update the csv file output code and add a progress bar in the code

EnergySystem.py

@@ -21,6 +21,13 @@ class EnergySystem:
         self.summer_week_soc = []
         self.autumn_week_soc = []
         self.winter_week_soc = []
+        self.factory_demand = []
+        self.buy_price_kWh = []
+        self.sell_price_kWh = []
+        self.pv_generated_kWh = []
+        self.grid_need_power_kW = []
+        self.time = []
+        self.ess_rest = 0
         self.granularity = 4
         self.season_step = self.granularity * 24 * 7 * 12
         self.season_start= self.granularity * 24 * 7 * 2
@@ -35,9 +42,14 @@ class EnergySystem:
     # 如果ESS也不足以满足需求，再从电网获取 - 当ESS中的存储电量也不足以补充时，再从电网购买剩余所需电量。
     def simulate(self, data, time_interval):
         total_benefit = 0
+        total_netto_benefit = 0
+        total_gen = 0
+        net_grid = 0.
         for index, row in data.iterrows():
             time = row['time']
-            sunlight_intensity = row['sunlight']
+            self.time.append(time)
+            # sunlight_intensity = row['sunlight']
+            pv_yield = row['PV yield[kW/kWp]']
             factory_demand = row['demand']
             electricity_price = row['buy']
             sell_price = row['sell']
@@ -53,8 +65,13 @@ class EnergySystem:
                 soc = self.ess.storage / self.ess.capacity
                 self.hour_stored_2.append(soc)
 
-            generated_pv_power = self.pv.capacity * sunlight_intensity  # 生成的功率，单位 kW
+            generated_pv_power = self.pv.capacity * pv_yield# 生成的功率，单位 kW
             generated_pv_energy = generated_pv_power * time_interval * self.pv.loss  # 生成的能量，单位 kWh
+            self.pv_generated_kWh.append(generated_pv_energy)
+            self.factory_demand.append(factory_demand)
+            self.buy_price_kWh.append(electricity_price)
+            self.sell_price_kWh.append(sell_price)
+
             self.generated += generated_pv_energy
             # pv生成的能量如果比工厂的需求要大
             if generated_pv_energy >= factory_demand * time_interval:
@@ -72,6 +89,7 @@ class EnergySystem:
                 # 节省的能量 = 工厂需求的能量 * 时间段
                 # total_energy = factory_demand * time_interval
                 saved_energy = factory_demand * time_interval
+                self.grid_need_power_kW.append(0)
             # pv比工厂的需求小
             else:
                 # 从ess中需要的电量 = 工厂需要的电量 - pv中的电量
@@ -87,6 +105,7 @@ class EnergySystem:
                     self.ess.storage -= discharging_power
                     # 节省下来的能量 = pv的能量 + 放出来的能量
                     saved_energy = generated_pv_energy + discharging_power * self.ess.loss
+                    self.grid_need_power_kW.append(0)
                 else:
                     # 如果存的电量不够
                     # 需要把ess中的所有电量释放出来
@@ -103,15 +122,18 @@ class EnergySystem:
                     self.ess.storage = 0
                     needed_from_grid = factory_demand * time_interval - saved_energy
                     net_grid = min(self.grid.capacity * time_interval, needed_from_grid) * self.grid.loss
+                    self.grid_need_power_kW.append(needed_from_grid * 4)
                     # grid_energy += net_grid
                     # total_energy += net_grid
             # print(total_energy)
             # 工厂需求量-总能量
             # unmet_demand = max(0, factory_demand * time_interval - total_energy)
             # benefit = (total_energy - unmet_demand) * electricity_price
+            total_gen += saved_energy
             benefit = (saved_energy) * electricity_price
             cost = net_grid * electricity_price
             # print(f"time:{time} benefit: {benefit}, cost: {cost}")
+            total_netto_benefit += benefit
             total_benefit += benefit - cost
             # # spring
             week_start = self.season_start
@@ -119,6 +141,7 @@ class EnergySystem:
             if index in range(week_start, week_end):
                 self.spring_week_gen.append(generated_pv_power)
                 self.spring_week_soc.append(self.ess.storage / self.ess.capacity)
+            self.ess_rest = self.ess.storage
             # summer
             # week_start += self.season_step
             # week_end += self.season_step
@@ -137,4 +160,4 @@ class EnergySystem:
             #     self.winter_week_gen.append(generated_pv_power)
             #     self.winter_week_soc.append(self.ess.storage / self.ess.capacity)
 
-        return total_benefit
+        return (total_benefit, total_netto_benefit, total_gen)

config.json

@@ -17,12 +17,12 @@
     "pv_capacities":{
         "begin": 0,
         "end": 50000,
-        "groups": 5 
+        "groups":  3
     },
     "ess_capacities":{
         "begin": 0,
         "end": 100000,
-        "groups": 10 
+        "groups":  3
     },
     "time_interval":{
         "numerator": 15,
@@ -31,7 +31,8 @@
     "annotated": {
         "unmet_prob": false,
         "benefit": false,
-        "cost": false 
+        "cost": false,
+        "roi": false 
     },
     "figure_size":{
         "height": 9,
@@ -40,6 +41,13 @@
     "plot_title":{
         "unmet_prob": "Coverage Rate of Factory Electrical Demands",
         "cost": "Costs of Microgrid system [m-EUR]",
-        "benefit": "Financial Profit Based on Py & Ess Configuration (k-EUR / year)"
+        "benefit": "Financial Profit Based on Py & Ess Configuration (k-EUR / year)",
+        "roi": "ROI"
+    },
+    "data_path": {
+        "pv_yield": "read_data/Serbia.csv",
+        "demand": "read_data/factory_power1.csv",
+        "sell": "read_data/electricity_price_data_sell.csv",
+        "buy": "read_data/electricity_price_data.csv"
     }
 }

config.py

@@ -10,12 +10,12 @@ class pv_config:
     def get_cost_per_year(self):
         return self.capacity * self.cost_per_kW / self.lifetime
 class ess_config:
-    def __init__(self, capacity, cost_per_kW, lifetime, loss, charge_power, discharge_power):
+    def __init__(self, capacity, cost_per_kW, lifetime, loss, charge_power, discharge_power, storage=0):
         self.capacity = capacity
         self.cost_per_kW = cost_per_kW
         self.lifetime = lifetime
         self.loss = loss
-        self.storage = 0
+        self.storage = storage
         self.charge_power = charge_power
         self.discharge_power = discharge_power
     def get_cost(self):

main.py

@@ -1,12 +1,21 @@
 #!/usr/bin/env python
 # coding: utf-8
 
-# In[14]:
+# In[83]:
 
 
 import os
 import glob
 import shutil
+import matplotlib.pyplot as plt
+import matplotlib.ticker as ticker
+from matplotlib.ticker import FuncFormatter
+import numpy as np
+import pandas as pd
+import os
+import seaborn as sns
+import json
+from matplotlib.colors import LinearSegmentedColormap
 
 def clear_folder_make_ess_pv(folder_path):
     if os.path.isdir(folder_path):
@@ -19,7 +28,7 @@ folder_path = 'plots'
 clear_folder_make_ess_pv(folder_path)
 
