feat(validate): CPUC Baseline Generator List capacity benchmark (CPUC stack 5/5)

docs/source/configtables/run.csv

@@ -4,3 +4,4 @@ disable_progrssbar,bool,"{true, false}",Switch to select whether progressbar sho
 shared_resources,bool,"{true, false}",Switch to select whether resources should be shared across runs.
 shared_cutouts,bool,"{true, false}",Switch to select whether cutouts should be shared across runs.
 validation,bool,"{true, false}",Switch to enable back-casting validation plotting
+benchmark_cpuc,bool,"{true, false}",Switch to enable the CPUC Baseline Generator List capacity benchmark (California runs)

workflow/Snakefile

@@ -258,13 +258,36 @@ def validation_figures(wildcards):
         return []
 
 
+BENCHMARK_CPUC_OUTPUTS = [
+    "cpuc_capacity_benchmark.csv",
+    "cpuc_capacity_deviation.pdf",
+]
+
+
+def benchmark_figures(wildcards):
+    """CPUC Baseline Generator List capacity benchmark, opt-in via run.benchmark_cpuc.
+
+    Gated on its own flag rather than on the demand profile: the fleet
+    benchmark is useful for any California run, whatever drives its load.
+    """
+    if not config["run"].get("benchmark_cpuc", False):
+        return []
+    return expand(
+        RESULTS
+        + "{interconnect}/figures/s{simpl}_cluster_{clusters}/l{ll}_{opts}_{sector}/benchmark/{figure}",
+        **config["scenario"],
+        figure=BENCHMARK_CPUC_OUTPUTS,
+    )
+
+
 rule all:
     input:
         #"repo_data/dag.jpg",
         electricity_statistics,
         electricity_figures,
         sector_figures,
         validation_figures,
+        benchmark_figures,
 
 
 rule data_model:

workflow/repo_data/CPUC/servm_benchmark_regions.csv

@@ -0,0 +1,8 @@
+servm_region,eia_ba_code,benchmark_region,note
+PGE,CISO,CAISO,EIA reports every CAISO plant under the single BA code CISO; PGE/SCE/SDGE cannot be split without geography
+SCE,CISO,CAISO,rolled into CAISO for the same reason
+SDGE,CISO,CAISO,rolled into CAISO for the same reason
+LADWP,LDWP,LADWP,
+IID,IID,IID,
+NCNC,BANC,NCNC,Balancing Authority of Northern California
+NCNC,TIDC,NCNC,Turlock Irrigation District

