Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
32
datasets available to search
ShareScore release 0.7.1
Dataset results
32 results for “substation”
High-Voltage Disconnector State Identification: synthetic and real images of substation disconnectors
<p>This dataset contains the training and test images used in the work detailed in the article: Barpp Gomes, V., Marchesi, B., Gruber, Y.A. <em>et al.</em> Exploring Synthetic Data for Training Deep Learning Models for High-Voltage Disconnector State Identification. <em>J Control Autom Electr Syst</em> (2025). <a href="https://doi.org/10.1007/s40313-025-01204-2">https://doi.org/10.1007/s40313-025-01204-2</a></p> <p>Contais about 940,000 synthetic (CGI-rendered) and 60,000 real (camera-captured) samples of four types of substation disconnectors, on both open and closed states:</p> <ul> <li>230 kV center break (type 1, as indicated in the article);</li> <li>230 kV center break (type 2);</li> <li>230 kV double side break</li> <li>525 kV horizontal semi-pantograph</li> </ul> <p>Each zip file contains images of one type of substation disconnector. Images are sized 320x128 and are organized in folders, as follows:</p> <ul> <li>00_train_synth: Synthetic training images.</li> <li>01_train_real: A small set of real training images, as indicated in the article.</li> <li>02_test_real_normal1: One set of real test images.</li> <li>03_test_real_normal2: Another set of real test images, from a different time period.</li> <li>04_test_real_maneuvers: A special set of real test images in which the switches have been operated (are in different states).</li> </ul>
CROSSBOW HLU2-UC4-TC4 Simulated curtailments at Konjsko substation
<p>For the evaluation of the curtailment distribution algorithm, an experiment was made with the forecast generation from TS Konjsko and the simulation of 30 limitations applied on random days.</p>
CROSSBOW HLU2-UC1-TC1 measurements: Substation measurements gathered during curtailment activation
<p>The data comprises the measurements read at the Konjsko substation before, during and after a curtailment in Pometeno Brno plant.</p> <p>The measurements gathered from the SCADA are:</p> <ul> <li>P, Q and V of the 110, 220 and 400 Kv buses at the substation</li> </ul> <p>P, Q and V of the line connecting the substation with the plant</p>
Great Britain's primary substation service areas and annual domestic energy statistics
<p>This geospatial data is a combination of Great Britain's 4436 primary substation service areas which have been parsed into a single shapefile for energy systems analysis. The original component datasets were provided by the six distribution network operator (DNO) companies in Great Britain (National Grid Electricity Distribution, Electricity North West Ltd, Scottish and Southern Electricity Networks, UK Power Networks, Scottish Power Energy Networks and Northern Power Grid). Attribution is given to the original data owners at each of these six DNOs and the resulting dataset from this work has been created and published under an open licence with each DNO's permission. </p><p>The data is available to download as two geojson files in the WGS84 coordinate system. One is a streamlined version which just contains the polygons along with a unique primary identifier (UPID), primary substation name, DNO licence area and local authority. The other contains the polygons along with richer energy data which was aggregated to the primary substation level from publicly available Department for Energy Security and Net Zero, Office for National Statistics and National Grid ESO datasets. This data is also available to download in tabular form as a csv file. The meter numbers and consumption values are the means of those reported from 2015-2020. The substation polygons were those as received or publicly available as of the time period of this study (2021-22).</p><p>The pre-print manuscript of the methodology used to create this dataset can be found on arXiv at:</p><p>https://doi.org/10.48550/arXiv.2311.03324</p><p>Funding to support this work was received from the Engineering and Physical Sciences Research Council (EP/W008726/1) under the Gas Net New project and the Alan Turing Institute's Science of Cities and Regions Programme. Thanks are also given to the contributors of QGIS and the Geopandas Python library, both of which were used in this analysis. </p>
Towards an open pipeline for the detection of Critical Infrastructure from satellite imagery – A case study on electrical substations in The Netherlands
<p><strong>Abstract.</strong> Critical infrastructure (CI) are at risk of failure due to the increased frequency and magnitude of climate extremes related to climate change. It is thus essential to include them in a risk management framework to identify risk hotspots, develop risk management policies and support adaptation strategies to enhance their resilience. However, the lack of information on the exposure of CI prevents their incorporation in large-scale risk assessment studies. This study sets out to improve the representation of CI for risk assessment studies by building a neural network model to detect CI assets from optical remote sensing imagery. We present a pipeline that extracts CI from OpenStreetMaps, processes the imagery and assets' masks, and trains a Mask R-CNN model that allows for instance segmentation of CI at the asset level. This study provides an overview of the pipeline and tests it with the detection of electrical substations assets in the Netherlands. Several experiments are presented for different under-sampling percentages of the majority class (25%, 50% and 100%) and hyperparameters settings (batch size and learning rate). The best metrics achieved are an Average Precision at an Intersection over Union of 50% of 30.93 and a tile F-score of 89.88%. This allows us to confirm the feasibility of the method and invite disaster risk researchers to use this pipeline for other infrastructure types. We conclude by exploring the different avenues to improve the pipeline by addressing the class imbalance, Transfer Learning and Explainable AI.</p>
