scholarly journals Voltage-Based Load Recognition in Low Voltage Distribution Grids with Deep Learning

Energies ◽  
2021 ◽  
Vol 15 (1) ◽  
pp. 104
Author(s):  
Henning Schlachter ◽  
Stefan Geißendörfer ◽  
Karsten von Maydell ◽  
Carsten Agert
Keyword(s):  
Deep Learning ◽  
Low Voltage ◽  
Control Strategies ◽  
Training Data ◽  
Grid Environment ◽  
Voltage Level ◽  
Grid Connection ◽  
Local Grid ◽  
Electric Loads ◽  
Distribution Grids

Due to the increasing penetration of renewable energies in lower voltage level, there is a need to develop new control strategies to stabilize the grid voltage. For this, an approach using deep learning to recognize electric loads in voltage profiles is presented. This is based on the idea to classify loads in the local grid environment of an inverter’s grid connection point to provide information for adaptive control strategies. The proposed concept uses power profiles to systematically generate training data. During hyper-parameter optimizations, multi-layer perceptron (MLP) and convolutional neural networks (CNN) are trained, validated, and evaluated to determine the best task configurations. The approach is demonstrated on the example recognition of two electric vehicles. Finally, the influence of the distance in a test grid from the transformer and the active load to the measurement point, respectively, onto the recognition accuracy is investigated. A larger distance between the inverter and the transformer improved the recognition, while a larger distance between the inverter and active loads decreased the accuracy. The developed concept shows promising results in the simulation environment for adaptive voltage control.

scholarly journals Integrated Algorithm for Selecting the Location and Control of Energy Storage Units to Improve the Voltage Level in Distribution Grids

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6720
Author(s):  
Agata Szultka ◽  
Seweryn Szultka ◽  
Stanislaw Czapp ◽  
Zbigniew Lubosny ◽  
Robert Malkowski
Keyword(s):  
Energy Storage ◽  
Reactive Power ◽  
Low Voltage ◽  
Renewable Energy Sources ◽  
Energy Sources ◽  
Voltage Level ◽  
Simple Description ◽  
And Control ◽  
Distribution Grids ◽  
Storage Units

This paper refers to the issue that mainly appears in distribution grids, where renewable energy sources (RES) are widely installed. In such grids, one of the main problems is the coordination of energy production time with demand time, especially if photovoltaic energy sources are present. To face this problem, battery energy storage units (ESU) can be installed. In recent years, more and more attention has been paid to optimizing the use of ESU. This paper contains a simple description of available solutions for the application of ESU as well as an original proposal for selecting the optimal location and control of ESU. The ESU selection method is based on the use of a genetic algorithm and the ESU control method utilizes the fuzzy logic. The combination of the aforementioned methods/algorithms of ESU application is named an integrated algorithm. The performance of the proposed algorithm was validated by multivariate computer simulations with the use of the real low-voltage grid model. The DIgSILENT PowerFactory environment was employed to develop the simulation model of the integrated algorithm. The proposal was utilized to improve the voltage level in the distribution grid and to install the optimal number of ESU. Based on daily load variations for selected load profiles, it was shown that after the ESU application the voltage deviations in the analyzed network were significantly limited. Moreover, the analysis proves that both the location of ESU in the grid and the control of their active and reactive power are important from the point of view of reducing overall costs.

scholarly journals Siamese Reconstruction Network: Accurate Image Reconstruction from Human Brain Activity by Learning to Compare

2019 ◽  
Vol 9 (22) ◽  
pp. 4749
Author(s):  
Lingyun Jiang ◽  
Kai Qiao ◽  
Linyuan Wang ◽  
Chi Zhang ◽  
Jian Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Human Brain ◽  
Brain Activity ◽  
Feature Space ◽  
Training Data ◽  
Reconstruction Method ◽  
Learning Method ◽  
Training Samples ◽  
Visual Reconstruction ◽  
Relationship Of

Decoding human brain activities, especially reconstructing human visual stimuli via functional magnetic resonance imaging (fMRI), has gained increasing attention in recent years. However, the high dimensionality and small quantity of fMRI data impose restrictions on satisfactory reconstruction, especially for the reconstruction method with deep learning requiring huge amounts of labelled samples. When compared with the deep learning method, humans can recognize a new image because our human visual system is naturally capable of extracting features from any object and comparing them. Inspired by this visual mechanism, we introduced the mechanism of comparison into deep learning method to realize better visual reconstruction by making full use of each sample and the relationship of the sample pair by learning to compare. In this way, we proposed a Siamese reconstruction network (SRN) method. By using the SRN, we improved upon the satisfying results on two fMRI recording datasets, providing 72.5% accuracy on the digit dataset and 44.6% accuracy on the character dataset. Essentially, this manner can increase the training data about from n samples to 2n sample pairs, which takes full advantage of the limited quantity of training samples. The SRN learns to converge sample pairs of the same class or disperse sample pairs of different class in feature space.

scholarly journals Domain randomization-enhanced deep learning models for bird detection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Mao ◽  
Jun Kang Chow ◽  
Pin Siang Tan ◽  
Kuan-fu Liu ◽  
Jimmy Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continuous Monitoring ◽  
Bird Species ◽  
Training Data ◽  
Learning Models ◽  
Fine Grained ◽  
Bird Detection ◽  
Relationship Of ◽  
The Relationship

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

scholarly journals U-Infuse: Democratization of Customizable Deep Learning for Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2611
Author(s):  
Andrew Shepley ◽  
Greg Falzon ◽  
Christopher Lawson ◽  
Paul Meek ◽  
Paul Kwan
Keyword(s):  
Deep Learning ◽  
Intellectual Property ◽  
Object Detection ◽  
Image Data ◽  
Learning Technologies ◽  
Training Data ◽  
Learning Models ◽  
Ecological Data ◽  
Single Class ◽  
Large Numbers

Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. Thus, there is a strong need to democratize access to deep learning technologies by providing an easy-to-use software application allowing non-technical users to train custom object detectors. U-Infuse addresses this issue by providing ecologists with the ability to train customised models using publicly available images and/or their own images without specific technical expertise. Auto-annotation and annotation editing functionalities minimize the constraints of manually annotating and pre-processing large numbers of images. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and object detection, allowing ecologists to access deep learning technologies usually only available to computer scientists, on their own device, customised for their application, without sharing intellectual property or sensitive data. It provides ecological practitioners with the ability to (i) easily achieve object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. Broad adoption of U-Infuse by ecological practitioners will improve ecological image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources, particularly for camera trap images. Ease of training and use of transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

Sign in / Sign up

Export Citation Format

Share Document