Heating MPC 0.4.0 — custom integration for Home Assistant OS

Experimental, observation-only (shadow mode). It never changes the Generic Thermostat, the physical relay, the boiler's setpoint, heat/off, or Comfort/Away/Sleep. No Docker add-on, MQTT or InfluxDB connection is needed.

This project targets Home Assistant OS on a Raspberry Pi 5, with one existing ON/OFF central-heating relay, generic_thermostat, and individual indoor temperature sensors.

Install / upgrade

1. Create a Home Assistant backup.
2. Copy the entire folder custom_components/heating_mpc into /config/custom_components/heating_mpc (replace its contents when upgrading; read the upgrade notes in CHANGELOG.md first).
3. Restart Home Assistant Core.
4. If new: Settings → Devices & services → Add integration → Heating MPC. If installed already: select Heating MPC → Configure (Options).
5. Choose the existing thermostat and physical heating switch (read-only), then room temperature sensors. Each sensor becomes a zone; group them later (see below).
6. Choose ordered lists of outdoor sensor entity IDs. First valid sensor is active; if missing, unavailable, nonnumeric or outside reasonable bounds, the next valid sensor is used automatically.
7. Assign a relative comfort weight (0.1–10) to each selected sensor's zone.
8. Optionally add zones, heat sources and windows from the integration page (next section).

On Home Assistant 2026.3 or newer the integration shows its own icon (a radiator with a forecast curve) in Devices & services; older versions show a generic placeholder.

No entity IDs are hard-coded. Every sensor, zone, heat source, window and outdoor measurement can be changed later in the UI, without editing YAML or Python.

Zones, heat sources and windows

On Settings → Devices & services → Heating MPC, the buttons Add zone, Add heat source and Add window create items that can each be edited or deleted later. Configure holds everything else: thermostat, relay, weather sources, report-age limits, MPC settings and model options.

Zones are rooms or areas. Each has a name, one or more temperature sensors with sensor weights (how much each counts in the zone temperature), a comfort weight (how much the zone matters to the MPC), an optional target offset relative to the thermostat's target, and optional adjacent zones it exchanges heat with. Sensor and comfort weights never change the learned thermal coefficients. A sensor belongs to one zone only. Upgrading from 0.3 turns each room sensor into a one-sensor zone with the same comfort weight; to group two sensors of one room, edit one zone to include both and delete the other.

Heat sources are equipment whose electricity ends up as heat in a zone, such as a UPS feeding computers. Settings: an active-power sensor (W or kW; VA and % are rejected), the zone, the share of the power that becomes heat there (1.0 by default), the baseline (automatic: the low end of the last 24 hours; or a manual value in W), whether its reading is already included in another source (for a PC measured separately behind a UPS, so it is not counted twice), and the thermal response time (default 15 minutes). Only the variation above the baseline is modeled; the persistent load is already part of the zone's learned behavior.

Windows need a contact sensor (binary sensor), the zone, whether the sensor reports on when closed (inverted), the direction the outside of the window faces (degrees clockwise from north; default 345°, editable) and an opening factor (1.0 normal, lower for tilted, higher for large). Unknown or unavailable states are treated as unknown, never as closed.

Model options in Configure: how fast extra electrical heat is assumed to fade in forecasts (half-life, default 30 minutes), how long an open window is assumed to stay open (default 15 minutes), the recovery time constant after closing (default 20 minutes), and whether to use wind, wind gusts and cross-ventilation terms. See docs/MODEL.md for the equations and what is learned when.

Reconfigurable weather inputs

Measurement	Required?	Used in the thermal model?
Outdoor temperature	Yes (1–10 prioritized sensors)	Yes: estimates thermal losses; constant over the 2 h forecast window
Wind speed	No	Yes, for open windows (ventilation), when enabled
Wind direction (degrees the wind comes from)	No	Yes, with the windows' facing direction
Wind gust	No	Only if the gust option is enabled
Cloud cover	No	No, diagnostics/source comparison only
Humidity	No	No, diagnostics/source comparison only
Feels-like temperature	No	No, diagnostics/source comparison only
Atmospheric pressure	No	No, diagnostics/source comparison only
Visibility	No	No, diagnostics/source comparison only
Rain / snow	No	No, diagnostics/source comparison only

Choose multiple sensors for a single variable, e.g. OpenWeatherMap then another provider, in priority order. Switch order in Configure to run A/B comparisons on successive days, or simply let the second sensor act as fallback. The active source and all current alternative readings are visible in the Heating MPC Status entity attributes (weather, weather_active_sources, weather_comparison). The MPC Outdoor Temperature sensor also has an active_source attribute and an alternatives map.

