Draft: Rl strategy for household

assume/common/outputs.py

@@ -98,9 +98,6 @@ def __init__(
         self.write_dfs: dict = defaultdict(list)
         self.locks = defaultdict(lambda: Lock())
 
-        if self.db is not None:
-            self.delete_db_scenario(self.simulation_id)
-
         self.kpi_defs: dict[str, OutputDef] = {
             "avg_price": {
                 "value": "avg(price)",
@@ -191,6 +188,8 @@ def setup(self):
     def on_ready(self):
         if self.db_uri:
             self.db = create_engine(self.db_uri)
+        if self.db is not None:
+            self.delete_db_scenario(self.simulation_id)
         if self.save_frequency_hours is not None:
             recurrency_task = rr.rrule(
                 freq=rr.HOURLY,

assume/markets/clearing_algorithms/simple.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
 import logging
+import math
 import random
 from datetime import timedelta
 from itertools import groupby
@@ -445,6 +446,8 @@ def clear(
                 if demand_order["accepted_volume"]:
                     accepted_demand_orders.append(demand_order)
                 accepted_supply_orders.extend(to_commit)
+                if math.isclose(gen_vol, dem_vol, abs_tol=1e-8):
+                    gen_vol, dem_vol = 0, 0
 
             # if demand is fulfilled, we do have some additional supply orders
             # these will be rejected

assume/strategies/__init__.py

@@ -56,10 +56,12 @@
     from assume.strategies.learning_strategies import (
         RLStrategy,
         StorageRLStrategy,
+        HouseholdStorageRLStrategy
     )
 
     bidding_strategies["pp_learning"] = RLStrategy
     bidding_strategies["storage_learning"] = StorageRLStrategy
+    bidding_strategies["household_storage_learning"] = HouseholdStorageRLStrategy
     bidding_strategies["learning_advanced_orders"] = RLAdvancedOrderStrategy
 
 except ImportError: