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.
10
datasets available to search
ShareScore release 0.7.1
Dataset results
10 results for “load forecasting”
Rye microgrid load and generation data, and meteorological forecasts.
<p>This dataset contains timeseries for Rye Microgrid, Trondheim, Norway. The timeseries include solar and wind power generation, consumption and historical weather forecasts.</p> <p>From <a href="https://github.com/TronderEnergi/tronderenergi-ai-hackathon-2021">https://github.com/TronderEnergi/tronderenergi-ai-hackathon-2021</a>:</p> <p><em>"The Rye microgrid is a pilot within the EU research project REMOTE. It is a small microgrid placed at Langørgen, in the outskirts of Trondheim, and is a small energy system designed to supply electricity to a modern farm and three households. The REMOTE projects goal for Rye Microgrid is to run the system in islanded mode.</em></p> <p><em>The system has two sources of generation – a wind turbine and a rack of PV panels. In addition, the system has two storages – a battery with high charge and discharge response, but with limited storage and losses, and a hydrogen energy system, with lower charge and discharge rates, higher losses and storage capacity. When you want to charge the hydrogen system, electricity is used to run an electrolyser that makes hydrogen from water and stores the resulting hydrogen in a tank. The process can be reversed by producing electricity from hydrogen using a fuel cell. (...)</em></p> <p><em>Morover, when local production or discharges from storages are not sufficient to cover the demand, the microgrid can draw electricity from the grid at some costs."</em></p> <p> </p> <p>For further details, see: <a href="https://www.remote-euproject.eu/remote18/rem18-cont/uploads/2019/03/REMOTE-D2.2.pdf">https://www.remote-euproject.eu/remote18/rem18-cont/uploads/2019/03/REMOTE-D2.2.pdf</a> and <a href="https://github.com/TronderEnergi/tronderenergi-ai-hackathon-2021">https://github.com/TronderEnergi/tronderenergi-ai-hackathon-2021</a></p> <p>rye_generation_and_load.csv is a comma-separated csv-file with the following columns (all values in <em>kW </em>and time as UTC):</p> <ul> <li>Consumption: Consumption of loads in system (residential and agriculture).</li> <li>Solar: Total production from all solar PV racks.</li> <li>Wind: Power production from wind turbine.</li> </ul> <p>met_data.h5: Contains historical weather forecasts data from The Norwegian Meteorological Institute (met.no) updated every 6 hours for the given location. The file is in hdf5 format. The forecasts include the following parameters: air_pressure_at_sea_level [Pa], air_temperature_2m [K], cloud_area_fraction [pu], integral_of_surface_downwelling_shortwave_flux_in_air_wrt_time [J/m<sup>2</sup>s], wind_direction_10m [deg], wind_speed_10m [m/s]</p> <p>The structure of the file is as follows:</p> <ul> <li>lat63_41_lon10_11 (coordinates) <ul> <li>[forecasted parameter] <ul> <li>forecast <ul> <li>2020-01-01T00Z (time forecast was issued) <ul> <li>axis0 (columns, index where each represent a point in a geographical grid. For example if axis=0,1,2,3, the tables contains the forecasts for the four closes points to the microgrid.)</li> <li>axis1 (rows, timestamps)</li> <li>block0_items (equal to axis0)</li> <li>block0_values (matrix, forecast values)</li> </ul> </li> </ul> </li> </ul> </li> </ul> </li> </ul>
Supplement to "Probabilistic load forecasting for the low voltage network: forecast fusion and daily peaks"
<p>This deposit contains the scripts and data used in the research article "Probabilistic load forecasting for the low voltage network: forecast fusion and daily peaks", which proposed a novel method for electricity demand forecasting in low voltage networks.</p> <p>The scripts are written in the form of R markdown and include additional commentary on the methodology. Both input data and the resulting forecast data and evaluation results are provided, though the latter two may be regenerated by running the scripts.</p>
Supplementary Material for "Probabilistic Forecasting of Regional Net-load with Conditional Extremes and Gridded NWP"
<p>Supplementary material to accompany pre-print of "Probabilistic Forecasting of Regional Net-load with Conditional Extremes and Gridded NWP" by Jethro Browell and Matteo Fasiolo available on on arXiv. This is version 3. The only changes from version 1 & 2 to forecast evaluation (significance testing and additional plots). Future releases are subject to change following revisions of this article.</p>
supplymentary for sediment load forecasting
<p>Forecasting results of sediment load from stations along the mainstream and different tributaries; Bayesian inference code to forecast sediment load</p>