 
-# In[15]:
+# In[84]:
 
 
 import matplotlib.pyplot as plt
@@ -30,18 +39,21 @@ from EnergySystem import EnergySystem
 from config import pv_config, grid_config, ess_config
 
 
-# In[16]:
+# In[85]:
 
 
 import json
 
-print("Version 0.0.2")
+print("Version 0.0.5")
 
 with open('config.json', 'r') as f:
     js_data = json.load(f)
 
-data = pd.read_csv('combined_data.csv')
+
+    
+
 time_interval = js_data["time_interval"]["numerator"] / js_data["time_interval"]["denominator"]
+# print(time_interval)
 
 pv_loss = js_data["pv"]["loss"]
 pv_cost_per_kW = js_data["pv"]["cost_per_kW"]
@@ -66,22 +78,45 @@ ess_groups = js_data["ess_capacities"]["groups"]
 annot_unmet = js_data["annotated"]["unmet_prob"]
 annot_benefit = js_data["annotated"]["benefit"]
 annot_cost = js_data["annotated"]["cost"]
+annot_roi = js_data["annotated"]["roi"]
 
 title_unmet = js_data["plot_title"]["unmet_prob"]
 title_cost = js_data["plot_title"]["cost"]
 title_benefit = js_data["plot_title"]["benefit"]
+title_roi = js_data["plot_title"]["roi"]
+
 
 figure_size = (js_data["figure_size"]["length"], js_data["figure_size"]["height"])
 
+data = pd.read_csv('combined_data.csv')
+
+granularity = js_data["time_interval"]["numerator"]
+
+months_days = [31,28,31,30,31,30,31,31,30,31,30,31]
+def get_month_coe(num, granularity):
+    return 60 / granularity * 24 * months_days[num]
+
+months_index = [get_month_coe(num, granularity) for num in range(12)]
+months_data = []
+for i in range(1,12):
+    months_index[i] += months_index[i-1]
+for i in range(12):
+    start = 0 if i == 0 else months_index[i-1]
+    end = months_index[i]
+    months_data.append(data.iloc[int(start):int(end)])
+    
+
+
+
 pv_capacities = np.linspace(pv_begin, pv_end, pv_groups)
 ess_capacities = np.linspace(ess_begin, ess_end, ess_groups)
-results = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
-affords = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
-costs = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
-overload_cnt = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+# results = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+# affords = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+# costs = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+# overload_cnt = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
 
 
-# In[17]:
+# In[86]:
 
 
 hour_demand = []
@@ -97,164 +132,414 @@ plt.savefig('plots/demand.png')
 plt.close()
 
 
-# In[18]:
+# In[87]:
 
 
-def cal_profit(es: EnergySystem, saved_money):
-    profit = saved_money - es.ess.get_cost_per_year() - es.pv.get_cost_per_year()
+def draw_results(results, filename, title_benefit, annot_benefit=False, figure_size=(10, 10)):
+    df=results
+    df = df.astype(float)
+    df.index = df.index / 1000
+    df.index = df.index.map(int)
+    df.columns = df.columns / 1000
+    df.columns = df.columns.map(int)
+    min_value = df.min().min()
+    max_value = df.max().max()
+    max_scale = max(abs(min_value/1000), abs(max_value/1000))
+
+    df[df.columns[-1] + 1] = df.iloc[:, -1] 
+    new_Data = pd.DataFrame(index=[df.index[-1] + 1], columns=df.columns)
+    for i in df.columns:
+        new_Data[i] = df[i].iloc[-1]
+    df = pd.concat([df, new_Data])
+
+    X, Y = np.meshgrid(np.arange(df.shape[1]), np.arange(df.shape[0]))
+
+    def fmt(x,pos):
+        return '{:.0f}'.format(x/1000)
+
+    cmap = sns.color_palette("coolwarm", as_cmap=True)
+    plt.figure(figsize=figure_size)
+    ax = sns.heatmap(df/1000, fmt=".1f", cmap=cmap, vmin=-max_scale, vmax=max_scale, annot=annot_benefit)
+    CS = ax.contour(X, Y, df,  colors='black', alpha=0.5)
+    ax.clabel(CS, inline=True, fontsize=10, fmt=FuncFormatter(fmt))
+    plt.title(title_benefit)
+    plt.gca().invert_yaxis()
+    plt.xlim(0, df.shape[1] - 1)
+    plt.ylim(0, df.shape[0] - 1)
+    plt.xlabel('ESS Capacity (MWh)')
+    plt.ylabel('PV Capacity (MW)')
+    plt.savefig(filename)
+
+
+# In[88]:
+
+
+def draw_roi(costs, results, filename, title_roi, days=365, annot_roi=False, figure_size=(10, 10)):
+    costs = costs.astype(float)
+    costs = costs / 365 
+    costs = costs * days
+
+    df = results
+    df = costs / df
+    if 0 in df.index and 0 in df.columns:
+        df.loc[0,0] = 100
+    df[df > 80] = 100
+    # print(df)
+
+    df = df.astype(float)
+    df.index = df.index / 1000
+    df.index = df.index.map(int)
+    df.columns = df.columns / 1000
+    df.columns = df.columns.map(int)
+    min_value = df.min().min()
+    max_value = df.max().max()
+    # print(max_value)
+    max_scale = max(abs(min_value), abs(max_value))
+
+    df[df.columns[-1] + 1] = df.iloc[:, -1] 
+    new_Data = pd.DataFrame(index=[df.index[-1] + 1], columns=df.columns)
+    for i in df.columns:
+        new_Data[i] = df[i].iloc[-1]
+    df = pd.concat([df, new_Data])
+
+    X, Y = np.meshgrid(np.arange(df.shape[1]), np.arange(df.shape[0]))
+
+    def fmt(x,pos):
+        return '{:.0f}'.format(x)
+
+    cmap = sns.color_palette("Greys", as_cmap=True)
+    plt.figure(figsize=figure_size)
+    ax = sns.heatmap(df, fmt=".1f", cmap=cmap, vmin=0, vmax=100, annot=annot_benefit)
+    CS = ax.contour(X, Y, df,  colors='black', alpha=0.5)
+    ax.clabel(CS, inline=True, fontsize=10, fmt=FuncFormatter(fmt))
+    plt.title(title_roi)
+    plt.gca().invert_yaxis()
+    plt.xlim(0, df.shape[1] - 1)
+    plt.ylim(0, df.shape[0] - 1)
+    plt.xlabel('ESS Capacity (MWh)')
+    plt.ylabel('PV Capacity (MW)')
+    plt.savefig(filename)
+    plt.close()
+
+
+# In[89]:
+
+
+def draw_cost(costs, filename, title_cost, annot_cost=False, figure_size=(10, 10)):
+    df = costs
+    df = df.astype(int)
+    df.index = df.index / 1000
+    df.index = df.index.map(int)
+    df.columns = df.columns / 1000
+    df.columns = df.columns.map(int)
+
+    df[df.columns[-1] + 1] = df.iloc[:, -1] 
+    new_Data = pd.DataFrame(index=[df.index[-1] + 1], columns=df.columns)
+    for i in df.columns:
+        new_Data[i] = df[i].iloc[-1]
+    df = pd.concat([df, new_Data])
+    X, Y = np.meshgrid(np.arange(df.shape[1]), np.arange(df.shape[0]))
+
+    def fmt(x, pos):
+        return '{:.0f}'.format(x / 1000000)
+
+    plt.figure(figsize=figure_size)
+    ax = sns.heatmap(df/1000000,  fmt=".1f", cmap='viridis', annot=annot_cost)
+    CS = ax.contour(X, Y, df,  colors='black', alpha=0.5)
+    ax.clabel(CS, inline=True, fontsize=10, fmt=FuncFormatter(fmt))
+    plt.title(title_cost)
+    plt.gca().invert_yaxis()
+    plt.xlim(0, df.shape[1] - 1)
+    plt.ylim(0, df.shape[0] - 1)
+    plt.xlabel('ESS Capacity (MWh)')
+    plt.ylabel('PV Capacity (MW)')
+    plt.savefig(filename)
+    plt.close()
+
+
+# In[90]:
+
+
+def draw_overload(overload_cnt, filename, title_unmet, annot_unmet=False, figure_size=(10, 10), days=365, granularity=15):
+    df = overload_cnt
+    # print(days, granularity)
+    coef = 60 / granularity * days * 24
+    # print(coef)
+    # print(df)
+    df = ( coef - df) / coef
+    # print(df)
+
+    df = df.astype(float)
+    df.index = df.index / 1000
+    df.index = df.index.map(int)
+    df.columns = df.columns / 1000
+    df.columns = df.columns.map(int)
+
+
+    df[df.columns[-1] + 1] = df.iloc[:, -1] 
+    new_Data = pd.DataFrame(index=[df.index[-1] + 1], columns=df.columns)
+    for i in df.columns:
+        new_Data[i] = df[i].iloc[-1]
+    # print(new_Data)
+    df = pd.concat([df, new_Data])
+
+
+    plt.figure(figsize=figure_size)
+    cmap = LinearSegmentedColormap.from_list("", ["white", "blue"])
+    ax = sns.heatmap(df, fmt=".00%", cmap=cmap, vmin=0, vmax=1, annot=annot_unmet)
+
+    cbar = ax.collections[0].colorbar
+    cbar.set_ticks([0, 0.10, 0.20, 0.30, 0.40, 0.50, 0.60, 0.70, 0.80, 0.90, 1])
+    cbar.set_ticklabels(['0%', '10%', '20%', '30%', '40%', '50%', '60%', '70%', '80%', '90%', '100%'])
+    cbar.ax.yaxis.set_major_formatter(ticker.FuncFormatter(lambda x, pos: f'{x:.0%}'))
+    X, Y = np.meshgrid(np.arange(df.shape[1]), np.arange(df.shape[0]))
+
+    def fmt(x, pos):
+        return '{:.0f}%'.format(x * 100)
+    CS = ax.contour(X, Y, df,  colors='black', alpha=0.5)
+
+    ax.clabel(CS, inline=True, fontsize=10, fmt=FuncFormatter(fmt))
+
+    plt.xlim(0, df.shape[1] - 1)
+    plt.ylim(0, df.shape[0] - 1)
+    plt.title(title_unmet)
+    plt.xlabel('ESS Capacity (MWh)')
+    plt.ylabel('PV Capacity (MW)')
+    plt.savefig(filename)
+    plt.close()
+
+
+# In[91]:
+
+
+def cal_profit(es: EnergySystem, saved_money, days):
+    profit = saved_money - es.ess.get_cost_per_year() / 365 * days - es.pv.get_cost_per_year() / 365 * days
     return profit
 
