Files
goodwe-addon/goodwe_controller/app/lateness.py
T
glenn schrooyenandClaude c70eeb6916
checks / unit (pull_request) Successful in 23m1s
infra-pin / fresh (pull_request) Successful in 1s
SAFETY-129 round 3: the real reason for the 16 s limit, a slow-start check, the row's tail
Co-Authored-By: Claude <noreply@anthropic.com>
2026-11-07 00:12:33 +01:00

411 lines
18 KiB
Python

"""SAFETY-128: a reading that does not answer the last command is not current.
When Home Assistant delivers readings late but still changing, every gate that
judges arrival (SAFETY-01) or an unchanged value (SAFETY-18, SAFETY-37) passes
them, and the loop corrects again, each cycle, an error its last command has
already fixed. The readings show it: they answer each power request late.
`Answer.watch()` (each 1 s read) fits two delays every FIT_EVERY_S:
- `Delay`: how long after its request each battery's reading shows it. The
house does not move that reading, so a repeating load cannot fool it. It
needs the request to move FIT_MOVE_W; one reading per 10 s makes it slow.
- `MeterFit`: how long after the site request the meter shows it. Quick at a
1-3 s meter, slower and for long lags only at a 5 s one (SAFETY-129), and a
house load that repeats can fool it.
The meter counts only when an ask was slow to start and no battery fit said
"on time"; with hysteresis (ON_S / OFF_S) the result is `late_seen`. Then (`observe()`, each cycle):
- a new command more than ANSWER_W from the battery reading is PENDING until
that reading comes within ANSWER_W of it, or half way;
- while pending the loop may not lead the battery reading by more than
ANSWER_W that way (`hold`, `hold_w`; not while `exempt`: a battery that
gives nothing under its ask or refuses is SAFETY-52/94's case) and the peak
guard may not push past what stands (`peak_cap`). Pending for LATE_S with
no reading moving towards it is LATE: control holds, then 0 W after
`stale_input_s`, as for a missing input.
Not `late_seen`, nothing here acts. DECISIONS/SAFETY-128-late-readings.md.
"""
import bisect
from collections import deque
from . import freshness
from .control import PROBE_ANSWER_W
# Within this of the command the reading has answered it (a probe's answer).
ANSWER_W = PROBE_ANSWER_W # 100
# The slowest healthy battery answer: SAFETY-75's 6 s dead time, the 6 s plant
# settle, one 10 s publish and one 1 s read.
LATE_S = (2 * freshness.PLANT_SETTLE_S + freshness.PUBLISH_PERIOD_S
+ freshness.READ_PERIOD_S) # 23.0
# Each battery reading's delay is fitted over this much history, up to this.
FIT_S = 60.0
MAX_DELAY_S = 90
FIT_EVERY_S = 2.0
# A fit needs this many new readings (all batteries) and this much movement
# of the reading and the request.
FIT_ROWS = 5
FIT_MOVE_W = 3 * ANSWER_W # 300
# Late from ON_S, on time again under OFF_S (hysteresis).
ON_S = 9.5
OFF_S = 6.5
# ...after this many late fits in a row.
ON_FITS = 2
# With no fit for this long the evidence is dropped (a steady site shows none).
FIT_GONE_S = 120.0
# A fit counts only if the commands explain this share of the reading's swing.
FIT_SHARE = 0.5
# A late delay must explain this share.
FIT_SHARE_LATE = 0.75
# ...and a late delay only if it fits this much better than any fresh one.
FIT_BETTER = 0.5
# A shorter delay within this factor of the best fit is taken instead.
FIT_NEAR = 2.0
# ...or within this of it (W^2): two fits this good are both exact.
FIT_FLOOR_W2 = (ANSWER_W / 2) ** 2 # 2 500
def per_second(cmds, first, last):
"""The request standing at each whole second from `first` to `last`."""
ts = [t for t, _c in cmds]
return [cmds[max(0, bisect.bisect_right(ts, k) - 1)][1]
for k in range(first, last + 1)]
def pooled(sets, d):
"""Pooled variance over [(rows, c, first, sign)] of value + sign *
c[t - d], each set about its own mean."""
tot, n = 0.0, 0
for rows, c, first, sign in sets:
e = [v + sign * c[int(t) - d - first] for t, v in rows]
m = sum(e) / len(e)
tot += sum((x - m) ** 2 for x in e)
n += len(e)
return tot / n
class UnitFit:
"""One battery's power requests and readings, as they were seen."""
