energy-systems-ai999x — offline, verified energy systems solver with step-by-step answers

Install · Capability guide · Evaluation · AI999X on Hugging Face · Website · Support: Buy Me a Coffee

License: Apache-2.0 · Author: Ibnul Jaif Farabi (creator and engineer) · Organization: AI999X · Version 1.0.3

Field: Engineering · Tasks: Question Answering, Token Classification, Text Classification, Sentence Similarity, Feature Extraction

energy-systems-ai999x is an offline, deterministic Python solver that answers energy systems questions with verified results from 79 certified capabilities, gives 311 documented answers identically on Windows and Linux, and refuses rather than guesses when an answer cannot be verified.

energy-systems-ai999x is a compact, deterministic energy systems engine for Python. It reads a question in plain English (or a typed call), picks a certified energy systems capability, computes the answer exactly, checks it, and returns the result with its steps, units, LaTeX and assumptions — or an honest refusal that says what is missing. It runs fully offline on any CPU, needs no GPU, no API key and no internet, and is built to give zero wrong answers: when it is not sure, it refuses instead of guessing.

Highlights

• Verified, not generated. Every answer is computed by a certified energy systems capability and checked (substituted back, dimension-checked or compared with an independent computation) before it is returned.
• Zero wrong answers by design. Seven explicit outcomes — SOLVED, NEEDS_INPUT, AMBIGUOUS, INVALID_INPUT, OUT_OF_SCOPE, UNRECOGNIZED_FORMAT, INTERNAL_ERROR — never a silent guess. Every one of its 311 documented answers is reproduced exactly on every tested platform.
• Plain-English questions and a guaranteed typed interface. ask() reads documented question forms; solve(capability_id, **inputs) always solves a supported task with valid inputs.
• Explains itself. Steps, formulas in LaTeX, units, assumptions and the model used, ready for notebooks, tutoring apps and homework checkers.
• Small and portable. Pure Python (sympy, mpmath); identical answers on Windows and Linux (Python 3.10, 3.11, 3.12, 3.13, 3.14).
• Coverage: solar resource and photovoltaics, wind power, three-phase power, transmission lines, load flow and economic dispatch, faults and stability, transformers and machines, batteries, fuel cells and hydrogen.

Model overview

Property	Value
Package	energy-systems-ai999x 1.0.3 (import energy_systems_ai999x)
Type	Deterministic neuro-symbolic energy systems engine (rule-based reading + certified symbolic capabilities)
Capabilities	79 certified procedures
Knowledge pack	version 1.0.1
Golden answers	311 documented answers, identical on every tested platform
Platforms tested	Windows (Python 3.13), Linux x86-64 (Python 3.10, 3.11, 3.12, 3.13, 3.14)
Runtime	CPU only, offline; no GPU, no network, no API key
License	Apache-2.0
Creator / engineer	Ibnul Jaif Farabi
Organization	AI999X

Quickstart

pip install energy-systems-ai999x

import energy_systems_ai999x as energy_systems

energy_systems.ask("Three-phase power: VL = 400 V, IL = 50 A, pf = 0.8, connection = star").show()
# -> SOLVED — P = 27712.8, Q = 20784.6, S = 34641, V_phase = 230.94  (energy_three_phase_power)
energy_systems.ask("Solar position: latitude = 40, longitude = -105, n = 172, clock = 13:00, utc_offset = -7").show()
# -> SOLVED — declination_deg = 23.452, eot_min = -1.34372, hour_angle_deg = 14.6641, zenith_deg = 20.66  (energy_solar_position)
energy_systems.ask("Power in the wind: rho = 1.225 kg/m^3, D = 80 m, v = 10 m/s, cp = 0.4").show()
# -> SOLVED — P_wind = 3.07876e+06, P_betz = 1.82445e+06, power_density = 612.5, area = 5026.55  (energy_wind_power)
energy_systems.ask("Hydrogen tank: V = 125 L, p = 700 bar, T = 15 degC").show()
# -> SOLVED — rho = 40.1722, Z = 1.46617, mass = 5.02152, rho_ideal = 58.8992  (energy_hydrogen_tank)
energy_systems.solve("energy_economic_dispatch", costs="500 5.3 0.004 200 450; 400 5.5 0.006 150 350; 200 5.8 0.009 100 225", demand=800).show()
# -> SOLVED — lambda_ = 8.5, P = [400.0, 250.0, 150.0], cost = 6682.5  (energy_economic_dispatch)
energy_systems.ask("Who created you?").message
# -> energy-systems-ai999x was created and engineered by Ibnul Jaif Farabi at AI999X.

Command line: energy-systems-ai999x "<question>", energy-systems-ai999x --capabilities. The outputs above were produced by running this exact code on energy-systems-ai999x 1.0.3.