 
-# In[24]:
+# In[92]:
 
 
-for ess_capacity in ess_capacities:
-    print(f"ess_capacity:{ess_capacity}")
+def generate_data(pv_capacity, pv_cost_per_kW, pv_lifetime, pv_loss, ess_capacity, ess_cost_per_kW, ess_lifetime, ess_loss, grid_capacity, grid_loss, sell_price, time_interval, data, days, storage=0):
+    pv = pv_config(capacity=pv_capacity, 
+                    cost_per_kW=pv_cost_per_kW,
+                    lifetime=pv_lifetime, 
+                    loss=pv_loss)
+    ess = ess_config(capacity=ess_capacity, 
+                        cost_per_kW=ess_cost_per_kW, 
+                        lifetime=ess_lifetime, 
+                        loss=ess_loss,
+                        charge_power=ess_capacity,
+                        discharge_power=ess_capacity,
+                        storage=storage)
+    grid = grid_config(capacity=grid_capacity, 
+                        grid_loss=grid_loss,
+                        sell_price= sell_price)
+    energySystem = EnergySystem(pv_type=pv, 
+                                ess_type=ess, 
+                                grid_type= grid)
+    (benefit, netto_benefit, gen_energy) = energySystem.simulate(data, time_interval)
+    results = cal_profit(energySystem, benefit, days)
+    overload_cnt = energySystem.overload_cnt
+    costs = energySystem.ess.capacity * energySystem.ess.cost_per_kW + energySystem.pv.capacity * energySystem.pv.cost_per_kW
+    return (results, 
+            overload_cnt,
+            costs, 
+            netto_benefit, 
+            gen_energy, 
+            energySystem.generated,
+            energySystem.ess_rest,
+            energySystem.factory_demand,
+            energySystem.buy_price_kWh,
+            energySystem.sell_price_kWh,
+            energySystem.pv_generated_kWh,
+            energySystem.grid_need_power_kW,
+            energySystem.time)
+
+
+
+# In[93]:
+
+
+from tqdm import tqdm
+months_results = []
+months_costs = []
+months_overload = []
+months_nettos = []
+months_gen_energy = []
+months_gen_energy2 = []
+months_ess_rest = pd.DataFrame(30, index=pv_capacities, columns= ess_capacities)
+months_csv_data = {}
+for index, month_data in tqdm(enumerate(months_data), total=len(months_data), position=0, leave= True):
+    results = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+    costs = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+    overload_cnt = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+    nettos = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+    gen_energies = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+    gen_energies2 = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+    factory_demands = {}
+    buy_prices= {}
+    sell_prices = {}
+    pv_generates = {}
+    grid_need_powers = {}
+    times = {}
+    for pv_capacity in tqdm(pv_capacities, total=len(pv_capacities), desc=f'generating pv for month {index + 1}',position=1, leave=False):
+        factory_demands[pv_capacity] = {}
+        buy_prices[pv_capacity] = {}
+        sell_prices[pv_capacity] = {}
+        pv_generates[pv_capacity] = {}
+        grid_need_powers[pv_capacity] = {}
+        times[pv_capacity] = {}
+        for ess_capacity in ess_capacities:
+            (result, 
+             overload, 
+             cost, 
+             netto,
+             gen_energy,
+             gen_energy2,
+             ess_rest,
+             factory_demand,
+             buy_price,
+             sell_price,
+             pv_generate,
+             grid_need_power,
+             time) = generate_data(pv_capacity=pv_capacity,
+                        pv_cost_per_kW=pv_cost_per_kW,
+                        pv_lifetime=pv_lifetime, 
+                        pv_loss=pv_loss, 
+                        ess_capacity=ess_capacity, 
+                        ess_cost_per_kW=ess_cost_per_kW, 
+                        ess_lifetime=ess_lifetime, 
+                        ess_loss=ess_loss, 
+                        grid_capacity=grid_capacity, 
+                        grid_loss=grid_loss, 
+                        sell_price=sell_price, 
+                        time_interval=time_interval, 
+                        data=month_data, 
+                        days=months_days[index],
+                        storage=months_ess_rest.loc[pv_capacity, ess_capacity])
+            results.loc[pv_capacity,ess_capacity] = result
+            overload_cnt.loc[pv_capacity,ess_capacity] = overload
+            costs.loc[pv_capacity,ess_capacity] = cost
+            nettos.loc[pv_capacity,ess_capacity] = netto
+            gen_energies.loc[pv_capacity, ess_capacity] = gen_energy
+            gen_energies2.loc[pv_capacity, ess_capacity] = gen_energy2
+            months_ess_rest.loc[pv_capacity, ess_capacity] = ess_rest
+            factory_demands[pv_capacity][ess_capacity] = factory_demand
+            buy_prices[pv_capacity][ess_capacity] = buy_price
+            sell_prices[pv_capacity][ess_capacity] = sell_price
+            pv_generates[pv_capacity][ess_capacity] = pv_generate
+            grid_need_powers[pv_capacity][ess_capacity] = grid_need_power
+            times[pv_capacity][ess_capacity] = time
+    months_csv_data[index] = {"factory_demand": factory_demands, "buy_price": buy_prices, "sell_price": sell_prices, "pv_generate": pv_generates, "grid_need_power": grid_need_powers, "time": times}
+    months_results.append(results)
+    months_costs.append(costs)
+    months_overload.append(overload_cnt)
+    months_nettos.append(nettos)
+    months_gen_energy.append(gen_energies)
+    months_gen_energy2.append(gen_energies2)
+    draw_results(results=results, 
+                    filename=f'plots/pv-{pv_capacity}-ess-{ess_capacity}-month-{index+1}-benefit.png',
+                    title_benefit=title_benefit,
+                    annot_benefit=annot_benefit,
