buzeraandClaude Opus 5.5
c3646ba876
The lag proxy was reset to the new relay command at every relay change and after any skipped interval, so it read 1.0 straight after ON and 0.0 straight after OFF. This disabled the lag model around every boiler cycle: on a synthetic lagged plant cycled by a hysteresis thermostat the learner's heat gain came out 34% low (0.079 vs 0.12) and the loss term 43% low, and the optimizer started post-transition plans from the wrong lag. Track the lag at every poll with a valid relay state, independently of room sensors. Integrate a single change between polls at its last_changed time. For ambiguous cases (round trip between polls, relay outage, restart, clock jump) restart from time-in-state with an explicit error half-width, and learn only once it is at most 0.1 (about 32 min after an HA restart). The same synthetic test now learns 0.1195/0.00389 (true 0.12/0.004). Expose heat_lag, heat_lag_uncertainty and sample_result on Status so users can see why a poll was or was not learned. The HA test fixture relay now has an hour-old timestamp; a new test covers a freshly written relay state. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
294 lines
15 KiB
Python
294 lines
15 KiB
Python
"""Read existing HA entities, learn thermal response, produce shadow MPC decisions."""
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from datetime import datetime, timedelta, timezone
|
|
from functools import partial
|
|
from math import exp, isfinite
|
|
from typing import Any
|
|
|
|
from homeassistant.core import HomeAssistant
|
|
from homeassistant.config_entries import ConfigEntry
|
|
from homeassistant.helpers.storage import Store
|
|
from homeassistant.helpers.update_coordinator import DataUpdateCoordinator
|
|
|
|
from .const import (
|
|
CONF_ROOM_MAX_AGE, CONF_WEATHER_MAX_AGE,
|
|
DOMAIN, CONF_CLIMATE, CONF_HEATER, CONF_ROOMS, CONF_WEIGHTS, WEATHER_SOURCES,
|
|
CONF_HORIZON, CONF_MIN_ON, CONF_MIN_OFF, CONF_SWITCH_COST, CONF_HEAT_COST,
|
|
CONF_BAND, DEFAULTS,
|
|
)
|
|
from .data_quality import freshness
|
|
from .physics import (
|
|
LAG_LEARN_MAX_UNCERTAINTY, LAG_TAU_SECONDS, Learner, advance_lag,
|
|
lag_from_time_in_state, optimize,
|
|
)
|
|
from .weather_sources import choose_weather_sources, sources_for, normalize
|
|
|
|
_LOGGER = logging.getLogger(__name__)
|
|
|
|
|
|
class HeatingMPCCoordinator(DataUpdateCoordinator[dict[str, Any]]):
|
|
"""The existing generic thermostat stays the only actuator owner."""
|
|
|
|
def __init__(self, hass: HomeAssistant, entry: ConfigEntry) -> None:
|
|
super().__init__(hass, _LOGGER, name=DOMAIN, update_interval=timedelta(minutes=5))
|
|
self.entry = entry
|
|
self.config = {**DEFAULTS, **entry.data, **entry.options}
|
|
self.rooms: list[str] = self.config[CONF_ROOMS]
|
|
self.learners: dict[str, Learner] = {room: Learner() for room in self.rooms}
|
|
self._store = Store(hass, 1, f"{DOMAIN}.{entry.entry_id}")
|
|
self._previous: dict[str, Any] | None = None
|
|
# Radiator-lag proxy at the last poll with a valid relay state. Tracked
|
|
# independently of room sensors so lag survives room outages and transitions.
|
|
self._lag: dict[str, Any] | None = None
|
|
self._on_samples = 0
|
|
self._off_samples = 0
|
|
|
|
async def async_restore_model(self) -> None:
|
|
stored = await self._store.async_load() or {}
|
|
if not isinstance(stored, dict) or stored.get("schema_version", 1) not in (1, 2):
|
|
_LOGGER.warning("Ignoring unsupported Heating MPC model data")
|
|
return
|
|
# Replacing the actual heating system invalidates heating coefficients.
|
|
# Switching among weather providers does not discard months of learning.
|
|
if stored.get("heater_entity", self.config[CONF_HEATER]) != self.config[CONF_HEATER]:
|
|
_LOGGER.warning("Heating MPC heater changed; starting a fresh thermal model")
