{
  "fetched_at": "2026-10-19T15:16:08Z",
  "source_url": "https://www.kaggle.com/competitions/eso-battery-forecasting/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Your challenge in this competition  is to predict battery behaviour on Great Britain's electricity network. Through this challenge you will identify trends,  detect anomalies, and develop predictive models to balance the system. \n\nThis is a forecasting competition. The data we have provided is open sourced, available to the public but we highly encourage you to explore additional data sets we've not considered.\n\n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\nAll files will have the same column types.\n\n## Columns\n\n*   `Settlement` - A settlement period is a half-hourly period used in trading and balancing of electricity. Each day has 48 settlement periods where generators and suppliers (including batteries) trade electricity in half-hourly blocks https://www.elexon.co.uk/data/open-settlement-data/\n*   `Battery Output`- The battery output is the amount of Mega Watt (MW) that  flow's  through a battery at a determined time. \n*   `Location and Price` - This field describes the price for electricity in a given location. This is data generated for the Octopus Agile Tariff and collected here: https://energy-stats.uk/download-historical-pricing-data/ \n*   `Location and Weather`- This field describes the hourly weather conditions in a given location https://open-meteo.com and https://open-meteo.com/en/license. You can find detailed metadata and units of measurement here: https://open-meteo.com/en/docs\n\n## Useful Info about this specific battery\n\n*   `Notice to deviate from zero` - 1 minutes\n*   `Notice to deliver bids` - 1 minutes\n*   `Notice to deliver offers` - 1 minutes\n*   `Maximum delivery Capacity` - 35 MW\n*   `Maximum delivery period` - 60 minutes\n*   `Minimum zero time` - 0 minutes\n*   `Minimum non-zero time` - 1 minutes\n*   `Location` - North East England\n\n## Other useful data sources\n\n**BMReports:** https://bmrs.elexon.co.uk/ `(System Data, including demand and generation actuals.)`\n**Carbon Intensity:** https://carbonintensity.org.uk/ `(Current and future carbon intensity of the GB electricity grid)`\n**ESO Data Portal:** https://www.nationalgrideso.com/data-portal `(System Data, including Demand forecast and actuals, constraints, balancing costs and lots more)`\n**ENTSO-E Transparency Platform:** https://transparency.entsoe.eu/ `(EU electricity data including GB)`\n**Sheffield Solar PV Live:** https://www.solar.sheffield.ac.uk/pvlive/ `(GB Solar Generation actuals)`\n**Price Data:** `There are various websites providing wholesale GB price data like NordPool (SEM-GB half hourly intraday) and Epexspot. However price data can be sensitive and restrictive, so please adhere to any terms and conditions on the respective sites when attempting to use and download data`",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Goal of the Competition\n\nThe goal of this competition is to predict the charging and discharging patterns of batteries on the electricity network, and the key drivers of this behaviour. \n\nThis exciting challenge will give you the opportunity to learn more about the Electricity System Operator (ESO) of Great Britain, and how we're trying to improve our understanding of battery behaviour on the network  to ensure we can balance supply and demand of electricity reliably and economically.\n\n## Context \n\nThe ESO sits at the heart of the electricity system in Great Britain. Our job is to move electricity around the country's high voltage network to balance supply and demand in real-time, using a mix of power sources (including batteries), to make sure electricity is available wherever and whenever it's needed. \n\nOne of our core ambitions is to facilitate the decarbonisation of Great Britain's energy network and ensure the delivery of reliable, affordable , and green electricity for consumers. \n\nBatteries enable us to store excess energy from intermittent renewable  sources such as sun and wind, so that when the sun isn't shining or the wind isn't blowing, we can deploy batteries to help us balance the network.  Currently, the capacity of batteries in GB is growing steadily, and you will have the opportunity to explore various datasets and understand how batteries support demand on the network, forecast their impact and see how they can be used to make real-time decisions to balance the system.\n\nImproving our forecasts of electricity demand across the network, and ultimately optimising the use of batteries will help us make better decisions in real-time. Your solutions may help shape the future of GB's energy system to help us facilitate net zero and a fair transition to a decarbonised system for all of GB's consumers. \n\nHere is a link to the ESO webpage to find out more about electricity \nhttps://www.nationalgrideso.com/electricity-explained\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on Mean Absolute Error (https://en.wikipedia.org/wiki/Mean_absolute_error) between the predicted battery output and the observed battery output.\n\n\n## Submission File\nFor each ID in the test set, you must predict the value for the battery_output variable. The file should contain a header and have the following format:\n\n    ID,battery_output\n    0,12.413\n    1,10.021\n    2,-5.123\n    etc.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "ESO battery forecasting hackathon rules: \n\n - Some data can be sensitive and restrictive, so please adhere to any terms and conditions on the respective sites when attempting to use and download data (E.g Price).\n - Don't cheat!\n - Ask questions!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}