+                    figure_size=figure_size)
+    draw_overload(overload_cnt=overload_cnt, 
+                    filename=f'plots/pv-{pv_capacity}-ess-{ess_capacity}-month-{index+1}-unmet.png',
+                    title_unmet=title_unmet,
+                    annot_unmet=annot_unmet,
+                    figure_size=figure_size,
+                    days=months_days[index],
+                    granularity=granularity)
+annual_result = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+annual_costs = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+annual_overload = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+annual_nettos = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+annual_gen = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+annual_gen2 = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
+
+
+# get the yearly results
+for pv_capacity in pv_capacities:
+    for ess_capacity in ess_capacities:
+        results = 0
+        costs = 0
+        overload_cnt = 0
+        nettos = 0
+        gen = 0
+        gen2 = 0
+        for index, month_data in enumerate(months_data):
+            results += months_results[index].loc[pv_capacity,ess_capacity]
+            costs += months_costs[index].loc[pv_capacity,ess_capacity]
+            overload_cnt += months_overload[index].loc[pv_capacity, ess_capacity]
+            nettos += months_nettos[index].loc[pv_capacity, ess_capacity]
+            gen += months_gen_energy[index].loc[pv_capacity, ess_capacity]
+            gen2 += months_gen_energy[index].loc[pv_capacity, ess_capacity]
+        annual_result.loc[pv_capacity, ess_capacity] = results
+        annual_costs.loc[pv_capacity, ess_capacity] = costs
+        annual_overload.loc[pv_capacity, ess_capacity] = overload_cnt
+        annual_nettos.loc[pv_capacity, ess_capacity] = nettos
+        annual_gen.loc[pv_capacity, ess_capacity] = gen
+        annual_gen2.loc[pv_capacity, ess_capacity] = gen2
+
+draw_cost(costs=annual_costs,
+          filename='plots/annual_cost.png',
+        title_cost=title_cost,
+        annot_cost=annot_cost,
+        figure_size=figure_size)
+draw_results(results=annual_result,
+                filename='plots/annual_benefit.png',
+                title_benefit=title_benefit,
+                annot_benefit=annot_benefit,
+                figure_size=figure_size)
+draw_overload(overload_cnt=annual_overload,
+                filename='plots/annual_unmet.png',
+                title_unmet=title_unmet,
+                annot_unmet=annot_unmet,
+                figure_size=figure_size)
+
+
+# In[94]:
+
+
+def collapse_months_csv_data(months_csv_data, column_name,pv_capacies, ess_capacities):
+    data = {}
     for pv_capacity in pv_capacities:
-        print(f"pv_capacity:{pv_capacity}")
-        pv = pv_config(capacity=pv_capacity, 
-                        cost_per_kW=pv_cost_per_kW,
-                        lifetime=pv_lifetime, 
-                        loss=pv_loss)
-        ess = ess_config(capacity=ess_capacity, 
-                            cost_per_kW=ess_cost_per_kW, 
-                            lifetime=ess_lifetime, 
-                            loss=ess_loss,
-                            charge_power=ess_capacity,
-                            discharge_power=ess_capacity)
-        grid = grid_config(capacity=grid_capacity, 
-                            grid_loss=grid_loss,
-                            sell_price= sell_price)
-        energySystem = EnergySystem(pv_type=pv, 
-                                    ess_type=ess, 
-                                    grid_type= grid)
-        benefit = energySystem.simulate(data, time_interval)
-        results.loc[pv_capacity,ess_capacity] = cal_profit(energySystem, benefit)
-        affords.loc[pv_capacity,ess_capacity] = energySystem.afford
-        overload_cnt.loc[pv_capacity,ess_capacity] = energySystem.overload_cnt
-        costs.loc[pv_capacity,ess_capacity] = energySystem.ess.capacity * energySystem.ess.cost_per_kW + energySystem.pv.capacity * energySystem.pv.cost_per_kW
-        pv_generated = energySystem.day_generated
-        ess_generated = energySystem.hour_stored
-        ess_generated_2 = energySystem.hour_stored_2
-    plt.figure(figsize=(10,8));
-    plt.plot(ess_generated)
-    plt.xlabel('day #')
-    plt.ylabel('SoC %')
-    plt.title(f'14:00 ESS SoC \n PV cap:{pv_capacity}, ESS cap:{ess_capacity}')
-    plt.savefig(f'plots/ess/1400-{pv_capacity}-{ess_capacity}.png')
-    plt.close()
-    plt.figure(figsize=(10,8));
-    plt.plot(ess_generated_2)
-    plt.xlabel('day #')
-    plt.ylabel('SoC%')
-    plt.title(f'08:00 ESS SoC \n PV cap:{pv_capacity}, ESS cap:{ess_capacity}')
-    plt.savefig(f'plots/ess/0800-{pv_capacity}-{ess_capacity}.png')
-    plt.close()
-        # print(energySystem.unmet)
-        # spring_week_start = energySystem.season_start
-        # spring_week_end = spring_week_start + energySystem.week_length
-        # summer_week_start = energySystem.season_start + 1 * energySystem.season_step
-        # summer_week_end = summer_week_start + energySystem.week_length
-        # autumn_week_start = energySystem.season_start + 2 * energySystem.season_step
-        # autumn_week_end = autumn_week_start + energySystem.week_length
-        # winter_week_start = energySystem.season_start + 3 * energySystem.season_step
-        # winter_week_end = winter_week_start+ energySystem.week_length
+        data[pv_capacity] = {}
+        for ess_capacity in ess_capacities:
+            annual_data = []
+            for index, month_data in enumerate(months_data):
+                annual_data.extend(months_csv_data[index][column_name][pv_capacity][ess_capacity])
+                # months_csv_data[index][column_name][pv_capacity][ess_capacity] = months_csv_data[index][column_name][pv_capacity][ess_capacity].tolist()
 
