{
  "fetched_at": "2026-10-19T22:48:36Z",
  "source_url": "https://www.kaggle.com/competitions/data-for-solar-energy-production-cavle/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Except for data and time, all input and output variables are floating-point values. There are some missing values defined as NaN.\n\n\n**Output**\n\nThe output should contain two columns, the first column should be the sample identifier ID (starting from 1), whereas the second column should contain predicted values Ghi value.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description ",
      "content": "**Stem Games - Day 2**\nCroatia, Umag, May 14 2024",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": " ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Introduction",
      "content": "The decarbonization goals and energy self-sustainability of each country prompts an increase of renewable energy sources such as hydro energy, solar energy, and wind energy. Consequently, the increase of renewable energy sources requires finding of appropriate energy storage solutions, including novel techniques such as hydrogen storage. Solar panels are an appropriate solution for renewable energy harvesting since they can easily be installed even at private houses.\n\nTo find the appropriate location for the solar power plant installation it is required to find the location with the best conditions. Three brothers decided that they would invest in solar power plants at the roof of their houses, however they can invest in only one location.\n\nLuckily, they were able to obtain the historical data of solar radiation for locations of their houses. This data can help them identify which location would be the most appropriate one. \n\n\n## Problem statement\n\nThe problem is that input data has some missing information. It is required to **determine best ML model that will predict Ghi value for next 3 months with most appropriate features** so the best location for installing solars can be determined. \n\n**Hints:** Evaluate appropriate treatment of missing data (elimination of these records, replacing missing data with some substitute value (imputation methods), etc.)\nExplore dimensionality reduction. Features can be omitted, manipulations with the data can be made (e.g. PCA), etc.\n\nThe meteorological data is given in a CSV file for 3 separate locations and contains parameters described at the link https://solcast.com/data-parameter-definitions.\n\nThe data comprises hour measurements for the period of 3 years. The data consist from all available meteorological data relevant for solar insolation for chosen locations. It is known that GHI component of solar irradiation is most important for determination of solar potential for solar pannels, therefore it is required to predict Ghi value for the period of next 3 months for 3 chosen locations. Some examples of data are shown in table below.  \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Solutions will be ranked by the obtained RMSE value. The data for the **last 3 months in the dataset (period from 1.10.2023 to 1.1.2024, including these dates)** will serve for the purpose of this evaluation. It is necessary to evaluate RMSE for each location. The best solution will be the model that has the smallest RMSE for all 3 locations, cumulatively. I.e. the best solution will be the cumulative RMSE (the sum of 3 RMSE values, one for each location). For each location the same machine learning algorithm should be used, but trained for every location separately. For example, if you want to use Linear regression, the linear regression with same model parameters should be done 3 times, one time for each location. For each location the RMSE should be calculated and summed up.\n\n**Root Mean Squared Error (RMSE)**\nRMSE stands for Root Mean Squared Error. Like MSE, it measures the average squared difference between the predicted values and the actual values. However, RMSE takes the square root of the MSE, which makes it easier to interpret because it is in the same units as the dependent variable.\nRMSE is calculated as:\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F20824360%2Fdd3ed02c69c16472dd79667093167d11%2Fformula.PNG?generation=1715587030016492&alt=media) \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Citation",
      "content": "Solcast, 2024. Global solar irradiance data and PV system power output data. URL https://solcast.com/ ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}