Features/#988 distribute home batteries within grid districts (#1008)

* added home battery allocation onto buildings
* add dataset to pipeline
* added sanity checks
* update dataset version and changelog
* undo hard coding in sanity checks and pv_rooftop

Co-authored-by: Julian.Endres <julian.endres@rl-institut.de>
Co-authored-by: nesnoj <jonathan.amme@rl-institut.de>

CHANGELOG.rst

@@ -233,6 +233,8 @@ Added
   `PR #978 <https://github.com/openego/eGon-data/pull/978>`_
 *  Add voltage level for electricity building loads
   `#955 <https://github.com/openego/eGon-data/issues/955>`_
+* Add desaggregation of pv home batteries onto buildings
+  `#988 <https://github.com/openego/eGon-data/issues/988>`_
 
 .. _PR #159: https://github.com/openego/eGon-data/pull/159
 .. _PR #703: https://github.com/openego/eGon-data/pull/703

setup.py

@@ -5,7 +5,8 @@
 from glob import glob
 from os.path import basename, dirname, join, splitext
 import io
-import re 
+import re
+
 from setuptools import find_packages, setup
 
 

src/egon/data/airflow/dags/pipeline.py

@@ -79,7 +79,7 @@
 from egon.data.datasets.scenario_capacities import ScenarioCapacities
 from egon.data.datasets.scenario_parameters import ScenarioParameters
 from egon.data.datasets.society_prognosis import SocietyPrognosis
-from egon.data.datasets.storages import PumpedHydro
+from egon.data.datasets.storages import Storages
 from egon.data.datasets.storages_etrago import StorageEtrago
 from egon.data.datasets.substation import SubstationExtraction
 from egon.data.datasets.substation_voronoi import SubstationVoronoi
@@ -419,7 +419,7 @@
             run_pypsaeursec,
             foreign_lines,
             insert_hydrogen_buses,
-            create_gas_polygons_egon100RE
+            create_gas_polygons_egon100RE,
         ]
     )
 
@@ -507,7 +507,7 @@
     )
 
     # Pumped hydro units
-    pumped_hydro = PumpedHydro(
+    pumped_hydro = Storages(
         dependencies=[
             mastr_data,
             mv_grid_districts,

src/egon/data/datasets.yml

@@ -1155,7 +1155,9 @@ mobility_hgv:
       # share of FCEV trucks
       # within the egon project the flat guess is 100%
       fcev_share: 1.
-      scenarios: ["eGon2035", "eGon100RE"]
+      scenarios:
+        - "eGon2035"
+        - "eGon100RE"
       carrier: "H2_hgv_load"
       energy_value_h2: 39.4  # kWh/kg
       hours_per_year: 8760
@@ -1172,3 +1174,24 @@ mobility_hgv:
       # Langfristszenarien
       # https://www.langfristszenarien.de/enertile-explorer-wAssets/docs/LFS3_Langbericht_Verkehr_final.pdf#page=17
       eGon100RE: 40000000000
+
+home_batteries:
+  constants:
+    scenarios:
+      - "eGon2035"
+      - "eGon100RE"
+    # Mean ratio between the storage capacity and the power of the pv rooftop system
+    cbat_ppv_ratio: 1
+    rtol: 0.05
+    max_it: 100
+  sources:
+    etrago_storage:
+      schema: 'grid'
+      table: 'egon_etrago_storage'
+    storage:
+      schema: 'supply'
+      table: 'egon_storages'
+  targets:
+    home_batteries:
+      schema: 'supply'
+      table: 'egon_home_batteries'

src/egon/data/datasets/power_plants/__init__.py

@@ -22,7 +22,7 @@
     pv_rooftop_to_buildings,
 )
 import egon.data.config
-import egon.data.datasets.power_plants.assign_weather_data as assign_weather_data
+import egon.data.datasets.power_plants.assign_weather_data as assign_weather_data  # noqa: E501
 import egon.data.datasets.power_plants.pv_ground_mounted as pv_ground_mounted
 import egon.data.datasets.power_plants.wind_farms as wind_onshore
 import egon.data.datasets.power_plants.wind_offshore as wind_offshore
@@ -796,7 +796,7 @@ def allocate_other_power_plants():
 