Find the right capability, and draw it

energy_systems.search() finds which certified capability a question is about — across every AI999X model, so a question for another model points you to it. It runs ai999x-encoder, AI999X's own capability encoder (4.7M parameters, a 4.9 MB ONNX model, offline; the root model.safetensors of this repository): pip install "energy-systems-ai999x[search]". ask(question, suggest=True) adds the same pointers to a question it does not answer; an answer itself never changes.

import energy_systems_ai999x as energy_systems

energy_systems.search("Solve x^2 - 5x + 6 = 0", k=2)
# -> Roots of a quadratic equation (math-foundations-ai999x, 0.63); Roots of a cubic equation (math-foundations-ai999x, 0.59)

How every answer is verified

1. Reading — the question is turned into typed quantities (value, unit, kind, role) and one asked quantity; every stated number must be used or the question is refused.
2. Planning — only certified capabilities may answer; a capability applies only under the conditions the wording states (for example a pendulum, a liquid at rest, boiling).
3. Computing — exact symbolic or high-precision numeric evaluation.
4. Checking — dimensions, substitution back into the defining equation, and agreement between independent readings; any disagreement becomes a refusal, never a number.

Capabilities are certified before they ship: each must reproduce hand-worked reference cases, reject a deliberately wrong variant (a control), and leave every benchmark answer unchanged.

Worked examples

Each question was put to energy-systems-ai999x; the answer is the one it returned, with the steps it took.

Balanced three-phase power from line quantities · Three-phase power

Three-phase power: VL = 400 V, IL = 50 A, pf = 0.8, connection = star

→ P = 27712.81292 W, Q = 20784.60969 var, S = 34641.01615 VA, V_phase = 230.9401077 V, I_phase = 50 A

Steps

• Balanced three-phase power from line quantities: VL = 400 V, IL = 50 A, pf = 0.8, connection = star → P = 27712.81292 W, Q = 20784.60969 var, S = 34641.01615 VA, V_phase = 230.9401077 V, I_phase = 50 A

Sun position at a place and local time · Solar resource

Solar position: latitude = 40, longitude = -105, n = 172, clock = 13:00, utc_offset = -7

→ declination_deg = 23.45204607, eot_min = -1.343724732, hour_angle_deg = 14.66406882, zenith_deg = 20.66003785, elevation_deg = 69.33996215, azimuth_deg = 221.165265

Steps

• Sun position at a place and local time: latitude = 40, longitude = -105, n = 172, clock = 13, utc_offset = -7 → declination_deg = 23.45204607, eot_min = -1.343724732, hour_angle_deg = 14.66406882, zenith_deg = 20.66003785, elevation_deg = 69.33996215, azimuth_deg = 221.165265

Power in the wind and the Betz limit · Wind power

Power in the wind: rho = 1.225 kg/m^3, D = 80 m, v = 10 m/s, cp = 0.4

→ P_wind = 3078760.801 W, P_betz = 1824450.845 W, power_density = 612.5, area = 5026.548246 m^2, P = 1231504.32 W

Steps

• Power in the wind and the Betz limit: rho = 1.225 kg/m^3, D = 80 m, v = 10 m/s, cp = 0.4 → P_wind = 3078760.801 W, P_betz = 1824450.845 W, power_density = 612.5 W, area = 5026.548246 m^2, P = 1231504.32 W

Hydrogen stored in a tank at pressure (real gas) · Hydrogen

Hydrogen tank: V = 125 L, p = 700 bar, T = 15 degC

→ rho = 40.17216108 kg/m^3, Z = 1.466169638, mass = 5.021520135 kg, rho_ideal = 58.89920286 kg/m^3, mass_ideal = 7.362400358 kg, ideal_over_real = 1.466169638, energy_LHV_kWh = 167.3289261

Steps

• Hydrogen stored in a tank at pressure (real gas): V = 125 L, p = 700 bar, T = 15 degC → rho = 40.17216108 kg/m^3, Z = 1.466169638 kg, mass = 5.021520135 kg, rho_ideal = 58.89920286 kg/m^3, mass_ideal = 7.362400358 kg, ideal_over_real = 1.466169638 kg, energy_LHV_kWh = 167.3289261 kg

Economic dispatch with quadratic costs and limits · Power systems

m.solve("energy_economic_dispatch", costs="500 5.3 0.004 200 450; 400 5.5 0.006 150 350; 200 5.8 0.009 100 225", demand=800)

→ lambda_ = 8.5, P = [400, 250, 150], cost = 6682.5

Steps

• Economic dispatch with quadratic costs and limits: costs = [500 5.3 0.004 200 450; 400 5.5 0.006 150 350; 200 5.8 0.009 100 225], demand = 800 → lambda_ = 8.5, P = [400, 250, 150], cost = 6682.5

Battery pack series-parallel sizing · Batteries

Battery pack sizing: V_target = 48 V, E_target = 10 kWh, V_cell = 3.2 V, Q_cell = 100 Ah

→ N_series = 15, N_parallel = 3, N_cells = 45, V_pack = 48 V, E_pack_kWh = 14.4, Q_pack_Ah = 300

Steps

• Battery pack series-parallel sizing: V_target = 48 V, E_target = 10 kWh, V_cell = 3.2 V, Q_cell = 360000 C → N_series = 15, N_parallel = 3, N_cells = 45, V_pack = 48 V, E_pack_kWh = 14.4, Q_pack_Ah = 300

Figures

Every point was computed by energy-systems-ai999x.