workflow/repo_data/CPUC/servm_tech_map.csv

@@ -0,0 +1,52 @@
+side,source_category,compare_category,note
+cpuc,CC,Gas CC,
+cpuc,CT,Gas CT/ICE/Steam,
+cpuc,ICE,Gas CT/ICE/Steam,
+cpuc,Steam,Gas CT/ICE/Steam,CA gas steam boilers; EIA maps 'Natural Gas Steam Turbine' to OCGT so it cannot be split out on the model side
+cpuc,Cogen,Gas Cogen/CHP,CPUC-only bucket; EIA/PyPSA carriers have no CHP concept so these units land in CCGT/OCGT on the model side
+cpuc,Coal,Coal,
+cpuc,Nuclear,Nuclear,
+cpuc,Geothermal,Geothermal,
+cpuc,Biomass/Wood,Biomass,
+cpuc,Biogas,Biomass,
+cpuc,Hydro,Hydro,
+cpuc,PSH,PSH,
+cpuc,Wind,Wind,
+cpuc,OOS_Wind,Wind,out-of-state wind contracted to a CA region; absent from the CA subset of the 2026 baseline
+cpuc,Solar_1Axis,Solar,
+cpuc,Solar_Fixed,Solar,
+cpuc,Solar_2Axis,Solar,
+cpuc,Solar_Thermal,Solar,
+cpuc,Paired_Solar_1Axis,Solar,
+cpuc,Paired_Solar_Fixed,Solar,
+cpuc,Hybrid_Solar_1Axis,Solar,
+cpuc,Hybrid_Solar_Fixed,Solar,
+cpuc,Battery_4h,Battery,
+cpuc,Paired_BattStorage,Battery,
+cpuc,Hybrid_BattStorage,Battery,
+cpuc,DR,Demand Response,CPUC-only; PyPSA-USA has no demand-response resource
+cpuc,Pumping_Load,Pumping Load,CPUC-only; modelled as load rather than as a resource in PyPSA-USA
+pypsa,CCGT,Gas CC,
+pypsa,CCGT-95CCS,Gas CC,
+pypsa,OCGT,Gas CT/ICE/Steam,EIA 'Natural Gas Steam Turbine' / 'Combustion Turbine' / 'Internal Combustion Engine' all map here
+pypsa,hydrogen_ct,Gas CT/ICE/Steam,
+pypsa,coal,Coal,
+pypsa,nuclear,Nuclear,
+pypsa,geothermal,Geothermal,
+pypsa,EGS,Geothermal,
+pypsa,biomass,Biomass,
+pypsa,waste,Biomass,municipal solid waste; CPUC folds it into Biogas
+pypsa,hydro,Hydro,pumped storage is split off before mapping via prime_mover_code == PS
+pypsa,PHS,PSH,
+pypsa,onwind,Wind,
+pypsa,offwind,Wind,
+pypsa,offwind_floating,Wind,
+pypsa,solar,Solar,
+pypsa,battery,Battery,
+pypsa,2hr_battery_storage,Battery,
+pypsa,4hr_battery_storage,Battery,
+pypsa,6hr_battery_storage,Battery,
+pypsa,8hr_battery_storage,Battery,
+pypsa,10hr_battery_storage,Battery,
+pypsa,oil,Oil,model-only; CPUC has no oil bucket for CA
+pypsa,other,Other,"model-only catch-all (flywheels, other gases, compressed air)"

workflow/repo_data/config/config.default.yaml

@@ -34,6 +34,7 @@ run:
   shared_resources: false         # true = reuse resources/ across all runs (DAG-keyed); false = isolate per run.name
   shared_cutouts: true            # true = share atlite cutouts across runs (recommended; cutouts are large and slow)
   validation: false               # true = wire in back-casting validation plots (historical-only)
+  benchmark_cpuc: false           # true = compare installed capacity against the CPUC Baseline Generator List (California runs)
 
 # ====================================================================
 # RENEWABLE DATASET — capacity-factor source for wind & solar

workflow/rules/validate.smk

@@ -66,3 +66,32 @@ rule plot_validation_figures:
         mem_mb=5000,
     script:
         "../scripts/plot_validation_production.py"
+
+
+# Compares installed capacity against the CPUC Baseline Generator List,
+# aggregated by SERVM benchmark region and technology, per planning horizon.
+# Gated by run.benchmark_cpuc (see benchmark_figures in the Snakefile).
+rule benchmark_cpuc_baseline:
+    params:
+        planning_horizons=config_provider("scenario", "planning_horizons"),
+    input:
+        network=NETWORKS
+        + "{interconnect}/elec_s{simpl}_c{clusters}_ec_l{ll}_{opts}_{sector}.nc",
+        powerplants="resources/powerplants/powerplants.csv",
+        cpuc_baseline=DATA + "cpuc/BaselineGeneratorList_CAISO.xlsx",
+        region_map="repo_data/CPUC/servm_benchmark_regions.csv",
+        tech_map="repo_data/CPUC/servm_tech_map.csv",
+    output:
+        comparison=RESULTS
+        + "{interconnect}/figures/s{simpl}_cluster_{clusters}/l{ll}_{opts}_{sector}/benchmark/cpuc_capacity_benchmark.csv",
+        heatmap=RESULTS
+        + "{interconnect}/figures/s{simpl}_cluster_{clusters}/l{ll}_{opts}_{sector}/benchmark/cpuc_capacity_deviation.pdf",
+    log:
+        LOGS
+        + "benchmark_cpuc_baseline/{interconnect}/elec_s{simpl}_c{clusters}_l{ll}_{opts}_{sector}.log",
+    threads: 1
+    resources:
+        walltime="00:20:00",
+        mem_mb=5000,
+    script:
+        "../scripts/benchmark_cpuc_baseline.py"