     # Select power plants representing carrier 'others' from MaStR files
     mastr_sludge = pd.read_csv(cfg["sources"]["mastr_gsgk"]).query(
-        """EinheitBetriebsstatus=='InBetrieb'and Energietraeger=='Klaerschlamm'"""
+        """EinheitBetriebsstatus=='InBetrieb'and Energietraeger=='Klaerschlamm'"""  # noqa: E501
     )
     mastr_geothermal = pd.read_csv(cfg["sources"]["mastr_gsgk"]).query(
         "EinheitBetriebsstatus=='InBetrieb' and Energietraeger=='Geothermie' "

src/egon/data/datasets/power_plants/pv_rooftop.py

@@ -1,5 +1,7 @@
 """The module containing all code dealing with pv rooftop distribution.
 """
+from pathlib import Path
+
 from loguru import logger
 from numpy import isclose
 import geopandas as gpd
@@ -10,6 +12,7 @@
     PV_CAP_PER_SQ_M,
     ROOF_FACTOR,
     load_building_data,
+    scenario_data,
 )
 from egon.data.datasets.scenario_parameters import get_sector_parameters
 
@@ -158,10 +161,22 @@ def pv_rooftop_per_mv_grid_and_scenario(scenario, level):
         dataset = config.settings()["egon-data"]["--dataset-boundary"]
 
         if dataset == "Schleswig-Holstein":
-            # since the required data is missing for a SH run, it is implemented
-            # manually here
-            total_2035 = 84070
-            sh_2035 = 2700
+            sources = config.datasets()["scenario_input"]["sources"]
+
+            path = Path(
+                f"./data_bundle_egon_data/nep2035_version2021/"
+                f"{sources['eGon2035']['capacities']}"
+            ).resolve()
+
+            total_2035 = (
+                pd.read_excel(
+                    path,
+                    sheet_name="1.Entwurf_NEP2035_V2021",
+                    index_col="Unnamed: 0",
+                ).at["PV (Aufdach)", "Summe"]
+                * 1000
+            )
+            sh_2035 = scenario_data(scenario="eGon2035").capacity.sum()
 
             share = sh_2035 / total_2035
 
@@ -187,8 +202,8 @@ def pv_rooftop_per_mv_grid_and_scenario(scenario, level):
         }
     )
 
-    # ensure that no more pv rooftop capacity is allocated to any mv grid district than
-    # there is rooftop potential
+    # ensure that no more pv rooftop capacity is allocated to any mv grid
+    # district than there is rooftop potential
     max_cap_per_bus_df = (
         valid_buildings_gdf[["max_cap", "bus_id"]].groupby("bus_id").sum()
         / 1000
@@ -225,8 +240,8 @@ def pv_rooftop_per_mv_grid_and_scenario(scenario, level):
 
     if loss < 0:
         logger.debug(
-            f"{loss:g} MW got redistributed from MV grids with too little rooftop "
-            f"potential towards other MV grids."
+            f"{loss:g} MW got redistributed from MV grids with too little "
+            f"rooftop potential towards other MV grids."
         )
 
     # Select feedin timeseries

src/egon/data/datasets/sanity_checks.py

@@ -21,7 +21,7 @@
     EgonCtsElectricityDemandBuildingShare,
     EgonCtsHeatDemandBuildingShare,
 )
-from egon.data.datasets.emobility.motorized_individual_travel.db_classes import (
+from egon.data.datasets.emobility.motorized_individual_travel.db_classes import (  # noqa: E501
     EgonEvCountMunicipality,
     EgonEvCountMvGridDistrict,
     EgonEvCountRegistrationDistrict,
@@ -49,6 +49,7 @@
     scenario_data,
 )
 from egon.data.datasets.scenario_parameters import get_sector_parameters
+from egon.data.datasets.storages.home_batteries import get_cbat_pbat_ratio
 import egon.data
 
 TESTMODE_OFF = (
@@ -60,7 +61,7 @@ class SanityChecks(Dataset):
     def __init__(self, dependencies):
         super().__init__(
             name="SanityChecks",
-            version="0.0.5",
+            version="0.0.6",
             dependencies=dependencies,
             tasks={
                 etrago_eGon2035_electricity,
@@ -71,6 +72,7 @@ def __init__(self, dependencies):
                 cts_heat_demand_share,
                 sanitycheck_emobility_mit,
                 sanitycheck_pv_rooftop_buildings,
+                sanitycheck_home_batteries,
             },
         )
 
@@ -769,10 +771,22 @@ def egon_power_plants_pv_roof_building():
             dataset = config.settings()["egon-data"]["--dataset-boundary"]
 
             if dataset == "Schleswig-Holstein":
-                # since the required data is missing for a SH run, it is implemented
-                # manually here
-                total_2035 = 84070
-                sh_2035 = 2700
+                sources = config.datasets()["scenario_input"]["sources"]
+
+                path = Path(
+                    f"./data_bundle_egon_data/nep2035_version2021/"
+                    f"{sources['eGon2035']['capacities']}"
+                ).resolve()
+
+                total_2035 = (
+                    pd.read_excel(
+                        path,
+                        sheet_name="1.Entwurf_NEP2035_V2021",
+                        index_col="Unnamed: 0",
+                    ).at["PV (Aufdach)", "Summe"]
+                    * 1000
+                )
+                sh_2035 = scenario_data(scenario="eGon2035").capacity.sum()
 