def __init__(self):
self.cmds = deque() # (t, request) when it changed
self.reads = deque() # (t, reading) when it changed
def add(self, now, cmd, reading):
if cmd is not None and (not self.cmds or self.cmds[-1][1] != cmd):
self.cmds.append((now, float(cmd)))
if reading is not None and (not self.reads
or self.reads[-1][1] != reading):
self.reads.append((now, float(reading)))
while self.reads and self.reads[0][0] < now - FIT_S:
self.reads.popleft()
while (len(self.cmds) > 1
and self.cmds[1][0] <= now - FIT_S - MAX_DELAY_S):
self.cmds.popleft()
def series(self):
"""(rows, request each second, first second) for the fit, or None:
too few new readings, or a reading or a request that has not moved
FIT_MOVE_W. The request is averaged over the 2 s before each second:
the battery's own lag and the read."""
rows = [r for r in self.reads
if self.cmds and r[0] >= self.cmds[0][0] + MAX_DELAY_S]
vals = [v for _t, v in rows]
if len(rows) < 3 or max(vals) - min(vals) < FIT_MOVE_W:
return None
cs = [c for _t, c in self.cmds]
if max(cs) - min(cs) < FIT_MOVE_W:
return None
first, last = int(rows[0][0]) - MAX_DELAY_S - 2, int(rows[-1][0])
c = per_second(self.cmds, first, last)
avg = [c[0], c[0]] + [(c[k - 2] + c[k - 1] + c[k]) / 3
for k in range(2, len(c))]
return rows, avg, first
class Delay:
"""How long after a power request the batteries' readings show it.
A reading follows its battery's own request and the house does not move
it, so `reading(t) - request(t - d)` is flattest at the right `d`. Each new
reading counts once, at the second it was seen, so the 10 s publish adds no
delay. One `d` for every battery (Home Assistant delays them all). None
with too few readings, or when the requests explain too little of them (a
battery that does not follow); not late unless it fits clearly better than
any fresh delay, and then the shortest delay that fits about as well."""
def __init__(self):
self.units = {}
def add(self, now, unit, cmd, reading):
self.units.setdefault(unit, UnitFit()).add(now, cmd, reading)
def estimate(self):
ser = [x for x in (u.series() for u in self.units.values()) if x]
if sum(len(rows) for rows, _c, _f in ser) < FIT_ROWS:
return None
sets = [(rows, c, first, -1.0) for rows, c, first in ser]
r_var = pooled([(rows, [0.0] * len(c), first, -1.0)
for rows, c, first in ser], 0)
pure = [pooled(sets, d) for d in range(0, MAX_DELAY_S + 1)]
# The shortest that fits about as well: a swing's period fits again.
best = next(d for d, v in enumerate(pure)
if v <= FIT_NEAR * min(pure) + FIT_FLOOR_W2)
if r_var <= 0 or pure[best] > (1 - FIT_SHARE) * r_var:
return None
if best < ON_S:
return float(best)
if (pure[best] > (1 - FIT_SHARE_LATE) * r_var
or pure[best] > FIT_BETTER * min(pure[:int(OFF_S) + 1])):
return None
return float(best)
# The meter's delay: fitted over this much history, from this many new
# values (a meter of about 3.5 s or faster; a slower one see M_SLOW_FIT_S);
# late over M_LATE_S (the plant's 6 s settle and one 2 s meter tick), but only
# when the batteries' own readings have not just shown them on time.
M_FIT_S = 60.0
M_ROWS = 16
M_LATE_S = freshness.PLANT_SETTLE_S + 2.0 # 8.0
M_SHARE, M_BETTER = 0.4, 0.7
# SAFETY-129: a meter slower than that (a 5 s P1) has fewer than M_ROWS values
# in M_FIT_S, so it is fitted over M_SLOW_FIT_S instead, from the same M_ROWS
# values. It calls a delay late only over M_SLOW_LATE_S and on ON_FITS fits in
# a row. Alone it reads 35-90 s on healthy runs, a few times in a row; what
# keeps those from a verdict is the slow-start and battery-fit check in
# watch(), not the limit. A 10 s lag is not found: it cannot be told from a
# slow battery (R2-1), nor does it swing at 5 s.
M_SLOW_FIT_S = 120.0
M_SLOW_LATE_S = 16.0
# A meter fit counts only after an ask that took this long to start moving a
# reading: on time they start within 1-2 s (the recorded house, at 1-5 s).
SLOW_START_S = 3.0
class MeterFit:
"""How long after a site request the meter shows it (round 1's fit).
