ES vis

v2/architecture.py

@@ -95,6 +95,8 @@ def simulator(battery_model, prod_cons, decider):
 
     discarded_production_series = [] # solar power thrown away
 
+    decisions = []
+
     # 1 is not nominal but targeted (healthy) maximum charge.
     # we start with an empty battery, but not emptier than what's healthy for the batteries.
 
@@ -123,6 +125,7 @@ def simulator(battery_model, prod_cons, decider):
         cons_prediction = demand_prediction_np[i: i + decider.input_window_size]
         consumption_fees = consumption_fees_np[i: i + decider.input_window_size]
         decision = decider.decide(prod_prediction, cons_prediction, consumption_fees, battery_model)
+        decisions.append(decision)
 
         production_used_to_charge = 0
         if unsatisfied_demand >= remaining_production:
@@ -169,6 +172,8 @@ def simulator(battery_model, prod_cons, decider):
     consumption_from_network_series = np.array(consumption_from_network_series)
     consumption_from_bess_series = np.array(consumption_from_bess_series)
     discarded_production_series = np.array(discarded_production_series)
+    decisions = np.array(decisions)
+    
 
     consumption_from_network_pandas_series = pd.Series(consumption_from_network_series, index=prod_cons.index)
 
@@ -197,10 +202,10 @@ def simulator(battery_model, prod_cons, decider):
                             'consumption_from_network_to_bess_series': consumption_from_network_to_bess_series,
                             'discarded_production': discarded_production_series,
                             'Consumption': prod_cons['Consumption'],
-                            'Production': prod_cons['Production']
+                            'Production': prod_cons['Production'],
+                            'decisions': decisions
                             })
     results = results.set_index(prod_cons.index)
-    # results['soc_series'].plot() ; plt.show() ; exit()
     return results, total_network_fee
 
 

v2/decider.py

@@ -53,12 +53,13 @@ class Decider:
         mean_surdemand_kw = (cons_pred[:surdemand_window] - prod_pred[:surdemand_window]).mean()
 
         current_fee = fees[0]
-        # TODO this should not be a hard threashold, and more importantly,
+        # TODO this should not be a hard threshold, and more importantly,
         # it should not be hardwired.
         HARDWIRED_THRESHOLD_FOR_CHEAP_POWER_HUF_PER_KWH = 20 # [HUF/kWh]
         if mean_surdemand_kw > self.lookahead_surdemand_kw and current_fee <= HARDWIRED_THRESHOLD_FOR_CHEAP_POWER_HUF_PER_KWH:
             return Decision.NETWORK_CHARGE
 
+        # peak shaving
         if deficit_kwh > self.precalculated_supplier.peak_demand:
             return Decision.DISCHARGE
         else:
@@ -80,6 +81,6 @@ class Decider:
         # surdemand_lookahead_window_min, lookahead_surdemand_kw
         # param1 [minutes]. one day mean, half day scale for lookahead horizon.
         # param2 [kWh], averaged over the horizon. negative values are meaningful.
-        init_mean = np.array([1440.0, 0.0])
-        init_scale = np.array([720.0, 100.0])
+        init_mean = np.array([60 * 24.0, 0.0])
+        init_scale = np.array([60 * 12.0, 100.0])
         return init_mean, init_scale

v2/evolution_strategies.py

@@ -1,4 +1,8 @@
 import numpy as np
+import matplotlib.pyplot as plt
+
+
+DO_VIS = True
 
 
 # in-place
@@ -11,7 +15,7 @@ def evolution_strategies_optimizer(objective_function, clipper_function, init_me
     # Initialize parameters
     population_size = 100
     number_of_generations = 30
-    mutation_scale = 0.1
+    mutation_scale = 0.05
     selection_ratio = 0.5
     selected_size = int(population_size * selection_ratio)
 
@@ -28,7 +32,7 @@ def evolution_strategies_optimizer(objective_function, clipper_function, init_me
         selected = population[selected_indices]
         
         # Reproduce (mutate)
-        offspring = selected + np.random.randn(selected_size, 2) * mutation_scale
+        offspring = selected + np.random.normal(loc=0, scale=init_scale * mutation_scale, size=(selected_size, len(init_mean)))
         clip_params(offspring, clipper_function) # in-place
         
         # Replacement: Here we simply generate new candidates around the selected ones
@@ -40,6 +44,19 @@ def evolution_strategies_optimizer(objective_function, clipper_function, init_me
         best_index = np.argmin(fitness)
         best_solution = population[best_index]
         print(f"Generation {generation + 1}: Best Fitness = {best_fitness}", f"Best solution so far: {best_solution}")
+        if DO_VIS:
+            plt.scatter(population[:, 0], population[:, 1])
+            plt.xlim(-5, 5)
+            plt.ylim(-5, 5)
+            x = np.linspace(-5, 5, 100)
+            y = np.linspace(-5, 5, 100)
+            XY = np.stack(np.meshgrid(x, y), axis=-1)
+            print(XY.shape)
+
+            # Defining the function (x - 3)**2 + (y + 2)**2
+            Z = toy_objective_function(XY)
+            contour = plt.contour(XY[..., 0], XY[..., 1], Z, levels=50)
+            plt.show()
 
 
     # Best solution
@@ -50,7 +67,7 @@ def evolution_strategies_optimizer(objective_function, clipper_function, init_me
 
 
 def toy_objective_function(x):
-    return (x[0] - 3)**2 + (x[1] + 2)**2
+    return (x[..., 0] - 3)**2 + (x[..., 1] + 2)**2
 
 
 def toy_clipper_function(x):