                 share = sh_2035 / total_2035
 
@@ -1345,3 +1359,48 @@ def check_model_data_lowflex_eGon2035():
     check_model_data_lowflex_eGon2035()
 
     print("=====================================================")
+
+
+def sanitycheck_home_batteries():
+    # get constants
+    constants = config.datasets()["home_batteries"]["constants"]
+    scenarios = constants["scenarios"]
+    cbat_pbat_ratio = get_cbat_pbat_ratio()
+
+    sources = config.datasets()["home_batteries"]["sources"]
+    targets = config.datasets()["home_batteries"]["targets"]
+
+    for scenario in scenarios:
+        # get home battery capacity per mv grid id
+        sql = f"""
+        SELECT el_capacity as p_nom, bus_id FROM
+        {sources["storage"]["schema"]}
+        .{sources["storage"]["table"]}
+        WHERE carrier = 'home_battery'
+        AND scenario = '{scenario}'
+        """
+
+        home_batteries_df = db.select_dataframe(sql, index_col="bus_id")
+
+        home_batteries_df = home_batteries_df.assign(
+            capacity=home_batteries_df.p_nom * cbat_pbat_ratio
+        )
+
+        sql = f"""
+        SELECT * FROM
+        {targets["home_batteries"]["schema"]}
+        .{targets["home_batteries"]["table"]}
+        WHERE scenario = '{scenario}'
+        """
+
+        home_batteries_buildings_df = db.select_dataframe(
+            sql, index_col="index"
+        )
+
+        df = (
+            home_batteries_buildings_df[["bus_id", "p_nom", "capacity"]]
+            .groupby("bus_id")
+            .sum()
+        )
+
+        assert (home_batteries_df.round(6) == df.round(6)).all().all()

src/egon/data/datasets/storages/__init__.py

@@ -1,25 +1,28 @@
 """The central module containing all code dealing with power plant data.
 """
-from geoalchemy2 import Geometry
 from pathlib import Path
+
+from geoalchemy2 import Geometry
 from sqlalchemy import BigInteger, Column, Float, Integer, Sequence, String
 from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import sessionmaker
-from egon.data.datasets.storages.pumped_hydro import (
-    select_mastr_pumped_hydro,
-    select_nep_pumped_hydro,
-    match_storage_units,
-    get_location,
-    apply_voltage_level_thresholds,
-)
-from egon.data.datasets.power_plants import assign_voltage_level
 import geopandas as gpd
 import pandas as pd
 
-from egon.data import db, config
+from egon.data import config, db
 from egon.data.datasets import Dataset
-
+from egon.data.datasets.power_plants import assign_voltage_level
+from egon.data.datasets.storages.home_batteries import (
+    allocate_home_batteries_to_buildings,
+)
+from egon.data.datasets.storages.pumped_hydro import (
+    apply_voltage_level_thresholds,
+    get_location,
+    match_storage_units,
+    select_mastr_pumped_hydro,
+    select_nep_pumped_hydro,
+)
 
 Base = declarative_base()
 
@@ -38,17 +41,18 @@ class EgonStorages(Base):
     geom = Column(Geometry("POINT", 4326))
 
 
-class PumpedHydro(Dataset):
+class Storages(Dataset):
     def __init__(self, dependencies):
         super().__init__(
             name="Storages",
-            version="0.0.2",
+            version="0.0.4",
             dependencies=dependencies,
             tasks=(
                 create_tables,
                 allocate_pumped_hydro_eGon2035,
                 allocate_pumped_hydro_eGon100RE,
-                allocate_pv_home_batteries,
+                allocate_pv_home_batteries_to_grids,
+                allocate_home_batteries_to_buildings,
             ),
         )
 
@@ -292,8 +296,8 @@ def allocate_pumped_hydro_eGon100RE():
     else:
         raise ValueError(f"'{boundary}' is not a valid dataset boundary.")
 
-    # Get allocation of pumped_hydro plants in eGon2035 scenario as the reference
-    # for the distribution in eGon100RE scenario
+    # Get allocation of pumped_hydro plants in eGon2035 scenario as the
+    # reference for the distribution in eGon100RE scenario
     allocation = allocate_pumped_hydro_eGon2035(export=False)
 
     scaling_factor = capacity_phes / allocation.el_capacity.sum()
@@ -412,7 +416,7 @@ def home_batteries_per_scenario(scenario):
     session.commit()
 
 
-def allocate_pv_home_batteries():
+def allocate_pv_home_batteries_to_grids():
 
     home_batteries_per_scenario("eGon2035")
     home_batteries_per_scenario("eGon100RE")