Lunar - SW11_exercise

{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "aa0b11a5",
      "metadata": {
        "id": "aa0b11a5"
      },
      "source": [
        "# SW11-Exercises\n",
        "## Black-box modelling of wind turbines\n",
        "\n",
        "Data are extracted from https://opendata-renewables.engie.com/ for Turbine R80721 for 2017 and 2018."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "id": "3274c77e",
      "metadata": {
        "id": "3274c77e"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import matplotlib.pylab as plt\n",
        "import numpy as np"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "id": "48a649b2",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 448
        },
        "id": "48a649b2",
        "outputId": "ff1e9fbd-c7dd-4076-fbe8-3fe241cf53de"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<matplotlib.collections.PathCollection at 0x7f22f073bd10>"
            ]
          },
          "execution_count": 2,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# preprocessed data\n",
        "data_excerpt=pd.read_csv(\"wind-data-R80721.csv\")\n",
        "\n",
        "#visualising data\n",
        "plt.scatter(\"Ws_avg\",\"P_avg\",data=data_excerpt)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "id": "402dd8de",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "402dd8de",
        "outputId": "b4731f5c-3f45-4870-b08e-3411c07ac1c4"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Unnamed: 0</th>\n",
              "      <th>Date_time</th>\n",
              "      <th>Ws_avg</th>\n",
              "      <th>P_avg</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>2017-01-26T02:40:00+01:00</td>\n",
              "      <td>4.85</td>\n",
              "      <td>197.32001</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>2017-01-26T13:50:00+01:00</td>\n",
              "      <td>5.04</td>\n",
              "      <td>176.45000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>2017-01-26T15:00:00+01:00</td>\n",
              "      <td>5.31</td>\n",
              "      <td>190.61000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>2017-02-18T01:10:00+01:00</td>\n",
              "      <td>3.15</td>\n",
              "      <td>-2.88000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>2017-01-27T18:50:00+01:00</td>\n",
              "      <td>5.20</td>\n",
              "      <td>143.39999</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>994</th>\n",
              "      <td>995</td>\n",
              "      <td>2017-11-06T17:50:00+01:00</td>\n",
              "      <td>7.21</td>\n",
              "      <td>743.57000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>995</th>\n",
              "      <td>996</td>\n",
              "      <td>2017-04-29T10:00:00+02:00</td>\n",
              "      <td>0.17</td>\n",
              "      <td>-0.82000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>996</th>\n",
              "      <td>997</td>\n",
              "      <td>2017-06-02T07:50:00+02:00</td>\n",
              "      <td>3.18</td>\n",
              "      <td>0.00000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>997</th>\n",
              "      <td>998</td>\n",
              "      <td>2017-11-06T19:20:00+01:00</td>\n",
              "      <td>8.11</td>\n",
              "      <td>940.43000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>998</th>\n",
              "      <td>999</td>\n",
              "      <td>2017-04-10T19:20:00+02:00</td>\n",
              "      <td>5.05</td>\n",
              "      <td>165.50000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>993 rows × 4 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     Unnamed: 0                  Date_time  Ws_avg      P_avg\n",
              "0             1  2017-01-26T02:40:00+01:00    4.85  197.32001\n",
              "1             2  2017-01-26T13:50:00+01:00    5.04  176.45000\n",
              "2             3  2017-01-26T15:00:00+01:00    5.31  190.61000\n",
              "3             4  2017-02-18T01:10:00+01:00    3.15   -2.88000\n",
              "4             5  2017-01-27T18:50:00+01:00    5.20  143.39999\n",
              "..          ...                        ...     ...        ...\n",
              "994         995  2017-11-06T17:50:00+01:00    7.21  743.57000\n",
              "995         996  2017-04-29T10:00:00+02:00    0.17   -0.82000\n",
              "996         997  2017-06-02T07:50:00+02:00    3.18    0.00000\n",
              "997         998  2017-11-06T19:20:00+01:00    8.11  940.43000\n",
              "998         999  2017-04-10T19:20:00+02:00    5.05  165.50000\n",
              "\n",
              "[993 rows x 4 columns]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# cleaning outliners\n",
        "data=data_excerpt.dropna()\n",
        "display(data)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "id": "10e4f667",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 467
        },
        "id": "10e4f667",
        "outputId": "98b68e15-c2df-4869-b13a-85fec9d3bd5e"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "array([1.87076677e+03, 6.66306166e-01, 8.49310645e+00])"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "text/plain": [
              "Text(0, 0.5, 'Power [kW]')"
            ]
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# define sigmoidal function\n",
        "def sigmoidal(time, amplitude, damping , shift):\n",
        "    return amplitude/(1+np.exp(-damping*(time-shift)))\n",
        "\n",
        "from scipy import optimize\n",
        "\n",
        "#fitting process\n",
        "optimalParameters, cov = optimize.curve_fit(f=sigmoidal, xdata=data[\"Ws_avg\"], ydata=data[\"P_avg\"], p0=[2000,0.7,8.5])\n",
        "display(optimalParameters)\n",
        "\n",
        "# visualise data and fitting data\n",
        "plt.scatter(data[\"Ws_avg\"], data[\"P_avg\"],marker=\"+\",color=\"black\")\n",
        "wind_speeds=np.arange(0,max(data[\"Ws_avg\"]),0.1)\n",
        "\n",
        "fitted=sigmoidal(wind_speeds,optimalParameters[0],optimalParameters[1],optimalParameters[2])\n",
        "plt.plot(wind_speeds,fitted,\"r\")\n",
        "plt.xlabel(\"Wind speed [m/s]\")\n",
        "plt.ylabel(\"Power [kW]\")\n",
        "#plt.savefig(\"wind-speed-fitted.png\",bbox_inches=\"tight\",dpi=500)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "bc2695a6",
      "metadata": {
        "id": "bc2695a6"
      },
      "source": [
        "In conclusion, we replaced the measurement data with the fit function:\n",
        "\n",
        "$$ \\mathrm{Power}(\\mathrm{windspeed}\\, w)=\\frac{1870}{1+\\exp(-0.666\\cdot (w - 8.49))}$$"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "base",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.12.4"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}