Source code for energy_analysis.pv_device_reliability

"""PV-specific reliability evidence and reproducible, explicitly scoped cases."""

from __future__ import annotations

import argparse
import json
from pathlib import Path
from typing import Any, cast

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

from energy_data_retrieval.pv_reliability_database import (
    load_pv_reliability_evidence,
    pv_reliability_sources,
)
from energy_methods.pv_device_reliability import assembly_event_scenario
from energy_methods.reliability_algorithms import repairable_availability

REFERENCE_IDS = (
    "baschel_2018_reliability",
    "lillo_2018_failures",
    "bucher_2022_inverter_survival",
    "martins_2026_tracker_availability",
    "brown_2026_weather_station_longevity",
    "deline_2026_pv_fleet",
)


[docs] def published_rate_scenarios() -> pd.DataFrame: """Recalculate constant-rate scenarios, excluding internally conflicting rows. Each row is a separate benchmark; alternative sources are never pooled. Per-year values use the source's 4015 operating hours. Probabilities are model-derived, not observed annual failure fractions or warranty estimates. """ data = load_pv_reliability_evidence(metric="failure_rate") data = data.loc[data.quality_flags.map(len) == 0].copy() data["model_events_per_year"] = data.value * data.operating_hours_per_year data["model_probability_one_year"] = -np.expm1(-data.model_events_per_year) data["model_mtbf_operating_years"] = 1 / data.model_events_per_year return data.reset_index(drop=True)
[docs] def combiner_box_case(*, boxes: int = 500) -> tuple[pd.DataFrame, dict[str, float]]: """Illustrative CBX bill of materials using disjoint, attributed part rates. Twenty-four string fuses, 48 lugs, one SMU and one DC switch per box. Not a reproduction of a particular OEM design, nor whole-box outage risk. No tracker/WST proxy rates or assumed repair costs are inserted. """ if isinstance(boxes, bool) or not isinstance(boxes, int) or boxes <= 0: raise ValueError("boxes must be a positive integer") data = published_rate_scenarios().set_index("record_id") keys = ["baschel_2018:t1-20", "baschel_2018:t1-10", "baschel_2018:t1-22", "baschel_2018:t1-23"] parts = data.loc[keys, ["device", "value", "evidence_origin"]].reset_index() parts["parts_per_box"] = [24, 48, 1, 1] parts["events_per_box_year"] = parts.value * parts.parts_per_box * 4015 scenario = assembly_event_scenario( parts.value.to_numpy(), parts.parts_per_box.to_numpy(), operating_hours_per_year=4015 ) scenario["boxes"] = boxes scenario["fleet_expected_component_events_per_year"] = ( boxes * scenario["expected_events_per_year"] ) return parts, scenario
[docs] def repair_time_sensitivity() -> pd.DataFrame: """Synthetic 10 MW fleet: restoration sensitivity, not a site forecast. Assumed constant calendar-up-time failure rate 0.04 per unit-year, with exponential restoration. Counterfactual fleet output follows an artificial 12-hour sinusoidal day, repeated for 365 days. Identical unit availability multiplies total fleet output in expectation; no shared crews/common cause. Neither the rate, repair durations nor production profile is field evidence. """ hour = np.arange(8760) + 0.5 power = 10000 * np.maximum(0, np.sin((hour % 24 - 6) * np.pi / 12)) rows = [] for restore in [8, 24, 72, 168]: model = repairable_availability(0.04 / 8760, restore, np.ones(8760), power) rows.append( dict( mean_restore_hours=restore, assumed_rate_per_unit_year=0.04, mean_availability=float(model.mean_availability.mean()), baseline_energy_mwh=float(model.baseline_energy_kwh.sum() / 1000), expected_energy_loss_mwh=float(model.expected_energy_loss_kwh.sum() / 1000), input_kind="synthetic_scenario", ) ) return pd.DataFrame(rows)