`meter(t) + request(t - d)` is the house alone at the right `d`. Quick,
as the meter reads every 1-5 s, but a house load that repeats can line
up with an earlier request, so it only counts while the batteries' own
fit is not on time (`Answer.watch`)."""
def __init__(self, fit_s=M_FIT_S, late_s=M_LATE_S):
self.fit_s, self.late_s = fit_s, late_s
self.cmds = deque() # (t, request) when it changed
self.grid = deque() # (t, meter) new values only
def slow(self):
"""The meter is too slow for M_ROWS values in `fit_s`: the usual gap
between its new values (median, so a pause does not count) is over
fit_s / M_ROWS."""
ts = [t for t, _g in self.grid]
if len(ts) < 5:
return False
gaps = sorted(b - a for a, b in zip(ts, ts[1:]))
return gaps[len(gaps) // 2] * M_ROWS > self.fit_s
def add(self, now, cmd, grid):
if cmd is not None and (not self.cmds or self.cmds[-1][1] != cmd):
self.cmds.append((now, float(cmd)))
if grid is not None and (not self.grid or self.grid[-1][1] != grid):
self.grid.append((now, float(grid)))
while self.grid and self.grid[0][0] < now - self.fit_s:
self.grid.popleft()
while (len(self.cmds) > 1
and self.cmds[1][0] <= now - self.fit_s - MAX_DELAY_S):
self.cmds.popleft()
def estimate(self):
if len(self.cmds) < 2:
return None
rows = [(t, g) for t, g in self.grid
if t >= self.cmds[0][0] + MAX_DELAY_S]
cs = [c for _t, c in self.cmds]
if len(rows) < M_ROWS or max(cs) - min(cs) < ANSWER_W:
return None
first, last = int(rows[0][0]) - MAX_DELAY_S, int(rows[-1][0])
c = per_second(self.cmds, first, last)
g_var = pooled([(rows, [0.0] * len(c), first, 1.0)], 0)
pure = [pooled([(rows, c, first, 1.0)], d)
for d in range(0, MAX_DELAY_S + 1)]
best = min(range(len(pure)), key=lambda d: (pure[d], d))
if g_var <= 0 or pure[best] > (1 - M_SHARE) * g_var:
return None
if best <= self.late_s:
return float(best)
if pure[best] > M_BETTER * min(pure[:int(self.late_s) + 1]):
return None
return float(best)
class Answer:
"""The answer gate. `observe()` once per cycle, before the loop."""
def __init__(self):
self.ask = None # the pending command, W (site, + = give)
self.from_w = None # the battery reading when it was asked
self.from_grid = None # the meter when it was asked
self.since = None # when it was asked
self.started = False # a reading has moved towards it
self.late_seen = False # the batteries' readings run late
self.late_at = None # when the late verdict started
self.exempt = False # a battery that cannot follow explains it
self._was = None # (command, reading, meter) at the last call
self.delay = Delay()
self.meter = MeterFit()
self.meter_slow = MeterFit(M_SLOW_FIT_S, M_SLOW_LATE_S) # SAFETY-129
self._ms_run = 0 # late slow-meter fits in a row
self._batt_fit = None # (when, d): the batteries' last fit
self._b_run = 0 # late battery fits in a row
self._start_age = None # (when, how long the last ask took to start)
self._exempt_at = None # when a battery last gave nothing under its ask
self._ask_exempt = False
self._start = None
self.delay_s = None # the last fitted delay (either fit), s
self.shown_s = None # the batteries' last late delay, for the page
self.fits = 0 # fits made (instrumentation)
self._fit_at = self._fit_ok = None
@property
def active(self) -> bool:
return self.ask is not None and self.late_seen
@property
def hold(self) -> int:
"""+1 / -1: the loop may not push further that way. 0: no hold."""
if not self.active or self.exempt:
return 0
return 1 if self.ask > self.from_w else -1
@property
def hold_w(self):
"""How far the loop may go while held: ANSWER_W past the reading."""
if not self.hold:
return None
return self._was[1] + self.hold * ANSWER_W
def peak_cap(self, standing_w):
"""The most the peak guard may ask, or None."""
return max(float(standing_w), 0.0) if self.active else None
def late_s(self, now):
"""Seconds the late verdict has stood, or None."""
return None if self.late_at is None else max(0.0, now - self.late_at)
def watch(self, now, units, standing_w=None, grid_w=None):
"""Each read (1 s): `units` = [(name, request on its wire, its battery
reading)], the site request and the meter. Every FIT_EVERY_S, fit both
delays. Late on ON_FITS battery fits from ON_S, or on a meter fit
over M_LATE_S when an ask was slow to start (SLOW_START_S) and no
battery fit within FIT_S said on time: a house load that repeats can
fool the meter fit, not these. A meter too slow for M_ROWS values in
M_FIT_S (a 5 s P1) is fitted over M_SLOW_FIT_S and counts only over
M_SLOW_LATE_S, on ON_FITS fits in a row. On time again on a battery fit
under OFF_S, or a meter fit within M_LATE_S unless a battery fit said
late.