Measurements are normalized where possible: outdoor temperatures to °C; wind and gusts to m/s (from km/h, mph, kn, ft/s); wind direction to degrees (360 = 0); pressure to hPa; visibility to meters. Unknown units or values outside plausibility bounds are rejected in favor of the next selected sensor. Clouds and humidity are expected in %, rain/snow in mm or mm/h as represented by their upstream sensor. A fallback source may have a different sampling delay; configurable report-age limits now reject stale inputs (see below).

Switching only the weather-provider sensors does not reset learned thermal parameters. The update is applied after the integration reloads, and it skips learning one transition when the primary temperature source changes, avoiding a jump in the training series. Nevertheless, two sensors with a persistent offset can bias predictions; compare their readings and validate the model again before relying on them. Replacing the physical heating switch discards incompatible model parameters. Learned zone parameters are kept as long as the zone exists (its key does not change when you edit it).

Model, sampling and output

• Every 5 minutes: reads sensor, relay, power and window states and learns a per-zone model in layers (full description in docs/MODEL.md):
  • base: dT = loss*(T_out-T) + heat*lag + bias, always learned, the fallback and comparison;
  • extended: adds electrical heat above baseline and exchange with adjacent zones;
  • ventilation: learned separately while a window is open or the room recovers, so open windows never look like poor insulation.
• New effects start at zero and report a confidence; nothing is assumed until the data shows it. Relay changes are timestamped by a read-only state listener.
• After 200 samples per zone, including both relay states, runs an ON/OFF MPC search for the next 60–180 minutes (default 120) in 15-minute command blocks, simulating all zones together with assumed electrical heat and window behavior.
• Uses zone comfort weights and target offsets with the existing Generic Thermostat's target and heat/off state. The simulated ON/OFF demand never operates hardware.
• Persists everything learned in HA's .storage. Models of zones removed in the UI are kept (up to 24) and restored if the zone is added back.

Entities (entity IDs may vary):

• sensor.heating_mpc_status — learning/ready/paused status and diagnostics, including outside weather, active source, all valid alternative weather values, model coefficients, proposed 15-minute plan.
• sensor.heating_mpc_weighted_temperature — comfort-weighted average of the zones, informative only.
• sensor.mpc_outdoor_temperature — selected external temp and alternatives.
• One forecast entity per zone (MPC 60min Prediction), state = the zone's temperature in 60 minutes. Attributes: current_temperature, forecast (+15/+30/ +60/+120 minutes as far as the horizon goes), forecast_15min, plan_15min, model_in_use, contributions_c_per_h (what drives the zone right now: loss, heat, bias, internal, neighbors, ventilation, recovery) and coefficients with confidence. Plan forecasts assume the MPC's plan is executed; while Generic Thermostat controls the relay they are counterfactual.
• binary_sensor.heating_mpc_proposed_heat — hypothetical heating demand (unavailable until ready).
• Heating MPC Learning Progress — how close the least trained zone is to being used for forecasts (100 % = ready); attributes show the sample counts and what is required.
• Heating MPC Last Sample — what the last poll did for learning (for example Learned, Relay switched, Waiting for radiators to settle); its history shows when learning happens.
• Heating MPC Forecast Error 15/30/60/120 min — how far the thermal model's forecasts were from what actually happened (see Forecast accuracy).

Known limitations / safety

• Do not connect the proposed binary sensor directly to the heating switch or build an automation from it. A production controller would need watchdog, manual override, safety handling, and an exclusive relay owner with Generic Thermostat fallback.
• Weather variables other than temperature, wind and gusts are captured but not fitted. Wind and gusts are used only for open windows. Keep optional model terms only when Forecast Error shows they help (improvement_vs_base).
• One temperature per zone (no separate wall mass), configured response times, and single-scenario forecasts of electrical heat and windows. See docs/MODEL.md.
• All rooms share one heating actuator. The model does not command individual radiators.
• No weather forecast: assumes outdoor temperature remains constant during simulated horizon.
• No Recorder/InfluxDB training backfill. It learns only from samples collected after installation.
• The demand switch is not a burner-flame or real gas consumption measurement.
• Not yet tested on HAOS or with real devices. Automated tests run the integration in a Home Assistant Core test harness (HA 2025.12.0 and 2026.2.3) with simulated entities.
• Home Assistant Core APIs and config-flow selectors can change; take a backup before trying this experimental custom integration.