Dataset for Advanced Persistent Threat (APT) Attacks on Power Substation Networks via GOOSE Protocol Exploitation
<p>This dataset captures network traffic from a simulated Advanced Persistent Threat (APT) campaign targeting a power substation's communication network. The attacker maintains a prolonged presence within the network, conducting low-profile scans using Nmap to stealthily discover the network configuration. The focus is on the communication between the Remote Terminal Unit (RTU), the Programmable Logic Controller (PLC), and the Bay Protection Unit, all of which utilize the Generic Object Oriented Substation Event (GOOSE) protocol for critical operations.</p>
Transparency dataset of "Noradrenergic circuit control of non-REM sleep substates"
<p>Raw transparency data file containing the information used the study “Noradrenergic circuit control of non-REM sleep substates” (Osorio-Forero, Cardis, Vantomme, Guillaume-Gentil, Katsioudi, Devenoges, Fernandez, Lüthi).</p> <p>Here you can find the raw data used for the effects of blockage of in-vivo or in-vitro noradrenergic signaling in the thalamus in sleep spindles clustering and cellular mechanisms. The effects on sleep spindles and sigma activity upon optogenetic stimulation of Locus coeruleus (LC) cells bodies, thalamic or somatosensory cortical LC terminals during non-rapid-eye movement sleep as well as the optogenetic inhibition of the LC bodies. Additionally, you can find the Information about the LC fiber density within the thalamus and somatosensory cortex. The effects on heart rate upon optogenetic stimulation of LC cell bodies is also included in the dataset. </p>
Simulation and Observation of GICs in the Portuguese power network SPI substation
<p>We developed an instrumental setup to measure Geomagnetic Induced Currents (GICs), consisting of a Hall effect current sensor LEM HOP 1000-SB with a manufacturer's sensitivity 4 mV/A, and a Raspberry Pi 4 Model B platform with a high resolution 24-bit digitizer board (Waveshare AD/DA). The sensor was installed at the Portuguese power network Paraimo (SPI) substation, about 35 km north of Coimbra, in the TRF6 transformer neutral to Earth connection cable.</p> <p>Here, we present measurements of GICs at SPI, during the 17th September 2021 geomagnetic event. Measurements were compared with estimations, which are also provided in this dataset.</p>
Great Britain Primary Substation Datasets
<p>The growing demand for electrified heating, electrified transportation, and power-intensive data centres challenge distribution networks. If electrification projects are carried out without considering electrical distribution infrastructure, there could be unexpected blackouts and financial losses. Datasets containing real-world distribution network information are required to address this. On the other hand, social data, such as household heating composition, are closely coupled with people’s lives. Studying the coupling between the energy system and society is important in promoting social welfare. To fill these gaps, this paper introduces two datasets. The first is the main dataset for the distribution networks in Great Britain (GB), collecting information on firm capacity, peak demands, locations, and parent transmission nodes (the Grid Supply Point, namely GSP) for all primary substations (PSs). PSs are a crucial part of the UK distribution network and are at the lowest voltage level (11 kV) with publicly available data for most UK Distribution Network Operators (DNOs). Substation firm capacity and peak demand facilitate an understanding of the remaining room of the existing network. The parent GSP information helps link the dataset of distribution networks to datasets of transmission networks. These datasets are collected, processed, and merged from various files published by the six DNOs in GB. There were inconsistencies among the PS names across files even for the same DNO. A Python script and manual validation are performed to carefully process and merge the corresponding PS information. The second dataset extends the main network dataset, linking each PS to information about the number of households that use different types of central heating recorded in census data (Census in year 2021 for England and Wales, and Census 2011 for Scotland as the most recent Scotland Census 2022 data has not yet been fully released). The derivation of the second dataset is based on locations of PSs collected in the main dataset with appropriate assumptions. The derivation process may also be replicated to integrate other social datasets.</p> <p> </p> <p>If you are interested and would like to use this dataset. Please cite our paper:</p> <p>Zhou, Yihong, Chaimaa Essayeh, and Thomas Morstyn. "Datasets of Great Britain Primary Substations Integrated with Household Heating Information." <em>Data in Brief</em> (2024): 110483. <a href="https://doi.org/10.1016/j.dib.2024.110483">https://doi.org/10.1016/j.dib.2024.110483</a>.</p> <p>The paper encloses a detailed description of all the files and methods for processing and deriving our data. The paper above also describes the values, applications, possible extensions, and limitations of the released datasets.</p>