-        # spring_consume_data = []
-        # summer_consume_data = []
-        # autumn_consume_data = []
-        # winter_consume_data = []
-        # for index, row in data.iterrows():
-            # if index in range(spring_week_start, spring_week_end):
-                # spring_consume_data.append(row['demand'])
-        #     elif index in range(summer_week_start, summer_week_end):
-        #         summer_consume_data.append(row['demand'])
-        #     elif index in range(autumn_week_start, autumn_week_end):
-        #         autumn_consume_data.append(row['demand'])
-        #     elif index in range(winter_week_start, winter_week_end):
-        #         winter_consume_data.append(row['demand'])
-
-        # spring_week_time = list(range(spring_week_start, spring_week_end))
-        # summer_week_time = list(range(summer_week_start, summer_week_end))
-        # autumn_week_time = list(range(autumn_week_start, autumn_week_end))
-        # winter_week_time = list(range(winter_week_start, winter_week_end))
-
-        # spring_pv_generated = energySystem.spring_week_gen
-        # summer_pv_generated = energySystem.summer_week_gen
-        # autumn_pv_generated = energySystem.autumn_week_gen
-        # winter_pv_generated = energySystem.winter_week_gen
-
-        # spring_soc = energySystem.spring_week_soc
-        # summer_soc = energySystem.summer_week_soc
-        # autumn_soc = energySystem.autumn_week_soc
-        # winter_soc = energySystem.winter_week_soc
+            data[pv_capacity][ess_capacity] = annual_data
+    return data 
 
 
-        # fig, ax1 = plt.subplots()
-
-        # plt.plot(spring_week_time, spring_pv_generated, label = 'pv generation')
-        # plt.plot(spring_week_time, spring_consume_data, label = 'factory consume')
-        # plt.ylabel('Power / kW')
-        # plt.xlabel('15 min #')
-        # plt.title(f'ess: {energySystem.ess.capacity/1000 } MWh pv: {energySystem.pv.capacity/1000 } MW spring week generate condition')
-        # plt.legend()
-        # plt.savefig(f'plots/{energySystem.ess.capacity}-{energySystem.pv.capacity}-spring.png')
-        # plt.close()
-
-        # plt.plot(summer_week_time, summer_pv_generated, label = 'pv generation')
-        # plt.plot(summer_week_time, summer_consume_data, label = 'factory consume')
-        # plt.ylabel('Power / kW')
-        # plt.xlabel('15 min #')
-        # plt.title(f'ess: {energySystem.ess.capacity/1000 } MWh pv: {energySystem.pv.capacity/1000 } MW summer week generate condition')
-        # plt.legend()
-        # plt.savefig(f'plots/{energySystem.ess.capacity}-{energySystem.pv.capacity}-summer.png')
-        # plt.close()
-
-        # plt.plot(autumn_week_time, autumn_pv_generated, label = 'pv generation')
-        # plt.plot(autumn_week_time, autumn_consume_data, label = 'factory consume')
-        # plt.ylabel('Power / kW')
-        # plt.xlabel('15 min #')
-        # plt.title(f'ess: {energySystem.ess.capacity/1000 } MWh pv: {energySystem.pv.capacity/1000 } MW autumn week generate condition')
-        # plt.legend()
-        # plt.savefig(f'plots/{energySystem.ess.capacity}-{energySystem.pv.capacity}-autumn.png')
-        # plt.close()
-
-        # plt.plot(winter_week_time, winter_pv_generated, label = 'pv generation')
-        # plt.plot(winter_week_time, winter_consume_data, label = 'factory consume')
-        # plt.ylabel('Power / kW')
-        # plt.xlabel('15 min #')
-        # plt.title(f'ess: {energySystem.ess.capacity/1000 } MWh pv: {energySystem.pv.capacity/1000 } MW winter week generate condition')
-        # plt.legend()
-        # plt.savefig(f'plots/{energySystem.ess.capacity}-{energySystem.pv.capacity}-winter.png')
-        # plt.close()
-
-    # plt.figure();
-    # plt.plot(pv_generated)
-    # plt.xlabel('day #')
-    # plt.ylabel('Electricity kWh')
-    # plt.title(f'PV generated pv cap:{pv_capacity}, ess cap:{ess_capacity}')
-    # plt.savefig(f'plots/pv/{pv_capacity}-{ess_capacity}.png')
-    # plt.close()
+# In[102]:
 
 
-        # plt.show()
+annual_pv_gen = collapse_months_csv_data(months_csv_data, "pv_generate", pv_capacities, ess_capacities)
+annual_time = collapse_months_csv_data(months_csv_data, "time", pv_capacities, ess_capacities)
+annual_buy_price = collapse_months_csv_data(months_csv_data, "buy_price",pv_capacities, ess_capacities)
+annual_sell_price = collapse_months_csv_data(months_csv_data, "sell_price", pv_capacities, ess_capacities)
+annual_factory_demand = collapse_months_csv_data(months_csv_data, "factory_demand", pv_capacities, ess_capacities)
+annual_grid_need_power = collapse_months_csv_data(months_csv_data, "grid_need_power", pv_capacities, ess_capacities)
+
+from datetime import datetime, timedelta
+
+for pv_capacity in pv_capacities:
+    for ess_capacity in ess_capacities:
+        with open(f'data/annual_data-pv-{pv_capacity}-ess-{ess_capacity}.csv', 'w') as f:
+            f.write("date, time,pv_generate (kW),factory_demand (kW),buy_price (USD/MWh),sell_price (USD/MWh),grid_need_power (kW)\n")
+            start_date = datetime(2023, 1, 1, 0, 0, 0)
+            for i in range(len(annual_time[pv_capacity][ess_capacity])):
+                current_date = start_date + timedelta(hours=i)
+                formate_date = current_date.strftime("%Y-%m-%d")
+                f.write(f"{formate_date},{annual_time[pv_capacity][ess_capacity][i]},{int(annual_pv_gen[pv_capacity][ess_capacity][i])},{int(annual_factory_demand[pv_capacity][ess_capacity][i])},{int(annual_buy_price[pv_capacity][ess_capacity][i]*1000)},{int(annual_sell_price[pv_capacity][ess_capacity][i]*1000)},{int(annual_grid_need_power[pv_capacity][ess_capacity][i])} \n")
 