|
|
return
|
|
# Models carry room identity, so changing the room list is safe.
|
|
saved = stored.get("learners", {})
|
|
if not isinstance(saved, dict):
|
|
return
|
|
for room, data in saved.items():
|
|
if room in self.learners:
|
|
self.learners[room] = Learner.from_dict(data)
|
|
self._update_counts()
|
|
|
|
def _update_counts(self) -> None:
|
|
self._on_samples = min(m.on_count for m in self.learners.values())
|
|
self._off_samples = min(m.off_count for m in self.learners.values())
|
|
|
|
def _sensor_quality(self, entity_id: str, now: datetime, limit: float) -> dict:
|
|
state = self.hass.states.get(entity_id)
|
|
if state is None:
|
|
return {"status": "missing", "age_seconds": None}
|
|
if state.state in ("unknown", "unavailable"):
|
|
return {"status": state.state, "age_seconds": None}
|
|
# last_updated is a conservative compatibility fallback for older HA.
|
|
return freshness(getattr(state, "last_reported", getattr(state, "last_updated", None)),
|
|
now, limit * 60)
|
|
|
|
def _track_lag(self, now: datetime, heater_on: bool, last_changed: datetime) -> bool:
|
|
"""Advance the lag proxy to `now`; return True if the relay held one state throughout.
|
|
|
|
A single relay change since the last poll is integrated at its timestamp.
|
|
Anything ambiguous (several changes, an outage, clock jumps) restarts the
|
|
estimate from the time spent in the current state, with an explicit error bound.
|
|
"""
|
|
tracker = self._lag
|
|
steady = False
|
|
lag = uncertainty = None
|
|
if tracker is not None:
|
|
dt = (now - tracker["time"]).total_seconds()
|
|
if dt > 0 and heater_on == tracker["heater_on"] and last_changed <= tracker["time"]:
|
|
lag = advance_lag(tracker["lag"], heater_on, dt)
|
|
steady = True
|
|
elif dt > 0 and heater_on != tracker["heater_on"] and tracker["time"] < last_changed <= now:
|
|
before = (last_changed - tracker["time"]).total_seconds()
|
|
lag = advance_lag(tracker["lag"], tracker["heater_on"], before)
|
|
lag = advance_lag(lag, heater_on, (now - last_changed).total_seconds())
|
|
if lag is not None:
|
|
# The lag update is a contraction, so an initial error decays the same way.
|
|
uncertainty = tracker["uncertainty"] * exp(-dt / LAG_TAU_SECONDS)
|
|
if lag is None:
|
|
lag, uncertainty = lag_from_time_in_state(
|
|
heater_on, (now - last_changed).total_seconds())
|
|
self._lag = {"time": now, "heater_on": heater_on, "lag": lag, "uncertainty": uncertainty}
|
|
return steady
|
|
|
|
async def _async_update_data(self) -> dict[str, Any]:
|
|
now = datetime.now(timezone.utc)
|
|
heater = self.hass.states.get(self.config[CONF_HEATER])
|
|
climate = self.hass.states.get(self.config[CONF_CLIMATE])