CROSSBOW HLU2-UC1-TC1 measurements: Substation measurements gathered during curtailment activation. Second test
<p>. Capture on 21/04/2022</p> <p>The data comprises the 2 sec measurements from HOPS SCADA system for for the Konjsko substation before, during and after a curtailment in Pometeno Brno plant (21:00 - 22:30 on 21/04/2022).</p> <p>The measurements gathered from the SCADA are:</p> <ul> <li>P, Q and V of the 110, 220 and 400 Kv buses at the substation</li> </ul> <p>P, Q and V of the line connecting the substation with the plant</p>
PowerDuck: A GOOSE Data Set of Cyberattacks in Substations
<p>A recorded GOOSE data set as described in </p> <p>Sven Zemanek, Immanuel Hacker, Konrad Wolsing, Eric Wagner, Martin Henze, and Martin Serror. 2022. PowerDuck: A GOOSE Data Set of Cyberattacks in Substations. In Cyber Security Experimentation and Test Workshop (CSET ’22), August 8, 2022, Virtual, CA, USA. ACM, New York, NY, USA, 5 pages. https://doi.org/10.1145/3546096.3546102</p> <p>The data set contains network traces of GOOSE communication recorded in a physical substation testbed. Further, it includes recordings of various scenarios with and without the presence of attacks. All network packets originating from the attacker are clearly labeled as such to facilitate their identification using the Industrial Protocol Abstraction Layer (IPAL) format. We thus envision PowerDuck improving and complementing existing data sets of substations, which are often generated synthetically, and thus aim to enhance the security of power grids.</p>
Dataset of the paper "Energy Efficiency Improvement with Reversible Substations for Electrified Transportation Systems"
<p>The dataset refers to the measurement and simulations of the supply system and rolling stock of line 10 B of Metro de Madrid. Simulations have been performed by changing the position of the reversible substation and computing the current flowing in the braking rheostat of the simulated rolling stock. The data refer to the paper "Energy Efficiency Improvement with Reversible Substations for Electrified Transportation Systems" published in "The Open Transportation Journal".</p>
Western Florida Panhandle Electric Transmission Grid Substations, Lines, and Towers
<p>The upload consists of 5 different datasets pertaining to the electric transmission grid in the nine counties of the western Florida Panhandle. The area largely coincides with the former operation area of the Gulf Power Company (GPCO) but is not limited to this utility. The five datasets describe the substations, lines, and transmission towers of the grid. The data were created and validated through a variety of datasets from the utility, national data, and state-level information. In total, 195 substations, 1800 miles of transmission lines, and over 18,000 transmission towers were cataloged and described spatially in the data. The spatial files are uploaded as feature classes within a ArcGIS geodatabase. Three metadata files are provided, one each for substations, transmission lines, and transmission towers, which describe the process and sources for creating each data as well as a detailed list of all fields in the files.</p>
A Semantically Annotated 15-Class Ground Truth Dataset for Substation Equipment
<p>This dataset contains 1660 images of electric substations with 50705 annotated objects. The images were obtained using different cameras, including cameras mounted on Autonomous Guided Vehicles (AGVs), fixed location cameras and those captured by humans using a variety of cameras. A total of 15 classes of objects were identified in this dataset, and the number of instances for each class is provided in the following table:</p> <table align="center"> <caption>Object classes and how many times they appear in the dataset.</caption> <thead> <tr> <th scope="col">Class</th> <th scope="col">Instances</th> </tr> </thead> <tbody> <tr> <td>Open blade disconnect</td> <td>310</td> </tr> <tr> <td>Closed blade disconnect switch</td> <td>5243</td> </tr> <tr> <td>Open tandem disconnect switch</td> <td>1599</td> </tr> <tr> <td>Closed tandem disconnect switch</td> <td>966</td> </tr> <tr> <td>Breaker</td> <td>980</td> </tr> <tr> <td>Fuse disconnect switch</td> <td>355</td> </tr> <tr> <td>Glass disc insulator</td> <td>3185</td> </tr> <tr> <td>Porcelain pin insulator</td> <td>26499</td> </tr> <tr> <td>Muffle</td> <td>1354</td> </tr> <tr> <td>Lightning arrester</td> <td>1976</td> </tr> <tr> <td>Recloser</td> <td>2331</td> </tr> <tr> <td>Power transformer</td> <td>768</td> </tr> <tr> <td>Current transformer</td> <td>2136</td> </tr> <tr> <td>Potential transformer</td> <td>654</td> </tr> <tr> <td>Tripolar disconnect switch</td> <td>2349</td> </tr> </tbody> </table> <p>All images in this dataset were collected from a single electrical distribution substation in Brazil over a period of two years. The images were captured at various times of the day and under different weather and seasonal conditions, ensuring a diverse range of lighting conditions for the depicted objects. A team of experts in Electrical Engineering curated all the images to ensure that the angles and distances depicted in the images are suitable for automating inspections in an electrical substation.