 
-        
 
-# results = results.astype(float)
-
-
-# pv = pv_config(capacity=100000,cost_per_kW=200,lifetime=25,loss=0.95)
-# ess = ess_config(capacity=100000,cost_per_kW=300,lifetime=25,loss=0.95,charge_power=100000,discharge_power=100000)
-# grid = grid_config(price_schedule=price_schedule, capacity=5000, grid_loss=0.95, sell_price=0.4)
-# grid = grid_config(capacity=50000, grid_loss=0.95, sell_price=0.4)
-
-
-    # print(benefit)
-
-
-# In[20]:
+# In[96]:
 
 
 def save_data(data, filename):
@@ -262,83 +547,25 @@ def save_data(data, filename):
     data.to_json(filename + '.json')
 
 
-# In[21]:
+# In[97]:
 
 
-import matplotlib.ticker as ticker
-
 if not os.path.isdir('data'):
     os.makedirs('data')
 
-save_data(results, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_end}-{ess_groups}-results')
-save_data(costs, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_end}-{ess_groups}-costs')
-save_data(overload_cnt, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_end}-{ess_groups}-overload_cnt')
-df=results
-df = df.astype(float)
-df.index = df.index / 1000
-df.columns = df.columns / 1000
-min_value = df.min().min()
-max_value = df.max().max()
-max_scale = max(abs(min_value/1000), abs(max_value/1000))
-plt.figure(figsize=figure_size)
-cmap = sns.color_palette("coolwarm", as_cmap=True)
-ax = sns.heatmap(df/1000, fmt=".1f", cmap=cmap, vmin=-max_scale, vmax=max_scale, annot=annot_benefit)
-# ax.yaxis.set_major_formatter(ticker.FormatStrFormatter('%.1f'))
-plt.title(title_benefit)
-plt.gca().invert_yaxis()
-plt.xlabel('ESS Capacity (MWh)')
-plt.ylabel('PV Capacity (MW)')
-plt.savefig('plots/benefit.png')
+save_data(annual_result, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_end}-{ess_groups}-results')
+save_data(annual_costs, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_end}-{ess_groups}-costs')
+save_data(annual_overload, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_end}-{ess_groups}-overload_cnt')
 
 
-# In[22]:
+# In[98]:
 
 
-df = costs
-df = df.astype(int)
-df.index = df.index / 1000
-df.columns = df.columns / 1000
-
-plt.figure(figsize=figure_size)
-sns.heatmap(df/1000000,  fmt=".1f", cmap='viridis', annot=annot_cost)
-plt.title(title_cost)
-plt.gca().invert_yaxis()
-plt.xlabel('ESS Capacity (MWh)')
-plt.ylabel('PV Capacity (MW)')
-plt.savefig('plots/costs.png')
-
-    # pv = pv_config(capacity=100000,cost_per_kW=200,lifetime=25,loss=0.95)
-    # ess = ess_config(capacity=100000,cost_per_kW=300,lifetime=25,loss=0.95,charge_power=100000,discharge_power=100000)
-    # grid = grid_config(price_schedule=price_schedule, capacity=5000, grid_loss=0.95, sell_price=0.4)
-    # grid = grid_config(capacity=50000, grid_loss=0.95, sell_price=0.4)
+draw_results(annual_result, 'plots/test.png', 'test', False)
 
 
-    # print(benefit)
+# In[99]:
 
 
-# In[23]:
-
-
-from matplotlib.colors import LinearSegmentedColormap
-df = overload_cnt
-df = df.astype(int)
-df.index = df.index / 1000
-df.columns = df.columns / 1000
-min_value = df.min().min()
-max_value = df.max().max()
-max_scale = max(abs(min_value/1000), abs(max_value/1000))
-
-plt.figure(figsize=figure_size)
-cmap = LinearSegmentedColormap.from_list("", ["white", "blue"])
-ax = sns.heatmap(df/(4*24*365), fmt=".00%", cmap=cmap, vmin=0, vmax=1, annot=annot_unmet)
-cbar = ax.collections[0].colorbar
-cbar.set_ticks([0, 0.25, 0.5, 0.75, 1])
-cbar.set_ticklabels(['0%', '25%', '50%', '75%', '100%'])
-cbar.ax.yaxis.set_major_formatter(ticker.FuncFormatter(lambda x, pos: f'{x:.0%}'))
-
-plt.title(title_unmet)
-plt.gca().invert_yaxis()
-plt.xlabel('ESS Capacity (MWh)')
-plt.ylabel('PV Capacity (MW)')
-plt.savefig('plots/unmet.png')
+draw_roi(annual_costs, annual_nettos, 'plots/annual_roi.png',  title_roi, 365, annot_benefit, figure_size)
 

read_data.py

@@ -1,69 +1,47 @@
 import pandas as pd
 import numpy as np
 import csv
+import json
 
-sunlight_file_name = 'lightintensity.xlsx'
-factory_demand_file_name = 'factory_power1.xlsx'
-electricity_price_data = 'electricity_price_data.csv'
+with open('config.json', 'r') as f:
+    js_data = json.load(f)
 
-df_sunlight = pd.read_excel(sunlight_file_name, header=None, names=['SunlightIntensity'])
+pv_yield_file_name = js_data["data_path"]["pv_yield"]
+print(pv_yield_file_name)
+# factory_demand_file_name = 'factory_power1.xlsx'
+factory_demand_file_name = js_data["data_path"]["demand"]
+print(factory_demand_file_name)
+electricity_price_data = js_data["data_path"]["buy"]
+print(electricity_price_data)
+electricity_price_data_sell = js_data["data_path"]["sell"]
+print(electricity_price_data_sell)
 
-start_date = '2023-01-01 00:00:00'  # 根据数据的实际开始日期调整
-hours = pd.date_range(start=start_date, periods=len(df_sunlight), freq='h')
-df_sunlight['Time'] = hours
-df_sunlight.set_index('Time', inplace=True)
+pv_df = pd.read_csv(pv_yield_file_name, index_col='Time', usecols=['Time', 'PV yield[kW/kWp]'])
+pv_df.index = pd.to_datetime(pv_df.index)
 
-df_sunlight_resampled = df_sunlight.resample('15min').interpolate()
+df_power = pd.read_csv(factory_demand_file_name, index_col='Time', usecols=['Time', 'FactoryPower'])
+df_power.index = pd.to_datetime(df_power.index)
+df_combined = pv_df.join(df_power)
 