[docs] def plot_pv_reliability_evidence() -> plt.Figure: """Four panels with source-specific units; no universal device ranking.""" data = load_pv_reliability_evidence() fig, axes = plt.subplots(2, 2, figsize=(14, 10), layout="constrained") fig.suptitle("PV reliability: four different evidence types", fontsize=18, weight="bold") ax = axes[0, 0] rates = published_rate_scenarios() names = [ "PV module", "PV connector", "String fuse", "String monitoring unit", "String inverter", "Central inverter", "DC capacitor", "IGBT module", "Central control board", "Transformer", ] rates = rates[rates.device.isin(names) & rates.selected_in_source.eq(True)].copy() rates = rates.sort_values("value") colors = rates.evidence_origin.map({"juwi_field": "#117b88", "cited_literature": "#bd6b2e"}) ax.barh(rates.device, rates.value * 1e6, color=colors) ax.set_xscale("log") ax.set_xlabel("Events per million operating hours (log scale)") ax.set_title( "Component rates • Baschel 2018\nTeal: field; orange: cited literature", fontsize=11 ) ax.grid(axis="x", alpha=0.2) ax = axes[0, 1] medians = data[(data.source_id == "martins_2026") & (data.statistic == "median")] for i, mode in enumerate(["ALL", "CORE"]): subset = medians[medians.method == mode].set_index("missing_data_assumption") low = float(cast(float, subset.at["unavailable", "value"])) high = float(cast(float, subset.at["available", "value"])) ax.barh(i, low * 100, color="#117b88") ax.barh(i, (high - low) * 100, left=low * 100, color="#c9dfe1", hatch="///") ax.text(high * 100 + 1, i, f"{low:.0%}-{high:.0%}", va="center") ax.set_yticks([0, 1], ["All tracking", "Core tracking"]) ax.set_xlim(0, 108) ax.set_xlabel("Published median availability (%)") ax.set_title( "Tracker angle KPI • Martins 2026\nHatched span: missing-data assumptions, not a CI", fontsize=11, ) ax = axes[1, 0] inv = data[data.source_id == "bucher_2022"].sort_values("age_years") ax.scatter(inv.age_years, inv.value * 100, s=90, color="#117b88", zorder=3) row = inv[inv.age_years == 18].iloc[0] ax.errorbar( [18], [row.value * 100], yerr=[[100 * (row.value - row.lower)], [100 * (row.upper - row.value)]], fmt="none", color="#117b88", capsize=7, ) for _, row in inv.iterrows(): ax.annotate( f"{row.value:.1%}", (row.age_years, row.value * 100), xytext=(8, 8), textcoords="offset points", ) ax.set(xlim=(13, 20), ylim=(45, 80), xlabel="Age (years)", ylabel="First-event survival (%)") ax.set_title( "Inverter survival • Bucher 2022\n2,121 units; only 15 at risk at year 18", fontsize=11 ) ax.grid(alpha=0.2) ax = axes[1, 1] stations = data[data.metric == "individual_observed_age"].sort_values("value") for i, (_, row) in enumerate(stations.iterrows()): marker = {"event": "x", "right_censored": ">", "event_age_lower_bound": ">"}[ row.observation_status ] color = "#bd6b2e" if row.observation_status == "event" else "#117b88" ax.scatter(row.value, i, marker=marker, s=65, color=color) ax.set_yticks(range(len(stations)), stations.device + " / " + stations.unit_id) ax.set(xlim=(0, 15), xlabel="Observed years; x stopped, > follow-up / lower bound") ax.set_title( "Unmaintained WSTs • Brown 2026\nIndividual cases; unit-count inconsistency flagged", fontsize=11, ) ax.grid(axis="x", alpha=0.2) return fig
[docs] def run_study(output: Path) -> dict[str, Any]: """Export typed source evidence and the CBX case, without network calls.""" output.mkdir(parents=True, exist_ok=True) evidence = load_pv_reliability_evidence() sources = pv_reliability_sources() rates = published_rate_scenarios() parts, scenario = combiner_box_case() repair = repair_time_sensitivity() evidence.to_parquet(output / "pv_reliability_evidence.parquet", index=False) evidence.to_json(output / "pv_reliability_evidence.json", orient="records", indent=2) sources.to_json(output / "sources.json", orient="records", indent=2) rates.to_csv(output / "component_rate_scenarios.csv", index=False) evidence[evidence.quality_flags.map(len) > 0].to_json( output / "quality_audit.json", orient="records", indent=2 ) parts.to_csv(output / "combiner_parts.csv", index=False) repair.to_csv(output / "synthetic_repair_sensitivity.csv", index=False) summary = { "sources_reviewed": len(sources), "evidence_records": len(evidence), "metric_counts": evidence.metric.value_counts().to_dict(), "unflagged_rate_alternatives": len(rates), "combiner_case": scenario, "synthetic_repair_sensitivity": repair.to_dict(orient="records"), "interpretation": "Historical benchmarks and explicit assumptions; not OEM predictions.", } (output / "summary.json").write_text(json.dumps(summary, indent=2) + "\n") figure = plot_pv_reliability_evidence() figure.savefig(output / "pv_reliability_evidence.png", dpi=160) plt.close(figure) return summary
[docs] def main() -> None: """Run with ``python -m energy_analysis.pv_device_reliability``.""" parser = argparse.ArgumentParser(description=__doc__) parser.add_argument("--output", type=Path, default=Path("artifacts/pv-device-reliability")) print(json.dumps(run_study(parser.parse_args().output), indent=2))
if __name__ == "__main__": main()