data.datasets.power_plants.wind_offshore.insert()

Complexity

Conditions

11

Size

Total Lines	220
Code Lines	131

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

from pathlib import Path
def insert():
    """
    Include the offshore wind parks in egon-data.

    Parameters
    ----------
    *No parameters required
    """
    # Read file with all required input/output tables' names
    cfg = egon.data.config.datasets()["power_plants"]

    scenarios = egon.data.config.settings()["egon-data"]["--scenarios"]

    for scenario in scenarios:
        # Delete previous generators
        db.execute_sql(
            f"""
            DELETE FROM {cfg['target']['schema']}.{cfg['target']['table']}
            WHERE carrier = 'wind_offshore'
            AND scenario = '{scenario}'
            """
        )

        # load file
        if scenario == "eGon2035":
            offshore_path = (
                Path(".")
                / "data_bundle_egon_data"
                / "nep2035_version2021"
                / cfg["sources"]["nep_2035"]
            )

            offshore = pd.read_excel(
                offshore_path,
                sheet_name="WInd_Offshore_NEP",
                usecols=[
                    "Netzverknuepfungspunkt",
                    "Spannungsebene in kV",
                    "C 2035",
                ],
            )
            offshore.dropna(subset=["Netzverknuepfungspunkt"], inplace=True)
            offshore.rename(columns={"C 2035": "el_capacity"}, inplace=True)

        elif scenario == "eGon100RE":
            offshore_path = (
                Path(".")
                / "data_bundle_egon_data"
                / "nep2035_version2021"
                / cfg["sources"]["nep_2035"]
            )

            offshore = pd.read_excel(
                offshore_path,
                sheet_name="WInd_Offshore_NEP",
                usecols=[
                    "Netzverknuepfungspunkt",
                    "Spannungsebene in kV",
                    "B 2040 ",
                ],
            )
            offshore.dropna(subset=["Netzverknuepfungspunkt"], inplace=True)
            offshore.rename(columns={"B 2040 ": "el_capacity"}, inplace=True)

        elif "status" in scenario:
            year = int(scenario[-4:])

            offshore_path = (
                Path(".")
                / "data_bundle_egon_data"
                / "wind_offshore_status2019"
                / cfg["sources"]["wind_offshore_status2019"]
            )
            offshore = pd.read_excel(
                offshore_path,
                sheet_name="wind_offshore",
                usecols=[
                    "Name ONEP/NEP",
                    "NVP",
                    "Spannung [kV]",
                    "Inbetriebnahme",
                    "Kapazität Gesamtsystem [MW]",
                ],
            )
            offshore.dropna(subset=["Name ONEP/NEP"], inplace=True)
            offshore.rename(
                columns={
                    "NVP": "Netzverknuepfungspunkt",
                    "Spannung [kV]": "Spannungsebene in kV",
                    "Kapazität Gesamtsystem [MW]": "el_capacity",
                },
                inplace=True,
            )
            offshore = offshore[offshore["Inbetriebnahme"] <= year]

        else:
            raise ValueError(f"{scenario=} is not valid.")

        id_bus = map_id_bus(scenario)

        # Match wind offshore table with the corresponding OSM_id
        offshore["osm_id"] = offshore["Netzverknuepfungspunkt"].map(id_bus)

        buses = db.select_geodataframe(
            f"""
                SELECT bus_i as bus_id, base_kv, geom as point, CAST(osm_substation_id AS text)
                as osm_id FROM {cfg["sources"]["buses_data"]}
                """,
            epsg=4326,
            geom_col="point",
        )

        # Drop NANs in column osm_id
        buses.dropna(subset=["osm_id"], inplace=True)

        # Create columns for bus_id and geometry in the offshore df
        offshore["bus_id"] = pd.NA
        offshore["geom"] = Point(0, 0)

        # Match bus_id
        for index, wind_park in offshore.iterrows():
            if not buses[
                (buses["osm_id"] == wind_park["osm_id"])
                & (buses["base_kv"] == wind_park["Spannungsebene in kV"])
            ].empty:
                bus_ind = buses[buses["osm_id"] == wind_park["osm_id"]].index[
                    0
                ]
                offshore.at[index, "bus_id"] = buses.at[bus_ind, "bus_id"]
            else:
                print(f'Wind offshore farm not found: {wind_park["osm_id"]}')

        offshore.dropna(subset=["bus_id"], inplace=True)

        # Overwrite geom for status2019 parks
        if scenario in ["eGon2035", "eGon100RE"]:
            offshore["Name ONEP/NEP"] = offshore["Netzverknuepfungspunkt"].map(
                assign_ONEP_areas()
            )

        offshore["geom"] = offshore["Name ONEP/NEP"].map(map_ONEP_areas())
        offshore["weather_cell_id"] = pd.NA

        offshore.drop(["Name ONEP/NEP"], axis=1, inplace=True)

        if "status" in scenario:
            offshore.drop(["Inbetriebnahme"], axis=1, inplace=True)

        # Scale capacities for eGon100RE
        if scenario == "eGon100RE":
            # Import capacity targets for wind_offshore per scenario
            cap_100RE = db.select_dataframe(
                f"""
                    SELECT SUM(capacity)
                    FROM {cfg["sources"]["capacities"]}
                    WHERE scenario_name = 'eGon100RE' AND
                    carrier = 'wind_offshore'
                    """
            ).iloc[0, 0]

            # Scale capacities to match  target
            scale_factor = cap_100RE / offshore.el_capacity.sum()
            offshore["el_capacity"] *= scale_factor

        # Assign voltage levels to wind offshore parks
        offshore["voltage_level"] = 0
        offshore.loc[
            offshore[offshore["Spannungsebene in kV"] == 110].index,
            "voltage_level",
        ] = 3
        offshore.loc[
            offshore[offshore["Spannungsebene in kV"] > 110].index,
            "voltage_level",
        ] = 1

        # Delete unnecessary columns
        offshore.drop(
            [
                "Netzverknuepfungspunkt",
                "Spannungsebene in kV",
                "osm_id",
            ],
            axis=1,
            inplace=True,
        )

        # Set static columns
        offshore["carrier"] = "wind_offshore"
        offshore["scenario"] = scenario

        offshore = gpd.GeoDataFrame(offshore, geometry="geom", crs=4326)

        # Look for the maximum id in the table egon_power_plants
        next_id = db.select_dataframe(
            "SELECT MAX(id) FROM "
            + cfg["target"]["schema"]
            + "."
            + cfg["target"]["table"]
        ).iloc[0, 0]

        if next_id:
            next_id += 1
        else:
            next_id = 1

        # Reset index
        offshore.index = pd.RangeIndex(
            start=next_id, stop=next_id + len(offshore), name="id"
        )

        # Insert into database
        offshore.reset_index().to_postgis(
            cfg["target"]["table"],
            schema=cfg["target"]["schema"],
            con=db.engine(),
            if_exists="append",
        )

        logging.info(
            f"""
              {len(offshore)} wind_offshore generators with a total installed capacity of