tune forecast correction parametersw

db/routines/R__078_fn_pv_forecast_delta_profile.sql

@@ -3,12 +3,17 @@
 -- (aditivní korekce: corrected = max(0, forecast - delta[slot]))
 -- ============================================================
 
+drop function if exists ems.fn_pv_forecast_delta_profile;
+
 create or replace function ems.fn_pv_forecast_delta_profile(
   p_site_id int,
   p_data_from timestamptz,
   p_data_to timestamptz default now(),
   p_half_life_days numeric default 14,
-  p_threshold_w int default 150
+  p_threshold_w int default 150,
+  p_top_n_days int default null,
+  p_non_top_day_factor numeric default 0.02,
+  p_day_weight_gamma numeric default 1.0
 )
 returns jsonb
 language sql
@@ -143,22 +148,45 @@ as $fn$
     left join day_jump dj on dj.day_local = de.day_local
     left join day_med dm on dm.day_local = de.day_local
   ),
+  -- Volitelně: jen top N kalendářních dní podle (w_energy * w_smooth); zbytek ztlumit (bez hardcodu data).
+  day_rank as (
+    select
+      ds.day_local,
+      row_number() over (
+        order by
+          (coalesce(ds.w_energy, 0.35) * coalesce(ds.w_smooth, 0.35)) desc,
+          ds.day_local desc
+      ) as rn
+    from day_stats ds
+  ),
   filtered as (
     select
       s.slot_of_day,
       (s.forecast_total_w - s.actual_total_w) as error_w,
       exp(-s.age_days / nullif((select half_life_days from bounds), 0))
+        * (
+          case
+            when p_top_n_days is null then 1::numeric
+            when p_top_n_days < 1 then 1::numeric
+            when dr.rn <= p_top_n_days then 1::numeric
+            else greatest(0::numeric, least(1::numeric, coalesce(p_non_top_day_factor, 0.02)))
+          end
+        )
         * (
           0.05
           + 0.95
-            * greatest(
-              0.0,
-              least(1.0, coalesce(ds.w_energy, 0.35) * coalesce(ds.w_smooth, 0.35))
+            * power(
+              greatest(
+                0.0,
+                least(1.0, coalesce(ds.w_energy, 0.35) * coalesce(ds.w_smooth, 0.35))
+              ),
+              greatest(0.25, least(coalesce(p_day_weight_gamma, 1.0), 8.0))
             )
         ) as w
     from slots s
     cross join bounds b
     left join day_stats ds on ds.day_local = s.day_local
+    left join day_rank dr on dr.day_local = s.day_local
     where s.slot_of_day between 0 and 95
       and (s.actual_total_w > b.threshold_w or s.forecast_total_w > b.threshold_w)
   ),
@@ -200,5 +228,5 @@ as $fn$
   left join agg a on a.slot_of_day = sp.slot_of_day;
 $fn$;
 
-comment on function ems.fn_pv_forecast_delta_profile(int, timestamptz, timestamptz, numeric, int) is
-  'Aditivní delta profil chyby PV forecastu po 15min slotu dne (96 slotů). Zdroj: forecast_accuracy, vážení exp(-age/half_life_days) * day_weight (preferuje „clear-ish“ dny: vyšší denní energie vs median v okně + nižší median skoků výkonu mezi 15min v daylight bandu). Vrací JSON {deltas:[{slot_of_day, delta_w, sample_count}], ...}. Interní minimální cutoff dat (2026-04-11 Europe/Prague) brání učení z nekonzistentní historie před kompletním plněním actual.';
+comment on function ems.fn_pv_forecast_delta_profile is
+  'Aditivní delta profil chyby PV forecastu po 15min slotu dne (96 slotů). Zdroj: forecast_accuracy, vážení exp(-age/half_life_days) * day_weight (clear-ish dny) * volitelně top_n_days (jen N nejlepších kalendářních dní podle w_energy*w_smooth, ostatní ztlumené) * power(day_weight, day_weight_gamma). Vrací JSON {deltas:[{slot_of_day, delta_w, sample_count}], ...}. Cutoff dat od 2026-04-11 Europe/Prague.';

db/routines/R__079_fn_forecast_pv_slots_range_corrected.sql

@@ -3,6 +3,8 @@
 -- corrected = max(0, forecast - delta_profile[slot_of_day])
 -- ============================================================
 
+drop function if exists ems.fn_forecast_pv_slots_range_corrected;
+
 create or replace function ems.fn_forecast_pv_slots_range_corrected(
   p_site_id int,
   p_from timestamptz,
@@ -10,7 +12,10 @@ create or replace function ems.fn_forecast_pv_slots_range_corrected(
   p_delta_data_from timestamptz,
   p_delta_data_to timestamptz default now(),
   p_half_life_days numeric default 14,
-  p_threshold_w int default 150
+  p_threshold_w int default 150,
+  p_top_n_days int default null,
+  p_non_top_day_factor numeric default 0.02,
+  p_day_weight_gamma numeric default 1.0
 )
 returns jsonb
 language sql
@@ -67,7 +72,10 @@ as $fn$
       p_delta_data_from,
       p_delta_data_to,
       p_half_life_days,
-      p_threshold_w
+      p_threshold_w,
+      p_top_n_days,
+      p_non_top_day_factor,
+      p_day_weight_gamma
     ) as j
   ),
   deltas as (
@@ -119,5 +127,5 @@ as $fn$
   left join fc on fc.interval_start = s.interval_start;
 $fn$;
 
-comment on function ems.fn_forecast_pv_slots_range_corrected(int, timestamptz, timestamptz, timestamptz, timestamptz, numeric, int) is
-  'JSON pole {interval_start, pv_forecast_total_w, pv_forecast_corrected_w, slot_of_day} po 15 min pro [p_from, p_to). Korekce je aditivní delta profil z fn_pv_forecast_delta_profile. Horizont je omezený na max. 60 dní.';
+comment on function ems.fn_forecast_pv_slots_range_corrected is
+  'JSON pole {interval_start, pv_forecast_total_w, pv_forecast_corrected_w, slot_of_day} po 15 min pro [p_from, p_to). Korekce je aditivní delta profil z fn_pv_forecast_delta_profile (top_n_days / non_top_day_factor / day_weight_gamma). Horizont je omezený na max. 60 dní.';