-df_power = pd.read_excel(factory_demand_file_name, 
-                         header=None, 
-                         names=['FactoryPower'], 
-                         dtype={'FactoryPower': float})
-times = pd.date_range(start=start_date, periods=len(df_power), freq='15min')
-df_power['Time'] = times
-df_power.set_index('Time',inplace=True)
-print(df_power.head())
-
-df_combined = df_sunlight_resampled.join(df_power)
-
-
-df_combined.to_csv('combined_data.csv', index=True, index_label='Time')
-
-def read_csv(file_path):
-    return pd.read_csv(file_path, index_col='Time', usecols=['Time', 'ElectricityPrice'])
-
-# price_data = np.random.uniform(0.3, 0.3, len(times))
-
-# 创建DataFrame
-price_df = read_csv(electricity_price_data)
+price_df = pd.read_csv(electricity_price_data, index_col='Time', usecols=['Time', 'ElectricityBuy'])
 price_df.index = pd.to_datetime(price_df.index)
 price_df = price_df.reindex(df_combined.index)
-
-# price_df.set_index('Time', inplace=True)
-
-# 保存到CSV文件
-# price_df.to_csv('electricity_price_data.csv', index=True)
-print("price____")
-print(price_df.index)
-print("df_combined____")
-print(df_combined.index)
-
-print("Electricity price data generated and saved.")
-
-
 df_combined2 = df_combined.join(price_df)
-print(df_combined2.head())
-# 保存结果
+
+sell_df = pd.read_csv(electricity_price_data_sell, index_col='Time', usecols=['Time', 'ElectricitySell'])
+sell_df.index = pd.to_datetime(sell_df.index)
+sell_df = sell_df.reindex(df_combined.index)
+df_combined3 = df_combined2.join(sell_df)
+
 with open('combined_data.csv', 'w', newline='') as file:
     writer = csv.writer(file)
-    writer.writerow(['time', 'sunlight', 'demand','price'])
+    writer.writerow(['time', 'PV yield[kW/kWp]', 'demand','buy', 'sell'])
     cnt = 0
-    for index, row in df_combined2.iterrows():
+    for index, row in df_combined3.iterrows():
         time_formatted = index.strftime('%H:%M')
-        writer.writerow([time_formatted, row['SunlightIntensity'], row['FactoryPower'],row['ElectricityPrice']])
+        writer.writerow([time_formatted, row['PV yield[kW/kWp]'], row['FactoryPower'],row['ElectricityBuy'], row['ElectricitySell']])
         
     print('The file is written to combined_data.csv')
 
-# combined_data.to_csv('updated_simulation_with_prices.csv', index=False)
 
 print("Simulation data with electricity prices has been updated and saved.")

read_data/convert_data.ipynb

@@ -0,0 +1,372 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import csv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def read_csv(filename):\n",
+    "    skip_rows = list(range(1, 17))\n",
+    "    data = pd.read_csv(filename, sep=';', skiprows=skip_rows)\n",
+    "    return data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_3075037/3659192646.py:3: DtypeWarning: Columns (32,33,35) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+      "  data = pd.read_csv(filename, sep=';', skiprows=skip_rows)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Time', 'Irradiance onto horizontal plane ',\n",
+       "       'Diffuse Irradiation onto Horizontal Plane ', 'Outside Temperature ',\n",
+       "       'Module Area 1: Height of Sun ',\n",
+       "       'Module Area 1: Irradiance onto tilted surface ',\n",
+       "       'Module Area 1: Module Temperature ', 'Grid Export ',\n",
+       "       'Energy from Grid ', 'Global radiation - horizontal ',\n",
+       "       'Deviation from standard spectrum ', 'Ground Reflection (Albedo) ',\n",
+       "       'Orientation and inclination of the module surface ', 'Shading ',\n",
+       "       'Reflection on the Module Surface ',\n",
+       "       'Irradiance on the rear side of the module ',\n",
+       "       'Global Radiation at the Module ',\n",
+       "       'Module Area 1: Reflection on the Module Surface ',\n",
+       "       'Module Area 1: Global Radiation at the Module ',\n",
+       "       'Global PV Radiation ', 'Bifaciality ', 'Soiling ',\n",
+       "       'STC Conversion (Rated Efficiency of Module) ', 'Rated PV Energy ',\n",
+       "       'Low-light performance ', 'Module-specific Partial Shading ',\n",
+       "       'Deviation from the nominal module temperature ', 'Diodes ',\n",
+       "       'Mismatch (Manufacturer Information) ',\n",
+       "       'Mismatch (Configuration/Shading) ',\n",
+       "       'Power optimizer (DC conversion/clipping) ',\n",
+       "       'PV Energy (DC) without inverter clipping ',\n",
+       "       'Failing to reach the DC start output ',\n",
+       "       'Clipping on account of the MPP Voltage Range ',\n",
+       "       'Clipping on account of the max. DC Current ',\n",
+       "       'Clipping on account of the max. DC Power ',\n",
+       "       'Clipping on account of the max. AC Power/cos phi ', 'MPP Matching ',\n",
+       "       'PV energy (DC) ',\n",
+       "       'Inverter 1 - MPP 1 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Inverter 1 - MPP 2 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Inverter 1 - MPP 3 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Inverter 1 - MPP 4 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Inverter 1 - MPP 5 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Inverter 1 - MPP 6 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Inverter 2 - MPP 1 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Inverter 2 - MPP 2 - to Module Area 1: PV energy (DC) ',\n",
+       "       'Energy at the Inverter Input ',\n",
+       "       'Input voltage deviates from rated voltage ', 'DC/AC Conversion ',\n",
+       "       'Own Consumption (Standby or Night) ', 'Total Cable Losses ',\n",
+       "       'PV energy (AC) minus standby use ', 'Feed-in energy ',\n",
+       "       'Inverter 1 to Module Area 1: Own Consumption (Standby or Night) ',\n",
+       "       'Inverter 1 to Module Area 1: PV energy (AC) minus standby use ',\n",
+       "       'Inverter 2 to Module Area 1: Own Consumption (Standby or Night) ',\n",
+       "       'Inverter 2 to Module Area 1: PV energy (AC) minus standby use ',\n",
+       "       'Unnamed: 58'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 87,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "file_name = 'Riyahd_raw.csv'\n",
+    "df = read_csv(file_name)\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "remain_column = ['Time','PV energy (AC) minus standby use ']\n",
+    "energy_row_name = remain_column[1]\n",
+    "\n",
+    "df = df[remain_column]\n",
+    "df[energy_row_name] = df[energy_row_name].str.replace(',','.').astype(float)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "770594.226863267"
+      ]
+     },
+     "execution_count": 89,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sum_energy = df[energy_row_name].sum()\n",
+    "sum_energy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1975.882632982736"
+      ]
+     },
+     "execution_count": 90,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sum_energy / 390"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 91,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "group_size = 15\n",
+    "df['group_id'] = df.index // group_size\n",
+    "\n",
+    "sums = df.groupby('group_id')[energy_row_name].sum()\n",
+    "sums_df = sums.reset_index(drop=True).to_frame(name = 'Energy')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 92,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<bound method NDFrame.head of        Energy\n",
+       "0         0.0\n",
+       "1         0.0\n",
+       "2         0.0\n",
+       "3         0.0\n",
+       "4         0.0\n",
+       "...       ...\n",
+       "35035     0.0\n",
+       "35036     0.0\n",
+       "35037     0.0\n",
+       "35038     0.0\n",
+       "35039     0.0\n",
+       "\n",
+       "[35040 rows x 1 columns]>"
+      ]
+     },
+     "execution_count": 92,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sums_df.head"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                 Time\n",
+      "0 2023-01-01 00:00:00\n",
+      "1 2023-01-01 00:15:00\n",
+      "2 2023-01-01 00:30:00\n",
+      "3 2023-01-01 00:45:00\n",
+      "4 2023-01-01 01:00:00\n",
+      "                     Time\n",
+      "35035 2023-12-31 22:45:00\n",
+      "35036 2023-12-31 23:00:00\n",
+      "35037 2023-12-31 23:15:00\n",
+      "35038 2023-12-31 23:30:00\n",
+      "35039 2023-12-31 23:45:00\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "start_date = '2023-01-01'\n",
+    "end_date = '2023-12-31'\n",
+    "\n",
+    "# 生成每天的15分钟间隔时间\n",
+    "all_dates = pd.date_range(start=start_date, end=end_date, freq='D')\n",
+    "all_times = pd.timedelta_range(start='0 min', end='1435 min', freq='15 min')\n",
+    "\n",
+    "# 生成完整的时间标签\n",
+    "date_times = [pd.Timestamp(date) + time for date in all_dates for time in all_times]\n",
+    "\n",
+    "# 创建DataFrame\n",
+    "time_frame = pd.DataFrame({\n",
+    "    'Time': date_times\n",
+    "})\n",
+    "\n",
+    "# 查看生成的DataFrame\n",
+    "print(time_frame.head())\n",
+    "print(time_frame.tail())\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(35040, 1)\n",
+      "(35040, 1)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(sums_df.shape)\n",
+    "print(time_frame.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sums_df['Time'] = time_frame['Time']\n",
+    "sums_df = pd.concat([time_frame, sums_df], axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                     Energy\n",
+      "Time                       \n",
+      "2023-01-01 00:00:00     0.0\n",
+      "2023-01-01 00:15:00     0.0\n",
+      "2023-01-01 00:30:00     0.0\n",
+      "2023-01-01 00:45:00     0.0\n",
+      "2023-01-01 01:00:00     0.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "sums_df.set_index('Time', inplace=True)\n",
+    "print(sums_df.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 97,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "max_value = sums_df['Energy'].max()\n",
+    "sums_df['Energy'] = sums_df['Energy'] / max_value\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def save_csv(df, filename, columns):\n",
+    "    tmp_df = df.copy()\n",
+    "    tmp_df[columns[1]] = tmp_df[columns[1]].round(4)\n",
+    "    with open(filename, 'w', newline='') as file:\n",
+    "        writer = csv.writer(file)\n",
+    "        writer.writerow(columns)\n",
+    "        for index, row in tmp_df.iterrows():\n",
+    "            time_formatted = index.strftime('%H:%M')\n",
+    "            writer.writerow([time_formatted, row[columns[1]]])\n",
+    "            \n",
+    "        print(f'The file is written to {filename}')\n",
+    "        \n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The file is written to Riyahd.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "save_csv(sums_df, 'Riyahd.csv', ['Time', 'Energy'])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "pv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