"""
if self._start is None:
self._start = now
for name, cmd, reading in units:
self.delay.add(now, name, cmd, reading)
self.meter.add(now, standing_w, grid_w)
self.meter_slow.add(now, standing_w, grid_w)
if self._fit_at is not None and now - self._fit_at < FIT_EVERY_S:
return
self._fit_at = now
b = self.delay.estimate()
if (b or 0.0) >= ON_S and self._exempt_at is not None \
and now - self._exempt_at <= FIT_S:
b = None # a battery that stopped following: no late fit
m = self.meter.estimate()
ms = None
if self.meter.slow():
ms = self.meter_slow.estimate()
if b is not None:
self._batt_fit = (now, b)
self.shown_s = b if b >= ON_S else None
recent = (self._batt_fit is not None
and now - self._batt_fit[0] <= FIT_S)
b_fresh = recent and self._batt_fit[1] < ON_S
b_late = recent and self._batt_fit[1] >= ON_S
self._b_run = self._b_run + 1 if (b or 0.0) >= ON_S else 0
self._ms_run = self._ms_run + 1 if (ms or 0.0) > M_SLOW_LATE_S else 0
# A slow-meter fit only ever adds a late verdict: it counts as a fit
# when it is late on ON_FITS in a row, and never ends one, so a slow
# battery (R2-1) runs exactly as before.
if self._ms_run < ON_FITS:
ms = None
d = b if b is not None else m if m is not None else ms
if d is None:
if self._fit_ok is None or now - self._fit_ok > FIT_GONE_S:
self.late_seen = False # nothing to tell it by
return
self.fits += 1
self.delay_s, self._fit_ok = d, now
warm = now - self._start >= MAX_DELAY_S + FIT_S
m_late = ((m or 0.0) > M_LATE_S and warm) or (
self._ms_run >= ON_FITS
and now - self._start >= MAX_DELAY_S + M_SLOW_FIT_S)
slow = (self._start_age is not None
and now - self._start_age[0] <= M_FIT_S
and self._start_age[1] >= SLOW_START_S)
if self._b_run >= ON_FITS or (m_late and slow and not b_fresh):
self.late_seen = True
elif (b is not None and b < OFF_S) or (
m is not None and m <= M_LATE_S and not b_late):
self.late_seen = False
def observe(self, now, standing_w, batt_w, *, grid_w=None, exempt=False,
idle_w=0.0):
"""`standing_w` the site command on the wire, `batt_w` the site
battery reading (None: unknown, nothing changes), `grid_w` the meter
(+ = import), `idle_w` what the batteries read while giving nothing.
`exempt`: a battery gives nothing under its ask, or refuses."""
if batt_w is None or standing_w is None:
return
cmd, r = float(standing_w), float(batt_w) - float(idle_w)
g = None if grid_w is None else float(grid_w)
self.exempt = bool(exempt)
if self.exempt:
self._exempt_at = now
was, self._was = self._was, (cmd, r, g)
if self.ask is None:
if was is None or cmd == was[0] or abs(cmd - was[1]) < ANSWER_W:
return
self.ask, self.from_w, self.from_grid = cmd, was[1], was[2]
self.since, self.started = now, False
self._ask_exempt = False
self.ask = cmd
# A battery that gives nothing under its ask explains a slow start.
self._ask_exempt = self._ask_exempt or self.exempt
age = now - self.since
gap = self.ask - self.from_w
way = 1.0 if gap > 0 else -1.0
batt_to = (r - self.from_w) * way
grid_to = (-1e9 if g is None or self.from_grid is None
else (self.from_grid - g) * way)
if not self.started and max(batt_to, grid_to) >= ANSWER_W:
self.started, self.late_at = True, None
self._start_age = (now, 0.0 if self._ask_exempt else age)
elif (not self.started and age >= SLOW_START_S
and not self._ask_exempt):
self._start_age = (now, age)
if (self.ask - r) * way < ANSWER_W or batt_to >= abs(gap) / 2:
self._clear() # answered
elif abs(gap) < ANSWER_W:
self._clear() # withdrawn
elif exempt:
self.late_at = None
elif (self.late_at is None and self.late_seen and not self.started
and age >= LATE_S):
self.late_at = now
def _clear(self):
self.ask = self.from_w = self.from_grid = self.since = None
self.started, self.late_at = False, None