Automatic reactive power and voltage control for regional power grid based on SVM

Meng, Xuan; Sun, Geng; Li, Jianxiang; Liu, Haibo

doi:10.1109/tencon.2013.6718482

Cited by 2 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike similarity-based methods, the model-based methods are not to find a suitable historical dispatching strategy, but to create a new one for the current case. Specifically, supportive vector machine (SVM) is a supervised learning method for reactive power optimization by constructing a decision surface, where the difference between two different classes can be maximized [16]. MLP, DBN, and CNN construct neural networks using dense layers, restricted Boltzmann machines, and convolutional layers, respectively, to represent the relationship between power loads and dispatching strategies.…”

Section: Nomenclature δ Ijmentioning

confidence: 99%

Data-driven Reactive Power Optimization for Distribution Networks Using Capsule Networks

Liao

Chen

Liu

et al. 2022

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

The construction of advanced metering infrastructure and the rapid evolution of artificial intelligence bring opportunities to quickly searching for the optimal dispatching strategy for reactive power optimization. This can be realized by mining existing prior knowledge and massive data without explicitly constructing physical models. Therefore, a novel datadriven approach is proposed for reactive power optimization of distribution networks using capsule networks (CapsNet). The convolutional layers with strong feature extraction ability are used to project the power loads to the feature space to realize the automatic extraction of key features. Furthermore, the complex relationship between input features and dispatching strategies is captured accurately by capsule layers. The back propagation algorithm is utilized to complete the training process of the CapsNet. Case studies show that the accuracy and robustness of the CapsNet are better than those of popular baselines (e.g., convolutional neural network, multi-layer perceptron, and casebased reasoning). Besides, the computing time is much lower than that of traditional heuristic methods such as genetic algorithm, which can meet the real-time demand of reactive power optimization in distribution networks.

show abstract

Section: Nomenclature δ Ijmentioning

confidence: 99%

Data-driven Reactive Power Optimization for Distribution Networks Using Capsule Networks

Liao

Chen

Liu

et al. 2022

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

show abstract

A novel SVM voltage supervisor

Rodriguez-Garcia

Rizo-Dominguez

2021

2021 IEEE 12th Annual Ubiquitous Computing, Electronics &Amp; Mobile Communication Conference (UEMCON)

View full text Add to dashboard Cite

Voltage supervisors ensure that an electronic system is turned off whenever the rail voltage drops below the threshold value. Common implementations rely on hard decisions to assert the system's reset; however, these schemes lack flexibility in configuration. In this paper, we introduce a soft-decision system using a machine learning algorithm called support vector machine (SVM). The proposed monitoring system's software is built on top of scikit-learn SVM libraries and experimentation was conducted in the Raspberry Pi 4 platform. Confusion matrix for the SVM model shows that the system will perform well on new and training data. Overall, the resulting system is configurable and, unlike other implementations, it can be trained in online and offline modes.

show abstract

Automatic reactive power and voltage control for regional power grid based on SVM

Cited by 2 publications

References 4 publications

Data-driven Reactive Power Optimization for Distribution Networks Using Capsule Networks

Data-driven Reactive Power Optimization for Distribution Networks Using Capsule Networks

A novel SVM voltage supervisor

Contact Info

Product

Resources

About