|
|
# Choose each weather variable independently from ordered sensor sources.
|
|
# Sensor priorities are editable in Options without touching integration code.
|
|
weather_entity_ids = {
|
|
entity_id for metric in WEATHER_SOURCES
|
|
for entity_id in sources_for(self.config, metric)
|
|
}
|
|
watched = set(self.rooms) | weather_entity_ids | {
|
|
self.config[CONF_CLIMATE], self.config[CONF_HEATER]}
|
|
snapshot = {entity: self.hass.states.get(entity) for entity in watched}
|
|
room_quality = {}
|
|
temps = {}
|
|
for room in self.rooms:
|
|
quality = self._sensor_quality(room, now, self.config[CONF_ROOM_MAX_AGE])
|
|
value = None
|
|
if quality["status"] == "valid":
|
|
state = snapshot[room]
|
|
value = normalize("temperature", state.state, state.attributes.get("unit_of_measurement"))
|
|
if value is None or not 0 <= value <= 45:
|
|
quality["status"] = "invalid_value_or_unit"
|
|
value = None
|
|
room_quality[room] = quality
|
|
temps[room] = value
|
|
weather_states = {}
|
|
weather_quality = {}
|
|
for entity_id in weather_entity_ids:
|
|
quality = self._sensor_quality(entity_id, now, self.config[CONF_WEATHER_MAX_AGE])
|
|
weather_quality[entity_id] = quality
|
|
if quality["status"] == "valid":
|
|
state = snapshot[entity_id]
|
|
weather_states[entity_id] = (state.state, state.attributes.get("unit_of_measurement"))
|
|
weather, active_sources, weather_comparisons = choose_weather_sources(
|
|
self.config, weather_states
|
|
)
|
|
metric_quality = {}
|
|
for metric in WEATHER_SOURCES:
|
|
metric_quality[metric] = {}
|
|
for entity_id in sources_for(self.config, metric):
|
|
quality = dict(weather_quality[entity_id])
|
|
if quality["status"] == "valid" and entity_id not in weather_comparisons[metric]:
|
|
quality["status"] = "invalid_value_or_unit"
|
|
metric_quality[metric][entity_id] = quality
|
|
outside = weather["temperature"]
|
|
status: dict[str, Any] = {
|
|
"input_quality": {"rooms": room_quality, "weather": metric_quality},
|
|
"status": "waiting_for_sensors", "proposal": None, "prediction_60m": {},
|
|
"temperatures": {r: t for r, t in temps.items() if t is not None},
|
|
"on_samples": self._on_samples, "off_samples": self._off_samples,
|
|
"samples": min(learner.count for learner in self.learners.values()),
|
|
"mode": climate.state if climate else "unavailable",
|
|
"weather": {k: v for k, v in weather.items() if v is not None},
|
|
"weather_active_sources": {k: v for k, v in active_sources.items() if v},
|
|
"weather_comparison": {k: v for k, v in weather_comparisons.items() if v},
|
|
"weather_model_inputs": ["temperature"],
|
|
}
|
|
heater_valid = heater is not None and heater.state in ("on", "off")
|
|
heater_on = heater_valid and heater.state == "on"
|
|
steady = False
|
|
if heater_valid:
|
|
steady = self._track_lag(now, heater_on, heater.last_changed)
|
|
status["heat_lag"] = round(self._lag["lag"], 3)
|
|
status["heat_lag_uncertainty"] = round(self._lag["uncertainty"], 3)
|
|
else:
|
|
self._lag = None
|
|
if (not heater_valid or climate is None or outside is None or
|
|
any(temp is None for temp in temps.values())):
|
|
self._previous = None
|
|
return status
|
|
|
|
# No casting surprises: all rooms are valid here.
|
|
vals: dict[str, float] = {room: float(temps[room]) for room in self.rooms}
|
|
if self._previous is None:
|
|
status["sample_result"] = "first_sample"
|
|
else:
|
|
dt = (now - self._previous["time"]).total_seconds()
|
|
# Do not fit across a relay change, a provider/fallback switch or an
|
|
# uncertain lag estimate (restart, relay outage, several changes).
|
|
if not 270 <= dt <= 330:
|
|
status["sample_result"] = "interval_out_of_range"
|
|
elif not steady or heater_on != self._previous["heater_on"]:
|
|
status["sample_result"] = "relay_changed"
|
|
elif self._previous["outside_source"] != active_sources["temperature"]:
|
|
status["sample_result"] = "outside_source_changed"
|
|
elif self._lag["uncertainty"] > LAG_LEARN_MAX_UNCERTAINTY:
|
|
status["sample_result"] = "lag_uncertain"
|
|
else:
|
|
accepted = [
|
|
self.learners[room].learn(
|
|
self._previous["temps"][room], vals[room],
|
|
self._previous["outside"], self._lag["lag"], dt, heater_on)
|
|
for room in self.rooms
|
|
]
|
|
status["sample_result"] = "learned" if all(accepted) else "partly_rejected"
|
|
self._update_counts()