Railbelt 2050 Load, Electrification, and Behind-the-Meter Solar Hourly Load Demand for Aggressive and Moderate Electrification Forecasts
<p>The data in this file is comprised of hourly load demand data for the year of 2050 for Alaska's Railbelt transmission system from the aggressive and moderate load, electrification adoption, and behind-the-meter solar forcasts generated by the ACEP Railbelt Decarbonization Study. </p>
Dataset - "An Adaptive Multi-Seasonal ARIMA Approach for Domestic Hot Water Load Forecasting: A Pilot Study"
<p>The description of the data is in README.txt.</p>
Supplementary materials for "Adaptive Probabilistic Forecasting of Electricity (Net-)Load"
<p>Supplementary materials for “Adaptive Probabilistic Forecasting of Electricity (Net-)Load”, presently under review. Only underlying data is included for now. Code will be included in a future update of this deposit.</p>
Dataset for "Artificial neural network and SARIMA based models for power load forecasting in Turkish electricity market"
<p>This is the dataset for the manuscript "Artificial neural network and SARIMA based models for power load forecasting in Turkish electricity market" submitted to the journal PLOS ONE. </p>
The EMSx dataset: historical photovoltaic and load scenarios and forecasts for 70 industrial sites
<p>The EMSx dataset gathers a large collection of photovoltaic and load profiles collected by the company Schneider Electric on 70 anonymized industrial sites. This dataset is released as a component of the EMSx benchmark for energy management systems introduced in a sister publication DOI: <a href="https://doi.org/10.1007/s12667-020-00417-5"> 10.1007/s12667-020-00417-5 </a>. Please refer to this related journal article for a detailed description of the dataset and if mentioning the EMSx dataset in your work.</p> <p>This dataset contains compressed files with a site ID ranging from 1 to 70. For these files, each line represents a timestep, gathering historical photovoltaic energy production and energy consumption data over the last 15 minutes, together with historical forecasts computed by Schneider Electric. The column naming follows the rules: </p> <ul> <li><code>load_XX</code> in kWh: For XX from 00 to 95, a forecast for the consumption where each subsequent value is 15 minutes later. <code>load_00</code> is a forecast for the load in the next 15 minutes. These values are forecasts, and so will not exactly match the actual consumption at that timestep.</li> </ul> <ul> <li><code>pv_XX</code> in kWh: For XX from 00 to 95, a forecast for the pv produced on site where each subsequent value is 15 minutes later. <code>pv_00</code> is a forecast for the pv production during the next 15 minutes. These values are forecasts, and so will not exactly match the actual_pv at that timestep.</li> </ul> <p>Besides files per sites, one file contains the unique historical photovoltaic production profile and forecasts employed in the data of all sites, after being rescaled appropriately. In this file, we have rescaled power values to [0,1] so that this data can serve the modeling of a photovoltaic unit beyond the scope of the EMSx benchmark. Finally, this dataset contains a metadata file providing battery storage capacities in kWh, battery flow capacities for 15 minutes in kWh, and battery efficiency coefficients, designed for the EMSx benchmark.</p> <p>This dataset contains information from Schneider's <a href="https://shop.exchange.se.com/en-US/apps/52535/microgrid-energy-management-benchmark">Microgrid Energy Management Benchmark</a>, which is made available under the Open Database License (ODbL).</p>
Dataset for the paper "Model Selection for Long-term Load Forecasting under Uncertainty"
<p>This is a CSV spreadsheet containing the time-series load data and its co-variates used in the study. The columns and their corresponding variable names are enlisted as follows:</p> <ol> <li>UTC : Universal Time Coordinated timestamp</li> <li>'mw' : Daily peak load in MW</li> <li>'MoY': Month of year</li> <li> 'DoW': Day of Week</li> <li> 'h_name': Holiday name</li> <li> 'TMAX_mean': Mean aggregation of maximum temperature series of 40 weather stations within PJM area</li> <li> 'Pop': Population</li> <li> 'PCI_real': Real per capita inncome</li> <li> 'GSP_real': Real Gross State product</li> <li>'flag': flag for structural change in load due to territorial expansion</li> <li>'flag_hol': flag for holiday</li> <li>'flag_recession': flag for structural change in load due to recession of 2007-09</li> <li>'wkday': flag for weekday effect</li> </ol>
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.