</p> <p>The file structure of this dataset contains the following directories and files:</p> <p> images: This directory contains 1660 electrical substation images in JPEG format.</p> <p>images: This directory contains 1660 electrical substation images in JPEG format.</p> <ul> <li><strong>labels_json: </strong>This directory contains JSON files annotated in the VOC-style polygonal format. Each file shares the same filename as its respective image in the images directory.</li> <li><strong>15_masks:</strong> This directory contains PNG segmentation masks for all 15 classes, including the porcelain pin insulator class. Each file shares the same name as its corresponding image in the images directory.</li> <li><strong>14_masks:</strong> This directory contains PNG segmentation masks for all classes except the porcelain pin insulator. Each file shares the same name as its corresponding image in the images directory.</li> <li><strong>porcelain_masks:</strong> This directory contains PNG segmentation masks for the porcelain pin insulator class. Each file shares the same name as its corresponding image in the images directory.</li> <li><strong>classes.txt:</strong> This text file lists the 15 classes plus the background class used in LabelMe.</li> <li><strong>json2png.py:</strong> This Python script can be used to generate segmentation masks using the VOC-style polygonal JSON annotations.</li> </ul> <p>The dataset aims to support the development of computer vision techniques and deep learning algorithms for automating the inspection process of electrical substations. The dataset is expected to be useful for researchers, practitioners, and engineers interested in developing and testing object detection and segmentation models for automating inspection and maintenance activities in electrical substations.</p> <p>The authors would like to thank UTFPR for the support and infrastructure made available for the development of this research and COPEL-DIS for the support through project PD-2866-0528/2020—Development of a Methodology for Automatic Analysis of Thermal Images. We also would like to express our deepest appreciation to the team of annotators who worked diligently to produce the semantic labels for our dataset. Their hard work, dedication and attention to detail were critical to the success of this project.</p>
Transmission and Distribution Substation Energy Management Considering Large-Scale Energy Storage, Demand Side Management and Security-Constrained Unit Commitment
<p>Data used in "Transmission and Distribution Substation Energy Management Considering Large-Scale Energy Storage, Demand Side Management and Security-Constrained Unit Commitment".</p>
Georeferentiation of CORE-TSO substations with OSM
<p>The data is in the form of a CSV table that identifies the components of the transmission grid operators (substations, transformers, and lines) in AT, BE, CZ, DE, FR, HU, HR, LU, NL, PL, RO, SI, and SK given in the Core-TSO data: https://www.jao.eu/staticgrid-model, second release, with OpenStreetMap (OSM) objects. The table was produced by geolocating the substations. To this purpose, the packages https://gitlab.com/dlr-ve-esy/esy-osm-pbf and https://gitlab.com/dlr-ve-esy/esy-osm-shape were used to extract the data from OSM and the package https://github.com/seatgeek/fuzzywuzzy was used to match the names of the substations in Core-TSO data and OSM. The value of this table is that one can produce models of the extra high voltage grid with highly reliable technical data (from Core-TSO) and precise coherent geolocations (from OSM). Additionally, a PyPSA network is created from the table (including buses, lines and transformers as well as the components not used to create the network). A detailed documentation is provided in a separate PDF file.<br> </p>
Data Set: Balanced Magnetic Antenna for Partial Discharge Measurements in Gas-Insulated Substations
<p>Data set for the publication named: Balanced Magnetic Antenna for Partial Discharge Measurements in Gas-Insulated Substations. Each header corresponds to the figure and legend.</p>
DataSet: Partial Discharge Power Flow in Gas-Insulated Substations Using Magnetic and Electric Antennas
<p>Dataset of the measurements presented in the paper "Partial Discharge Power Flow in Gas-Insulated Substations Using Magnetic and Electric Antennas" in the conference ISH 2023</p>
Dataset: Magnetic and electric antennas synergy for partial discharge measurements in gas-insulated substations: Power flow and reflection suppression
<p>Data set for the publication named: Magnetic and electric antennas synergy for partial discharge measurements in gas-insulated substations: Power flow and reflection suppression. Each header corresponds to the figure and legend.</p>
Data set: IEC 60270 Calibration Uncertainty in Gas-Insulated Substations
<p>Data set for the publication named: IEC 60270 Calibration Uncertainty in Gas-Insulated Substations.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.