read_data/convert_data.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+
+import matplotlib.pyplot as plt
+import pandas as pd
+import numpy as np
+import os
+import csv
+
+def generate_min_df(mins = 15):
+    end = 60/mins * 24
+    start_date = '2023-01-01'
+    end_date = '2023-12-31'
+
+    all_dates = pd.date_range(start=start_date, end=end_date, freq='D')
+    all_times = pd.timedelta_range(start='0 min', end=f'1435 min', freq=f'{mins} min')
+
+    date_times = [pd.Timestamp(date) + time for date in all_dates for time in all_times]
+
+    time_frame = pd.DataFrame({
+        'Time': date_times
+    })
+    return time_frame
+
+def save_csv(df, filename, columns):
+    with open(filename, 'w', newline='') as file:
+        writer = csv.writer(file)
+        writer.writerow(['Time', 'PV yield[kW/kWp]'])
+        for index, row in df.iterrows():
+            time_formatted = index.strftime('%H:%M')
+            writer.writerow([time_formatted, row[columns[1]]])
+            
+        print(f'The file is written to {filename}')
+
+def read_csv(filename):
+    skip_rows = list(range(1, 17))
+    data = pd.read_csv(filename, sep=';', skiprows=skip_rows)
+    return data
+
+def process(file_name):
+    df = read_csv(file_name)
+    city = file_name.split('_')[0]
+
+    remain_column = ['Time','PV energy (AC) minus standby use ']
+    energy_row_name = remain_column[1]
+
+    df = df[remain_column]
+    df[energy_row_name] = df[energy_row_name].str.replace(',','.').astype(float)
+
+    sum_energy = df[energy_row_name].sum()
+    group_size = 15
+    df['group_id'] = df.index // group_size
+
+    sums = df.groupby('group_id')[energy_row_name].sum()
+    sums_df = sums.reset_index(drop=True).to_frame(name = 'Energy')
+
+    pv_energy_column_name = 'PV yield[kW/kWp]'
+    sums_df = sums_df.rename(columns={'Energy': pv_energy_column_name})
+
+    time_frame = generate_min_df(15)
+    sums_df = pd.concat([time_frame, sums_df], axis=1)
+    # sums_df.set_index('Time', inplace=True)
+    # max_value = sums_df[pv_energy_column_name].max()
+    sums_df[pv_energy_column_name] = sums_df[pv_energy_column_name] / 390.
+    sums_df[pv_energy_column_name] = sums_df[pv_energy_column_name].round(4)
+    sums_df[pv_energy_column_name].replace(0.0, -0.0)
+
+    sums_df.to_csv(f'{city}.csv')
+    # save_csv(sums_df, f'{city}.csv', ['Time', 'Energy'])
+
+if __name__ == '__main__':
+    city_list = ['Riyahd', 'Cambodge', 'Berlin', 'Serbia']
+    for city in city_list:
+        print(f'Processing {city}')
+        file_name = f'{city}_raw.csv'
+        process(file_name)
+        print(f'Processing {city} is done\n')
+

xlsx2csv.py

@@ -0,0 +1,16 @@
+import pandas as pd
+
+excel_file = 'factory_power1.xlsx'
+sheet_name = 'Sheet1'
+
+df = pd.read_excel(excel_file, sheet_name=sheet_name)
+
+start_date = '2023-01-01'
+df_power = pd.read_excel(excel_file, 
+                         header=None, 
+                         names=['FactoryPower'], 
+                         dtype={'FactoryPower': float})
+times = pd.date_range(start=start_date, periods=len(df_power), freq='15min')
+df_power['Time'] = times
+df_power = df_power[['Time', 'FactoryPower']]
+df_power.to_csv('factory_power1.csv', index=True)