|
|
# Persist at each sample so restart does not erase hours of training.
|
|
await self._store.async_save({
|
|
"schema_version": 2,
|
|
"learners": {room: learner.as_dict() for room, learner in self.learners.items()},
|
|
"on_samples": self._on_samples, "off_samples": self._off_samples,
|
|
"heater_entity": self.config[CONF_HEATER],
|
|
"outside_source": active_sources["temperature"],
|
|
})
|
|
|
|
self._previous = {
|
|
"time": now, "temps": vals, "outside": outside, "heater_on": heater_on,
|
|
"outside_source": active_sources["temperature"],
|
|
}
|
|
weights = self.config.get(CONF_WEIGHTS, {})
|
|
try:
|
|
weights = {r: float(weights.get(r, 1.0)) for r in self.rooms}
|
|
if any(not isfinite(w) or w <= 0 for w in weights.values()) or not isfinite(sum(weights.values())):
|
|
raise ValueError
|
|
except (AttributeError, TypeError, ValueError, OverflowError):
|
|
status["status"] = "invalid_weights"
|
|
return status
|
|
weighted_temp = sum(weights[r] * vals[r] for r in self.rooms) / sum(weights.values())
|
|
status.update({
|
|
"weighted_temperature": round(weighted_temp, 3),
|
|
"outside_temperature": outside,
|
|
"reference_heat": heater_on,
|
|
"on_samples": self._on_samples,
|
|
"off_samples": self._off_samples,
|
|
"samples": min(learner.count for learner in self.learners.values()),
|
|
"models": {
|
|
room: {"loss": round(model.theta[0], 6),
|
|
"heat": round(model.theta[1], 6),
|
|
"bias": round(model.theta[2], 6),
|
|
"samples": model.count,
|
|
"on_samples": model.on_count, "off_samples": model.off_count,
|
|
"mae_5m": round(model.mae, 4) if model.mae is not None else None}
|
|
for room, model in self.learners.items()
|
|
},
|
|
})
|
|
if climate.state != "heat":
|
|
status["status"] = "paused"
|
|
return status
|
|
try:
|
|
target = normalize("temperature", climate.attributes["temperature"],
|
|
climate.attributes.get("temperature_unit",
|
|
self.hass.config.units.temperature_unit))
|
|
if target is None or not 5 <= target <= 35:
|
|
raise ValueError
|
|
except (TypeError, KeyError, ValueError):
|
|
status["status"] = "waiting_for_target"
|
|
return status
|
|
status["target"] = target
|
|
# Do not act on a cold model: need ~17 hours of samples plus both conditions.
|
|
if status["samples"] < 200 or self._on_samples < 30 or self._off_samples < 30:
|
|
status["status"] = "learning"
|
|
return status
|
|
try:
|
|
# 180-minute exhaustive search can take several seconds on RPi5;
|
|
# never block Home Assistant's event loop with CPU work.
|
|
job = partial(
|
|
optimize,
|
|
vals, outside, self._lag["lag"], target, weights, self.learners,
|
|
heater_on, (now - heater.last_changed).total_seconds(),
|
|
horizon_minutes=int(self.config[CONF_HORIZON]),
|
|
minimum_on_minutes=int(self.config[CONF_MIN_ON]),
|
|
minimum_off_minutes=int(self.config[CONF_MIN_OFF]),
|
|
switching_cost=float(self.config[CONF_SWITCH_COST]),
|
|
heating_cost=float(self.config[CONF_HEAT_COST]),
|
|
comfort_band=float(self.config[CONF_BAND]),
|
|
)
|
|
# HA State objects are immutable snapshots. Discard a result if any
|
|
# input changed while the worker was calculating the hypothetical plan.
|
|
output = await self.hass.async_add_executor_job(job)
|
|
if any(self.hass.states.get(entity) is not state for entity, state in snapshot.items()):
|
|
status["status"] = "inputs_changed"
|
|
return status
|
|
except (ValueError, RuntimeError, OverflowError) as err:
|
|
_LOGGER.warning("MPC prediction failed: %s", err)
|
|
status["status"] = "prediction_error"
|
|
return status
|
|
status.update({
|
|
"status": "ready", "proposal": output["proposal"],
|
|
"prediction_60m": output["predicted_60m"],
|
|
"prediction_end": output["predicted_end"],
|
|
"plan_15min": output["plan_15min"], "objective": output["cost"],
|
|
"model_quality_note": "5-minute in-sample MAE; not a validated 60-minute forecast error",
|
|
})
|
|
return status
|