Diagnostics

Start with Learning Progress and Last Sample. For details, open the Heating MPC Status entity's attributes. In recent Home Assistant versions Developer Tools is at the bottom of Settings (or press Cmd/Ctrl+K and type "developer"); its States tab lists every attribute.

Why learning starts about 30 minutes after a restart. The model learns how much the radiators warm each room, so it needs to know how warm the radiators are. It estimates this from when the relay last switched (20-minute time constant). After a Home Assistant restart that time is unknown, so learning waits until the estimate is within 10 % (Waiting for radiators to settle), about 32 minutes. Forecasts continue meanwhile. Reloading the integration usually does not cause this wait, because the relay's last change is still known. Ready then needs 200 accepted samples (about 17 hours) per zone, including 30 with the relay ON and 30 with it OFF, which can take a few days depending on how often the boiler runs.

The Heating MPC Status entity's state is one of waiting_for_sensors, no_zones (add a zone), learning, paused (thermostat not in heat), waiting_for_target, ready, inputs_changed or prediction_error. Proposed heat is available only while it is ready. Useful attributes:

• input_quality — per zone (with each of its sensors) and per weather source (grouped by metric): status (valid, missing, unknown, unavailable, stale, invalid_timestamp, future_timestamp or invalid_value_or_unit), age_seconds (time since the sensor last reported to HA) and max_age_seconds_24h (largest age seen at polls in the last 24 hours; resets on reload and can read up to one poll, 5 minutes, low). Zones and sensors have used.
• excluded_zones and weight_coverage — zones left out of this poll, and the share of the total comfort weight still covered by the zones used (1.0 = all). zone_names maps zone keys to names.
• heat_sources — per source: measured and effective power (after removing included sources), baseline, variable power above it, thermal response, whether it has settled.
• windows — per window: state, minutes open, wind direction relative to the window's facing and the resulting exposure (1 = wind straight at it). ventilation — per zone: current opening, recovery, temperature before opening, its contribution in °C/h and the ventilation coefficients. ventilation_events — the last five openings with temperatures before, lowest, at closing and 30 minutes after, and the weather.
• heat_lag and heat_lag_uncertainty — the radiator-lag estimate (0 cold, 1 fully warm) and its error bound. Learning waits while the bound is above 0.1, for example for about 30 minutes after an HA restart.
• sample_result — why the last poll was or was not learned: first_sample, sensors_changed (a zone's set of usable sensors changed), learned, ventilation (only window-affected zones; given to the ventilation model), partly_rejected (an outlier in some zone), interval_out_of_range, relay_changed, outside_source_changed, lag_uncertain or waiting_for_inputs.
• models — per-zone base coefficients, accepted sample counts and the in-sample 5-minute error (mae_5m, not a forecast accuracy), model_in_use and the extended layer's coefficients with confidence.
• retired_zone_models — removed zones whose learned models are kept.

input_quality, weather_comparison, heat_sources, windows, ventilation and ventilation_events change every poll, so they are not written to the Recorder; the other attributes are.

Choosing freshness limits

Room and weather report-age limits are set during setup and in Configure (5–1440 minutes; defaults 30 for rooms and 120 for weather).

A zone sensor that is older than its limit, unavailable, missing or invalid is left out; the zone uses its other sensors (without learning across that change). A zone with no usable sensor is left out entirely: the weighted temperature, learning and forecasts continue with the other zones, whose weights are re-normalized. Status shows it in excluded_zones. Learning and forecasts pause only when no zone is usable, or when the relay, thermostat or outdoor temperature is missing. A zone that reports again learns from its second poll onwards, so nothing is learned across its gap.

The checkbox Keep using the last value of a room sensor that stopped reporting changes this for stale sensors: their last value is still used, for up to 24 hours without a report. Use it for sensors that report only when the value changes. Unavailable or invalid sensors are always left out, and so is any sensor silent for more than 24 hours, since it is most likely dead.

A stale outdoor source falls back to the next one in its list; optional weather metrics never block.

Within the limit (or with the checkbox on), the last reading counts as current, so a frozen value can be learned for a while. A too-tight limit (with the checkbox off) drops a room whenever its sensor is quietly between reports. Freshness uses HA's last_reported: the time a sensor last reported to HA, even with an unchanged value. It is not the age of the physical measurement, so a provider re-publishing cached data looks fresh, and sensors that report only on change can look stale in a steady room.

