

Steens²,

Schlüters³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The growing integration of renewable energies into electricity grids leads to an increase of grid congestions. One countermeasure is the curtailment of renewable energies, which has the disadvantage of wasting energy. Forecasting congestion provides valuable information for grid operators to prepare and instruct countermeasures to reduce these energy losses. This paper presents a novel approach for congestion prediction in distribution grids (i.e. up to 110 kV) considering the n-1 security criterion. For this, our method considers node injections and power flow and combines three artificial neural network models. The analysis of study results shows that the implemented neural networks within the presented approach perform better than naive forecasts models. In the case of vertical power flow, the artificial neural networks also show better results than comparable parametric models: average values of the mean absolute errors relative to the parametric models range from 0.89 to 0.21. A high level of accuracy can be achieved for the neural network that predicts the loading of grid components with a F1 score of 0.92. Further, also with a F1 score of 0.92, this model shows higher accuracy for the distribution grid components than for those of the transmission grid, which achieve a F1 score of 0.84. The presented approaches show good potential to support grid operators in congestion management.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting Renewable Curtailment in Distribution Grids Using Neural Networks

Memmel¹,

Steens²,

Schlüters³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The aim of this study, which is actually an extension of the work in (Fainti et al, 2016), is to develop a method for accurate ampacity level predictions with the ultimate goal and effort to be towards accurate line overloading predictions ahead of time. Monitoring of the ampacity level and a precise indication about high risk time periods where may occur is of high importance.…”

mentioning

confidence: 99%

Backpropagation Neural Network for Interval Prediction of Three-Phase Ampacity Level in Power Systems

Tsoukalas

Alamaniotis

Fainti

2016

International Journal of Monitoring and Surveillance Technologies Research

Self Cite

View full text Add to dashboard Cite

The modern way of living depends on a very high degree on electricity utilization. People take for granted that their energy needs will be satisfied 24/7 which mandates the maintaining of the power grid in stable state. To that end, the development of precise methods for monitoring and predicting events that might disturb its uninterrupted operation is immense. Moreover, the evolvement of power grids into smart grids where the end users continuously participate in the power market by forming energy prices and/or by adjusting their energy needs according to their own agenda, adds high volatility to load demand. In that sense, with regard to predictive methods, a plain single point prediction application may not be enough. The aim of this study is to develop and evaluate a method in order to further enhance this type of applications by providing Predictive Intervals (PIs) regarding ampacity overloading in smart power systems through the use of Artificial Neural Networks (ANNs).

show abstract