Photovoltaic module: current–voltage curve and maximum power

Current–voltage curve of a PV module (single-diode model: photocurrent 9 A, saturation current 1.0000e-10 A, Rs = 0.3 Ω, Rsh = 400 Ω), computed by the package at 81 voltages. The shaded rectangle is the maximum power the package finds, P = 335.252 W at V = 39.6025 V, I = 8.46542 A; it fills 0.778276 of Isc × Voc (8.99326 A × 47.8984 V), the fill factor.

Wind turbine power curve

Wind turbine output against wind speed from the tabulated power curve (speeds 3, 5, 8, 12, 25 m/s, powers 0, 150, 800, 2000, 2000 kW), computed by the package at 121 speeds from 0 to 30 m/s: nothing below cut-in at 3 m/s, rated 2000 kW up to cut-out at 25 m/s, nothing above. Marked: v = 6.5 m/s, P = 475 kW.

The Sun's path across the sky: polar sky chart

The Sun's path across the sky at latitude 40°, longitude -105° (UTC-7) on three days: azimuth around the rim (N at the top) and elevation inward (rings at 0°, 30° and 60°), computed by the package every 15 minutes while the Sun is up; dots every 2 h of clock time. Highest computed elevations: 21 June 73.4496°, 22 March 50.2928°, 21 December 26.5781°. Marked: 21 June at 13 h, elevation 69.34°, azimuth 221.165°.

Economic dispatch: three generators sharing a load

Economic dispatch of 3 generators with quadratic cost curves (rows a, b, c, Pmin, Pmax: 500 5.3 0.004 200 450; 400 5.5 0.006 150 350; 200 5.8 0.009 100 225) meeting a demand of 800 MW: the package returns outputs 400, 250, 150 MW (bars, dashed lines the limits) at a common incremental cost λ = 8.5 per MWh, total cost 6682.5 per hour.

Wind speed with height: the shear profile as arrows

Wind speed at nine heights extrapolated from 5 m/s measured at 10 m, drawn as arrows whose length is the speed: logarithmic law (roughness length 1 m) and power law (exponent 0.333333), each computed by the package. At 100 m: 10 and 10.7722 m/s; at 150 m: 10.8805 and 12.3311 m/s.

Capabilities

79 certified procedures. A few of them:

• Procedures: AC load flow by Newton-Raphson; Actuator-disc (momentum theory) rotor performance; Air density at hub height; Angle of incidence of the sun on a tilted surface; Annual energy production from a power curve and a Weibull distribution; Balanced three-phase power from line quantities; Base impedance and per-unit impedance; Battery pack series-parallel sizing; Battery terminal voltage under constant current (one-RC equivalent circuit); Clear-sky global horizontal irradiance (Haurwitz); Clear-sky irradiance (Ineichen-Perez with Linke turbidity); Combined PV system losses (PVWatts); Critical clearing angle and time (equal-area criterion); DC power flow; Diffuse and direct irradiance from global horizontal irradiance (Erbs); Direct normal irradiance from global horizontal irradiance (DISC model); Double line-to-ground fault (symmetrical components); Economic dispatch with quadratic costs and limits; Electrical power of a fuel-cell or electrolyser stack; Equation of time; Extraterrestrial (top-of-atmosphere) normal irradiance; Frequency deviation and load sharing under governor droop; Geometric mean distance of a three-phase line; Hydrogen fuel-cell stack: consumption, power and efficiency …

energy_systems_ai999x.templates() lists every question form ask() reads; the capability guide (PDF, every example executed) is included in this repository.

Out of scope

• Open-ended explanation, essay writing or tutoring dialogue: it is a solver, not a chatbot.
• Questions outside its certified energy systems capabilities, and any question whose stated numbers it cannot all use — it refuses with the reason instead.
• High-stakes engineering, medical or legal decisions without independent review.

Limitations

• It answers what its certified capabilities cover (solar resource and photovoltaics, wind power, three-phase power, transmission lines, load flow and economic dispatch, faults and stability, transformers and machines, batteries, fuel cells and hydrogen); anything else is refused with a reason.
• ask() reads documented question forms and common phrasings; unusual wording may be refused — use solve() for guaranteed results.
• Results are as correct as the certified relations and their stated conditions; a certified relation is a checked model, not a claim about every physical situation.

Citation

@software{energy_systems_ai999x_1_0_3,
  title  = {energy-systems-ai999x: an offline, verified energy systems solver},
  author = {Farabi, Ibnul Jaif}, organization = {AI999X},
  year   = {2026}, version = {1.0.3},
  url    = {https://huggingface.co/AI999X/energy-systems-ai999x}
}

Contact

Questions, bug reports and requests: open a discussion on https://huggingface.co/AI999X/energy-systems-ai999x/discussions or visit https://ai999x.com.

Support the project

energy-systems-ai999x is free and open source. If it helps you, you can support further development on Buy Me a Coffee.

Created and engineered by Ibnul Jaif Farabi · AI999X · ai999x.com