After a day of running, set each limit comfortably above (about 1.5–2×) the largest max_age_seconds_24h among the sensors it covers. The relay and thermostat have no age limit.

Forecast accuracy

The four Forecast Error sensors measure the thermal model against reality, continuously and out of sample. At every poll the integration records each zone's reading, the outdoor temperature, the radiator-lag estimate and the model's parameters. 15, 30, 60 and 120 minutes later it replays the zones from the earlier reading using the parameters it had then, the outdoor temperature held at its starting value, and the radiator heat that actually followed from the relay's real ON/OFF history. The result is compared with the current reading.

This tests the thermal model, not the MPC plan, because the plan is never executed. All zones are replayed together, with the electrical heat and window openings that actually happened, and the base model is scored on the same spans. Each sensor's state is the mean absolute error (°C) over the last 7 days, across all zones. Attributes, all in °C except counts:

• samples — number of scored forecasts. Consecutive forecasts overlap, so they are not independent; treat small counts as indicative only.
• bias — mean error: negative means the model predicts too cold.
• persistence_mae — error of simply assuming no change; the baseline to beat.
• skill — 1 - mae / persistence_mae: 1 is perfect, 0 is no better than assuming no change, negative is worse. Empty while the temperature did not change.
• base_model_mae, improvement_vs_base — the base model's error on the same spans, and the share of it the extra layers remove (0 = no gain, negative = they make it worse: switch that option off).
• zones — the same numbers per zone (not written to the Recorder).

Forecasts are scored only where the inputs were known: polls 4.5–5.5 minutes apart, a usable reading at the start and the end, and a well-known radiator-lag estimate throughout. A missing relay, outdoor temperature or all zones restarts the replay window, so scores resume 15–120 minutes later. Statistics are kept with the model and survive restarts; deleting the model resets them.

What it does not cover: outdoor temperature changes during the horizon (held constant, as in the MPC), and periods when the model was still learning (included, so early numbers are pessimistic). The roadmap's working target is about 0.3–0.4 °C at 60 minutes with clearly positive skill, before any control is considered.

Release notes

See CHANGELOG.md for changes and upgrade notes per version, and AUDIT.md for audit findings and test evidence.

Developer checks and Forgejo/Gitea Actions

The HA Core test suite runs against Home Assistant 2025.12.0 (the minimum in hacs.json, requirements-test.txt) and 2026.2.3 (newest published test fixtures, requirements-test-latest.txt), both on Python 3.13. Use a dedicated development virtual environment; these test dependencies are not installed with the integration and do not change its local, standard-library model inference.

python3.13 -m venv .venv
. .venv/bin/activate
python -m pip install -r requirements-test.txt   # or requirements-test-latest.txt
sh scripts/check.sh

The check script runs dependency consistency checks, the offline tests, the HA Core tests, compilation, package metadata, translation and changelog checks, and diff whitespace checks. The 2025.12.0 requirements pin a compatible DNS library because pycares 5 breaks that release's dependency. The script also disables a transitive HA test dependency's optional metadata download. The offline tests also run without Home Assistant installed:

python -m unittest discover -s tests -v

The brand icons in custom_components/heating_mpc/brand/ are drawn by python scripts/make_brand_icons.py (uses Pillow from the test requirements); the package check verifies their sizes and transparency.

HA tests cover setup, config/options forms, migration, reload and entity cleanup, scheduled sampling and poll cancellation, the relay listener, stored model restoration, retention and deletion, missing inputs, manual off/presets, optimizer failure and Recorder exclusions. A fixture rejects all HA service calls throughout each test, and a static test fails if actuator service calls are added to the source. HA Core runs locally with simulated input entities and mocked storage I/O; this does not validate HAOS, physical devices, disk failures or full process restarts.

.gitea/workflows/tests.yml runs the same checks for both HA versions on pushes and pull requests, on the dedicated bs-node Actions runner label (bs-node:docker://node:22-bookworm). Repository Actions must be enabled, and the runner must support the checkout and setup-uv actions. CI uses pinned uv 0.9.6 to create a Python 3.13 virtual environment from standalone Python builds; setup-python cannot provision this version in the Debian Bookworm job image. Action caching is disabled to avoid requiring GitHub cache services on Gitea. Dependencies, Python builds and action downloads need internet access in CI; model inference does not. Remote CI execution has not yet been verified; local validation used macOS.