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
@@ -37,9 +44,12 @@ class EnergySystem:
         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']
@@ -55,8 +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:
@@ -74,6 +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
@@ -89,6 +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
@@ -105,6 +122,7 @@ 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)
@@ -123,6 +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

config.json

@@ -17,12 +17,12 @@
     "pv_capacities":{
         "begin": 0,
         "end": 50000,
-        "groups": 11 
+        "groups":  3
     },
     "ess_capacities":{
         "begin": 0,
         "end": 100000,
-        "groups":  11
+        "groups":  3
     },
     "time_interval":{
         "numerator": 15,
@@ -43,5 +43,11 @@
         "cost": "Costs of Microgrid system [m-EUR]",
         "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

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # coding: utf-8
 
-# In[ ]:
+# In[83]:
 
 
 import os
@@ -28,7 +28,7 @@ folder_path = 'plots'
 clear_folder_make_ess_pv(folder_path)
 
 
-# In[ ]:
+# In[84]:
 
 
 import matplotlib.pyplot as plt
@@ -39,7 +39,7 @@ from EnergySystem import EnergySystem
 from config import pv_config, grid_config, ess_config
 
 
-# In[ ]:
+# In[85]:
 
 
 import json
@@ -53,7 +53,7 @@ with open('config.json', 'r') as f:
     
 
 time_interval = js_data["time_interval"]["numerator"] / js_data["time_interval"]["denominator"]
-print(time_interval)
+# print(time_interval)
 
 pv_loss = js_data["pv"]["loss"]
 pv_cost_per_kW = js_data["pv"]["cost_per_kW"]
@@ -116,7 +116,7 @@ ess_capacities = np.linspace(ess_begin, ess_end, ess_groups)
 # overload_cnt = pd.DataFrame(index=pv_capacities, columns= ess_capacities)
 
 
-# In[ ]:
+# In[86]:
 
 
 hour_demand = []
@@ -132,7 +132,7 @@ plt.savefig('plots/demand.png')
 plt.close()
 
 
-# In[ ]:
+# In[87]:
 
 
 def draw_results(results, filename, title_benefit, annot_benefit=False, figure_size=(10, 10)):
@@ -171,7 +171,7 @@ def draw_results(results, filename, title_benefit, annot_benefit=False, figure_s
     plt.savefig(filename)
 
 
-# In[ ]:
+# In[88]:
 
 
 def draw_roi(costs, results, filename, title_roi, days=365, annot_roi=False, figure_size=(10, 10)):
@@ -184,7 +184,7 @@ def draw_roi(costs, results, filename, title_roi, days=365, annot_roi=False, fig
     if 0 in df.index and 0 in df.columns:
         df.loc[0,0] = 100
     df[df > 80] = 100
-    print(df)
+    # print(df)
 
     df = df.astype(float)
     df.index = df.index / 1000
@@ -193,7 +193,7 @@ def draw_roi(costs, results, filename, title_roi, days=365, annot_roi=False, fig
     df.columns = df.columns.map(int)
     min_value = df.min().min()
     max_value = df.max().max()
-    print(max_value)
+    # print(max_value)
     max_scale = max(abs(min_value), abs(max_value))
 
     df[df.columns[-1] + 1] = df.iloc[:, -1] 
@@ -219,9 +219,10 @@ def draw_roi(costs, results, filename, title_roi, days=365, annot_roi=False, fig
     plt.xlabel('ESS Capacity (MWh)')
     plt.ylabel('PV Capacity (MW)')
     plt.savefig(filename)
+    plt.close()
 
 
-# In[ ]:
+# In[89]:
 
 
 def draw_cost(costs, filename, title_cost, annot_cost=False, figure_size=(10, 10)):
@@ -253,19 +254,20 @@ def draw_cost(costs, filename, title_cost, annot_cost=False, figure_size=(10, 10
     plt.xlabel('ESS Capacity (MWh)')
     plt.ylabel('PV Capacity (MW)')
     plt.savefig(filename)
+    plt.close()
 
 
-# In[ ]:
+# 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)
+    # print(days, granularity)
     coef = 60 / granularity * days * 24
-    print(coef)
+    # print(coef)
-    print(df)
+    # print(df)
     df = ( coef - df) / coef
-    print(df)
+    # print(df)
 
     df = df.astype(float)
     df.index = df.index / 1000
@@ -304,9 +306,10 @@ def draw_overload(overload_cnt, filename, title_unmet, annot_unmet=False, figure
     plt.xlabel('ESS Capacity (MWh)')
     plt.ylabel('PV Capacity (MW)')
     plt.savefig(filename)
+    plt.close()
 
 
-# In[ ]:
+# In[91]:
 
 
 def cal_profit(es: EnergySystem, saved_money, days):
@@ -314,10 +317,10 @@ def cal_profit(es: EnergySystem, saved_money, days):
     return profit
 
 
-# In[ ]:
+# In[92]:
 
 
-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):
+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, 
@@ -327,7 +330,8 @@ def generate_data(pv_capacity, pv_cost_per_kW, pv_lifetime, pv_loss, ess_capacit
                         lifetime=ess_lifetime, 
                         loss=ess_loss,
                         charge_power=ess_capacity,
-                        discharge_power=ess_capacity)
+                        discharge_power=ess_capacity,
+                        storage=storage)
     grid = grid_config(capacity=grid_capacity, 
                         grid_loss=grid_loss,
                         sell_price= sell_price)
@@ -338,34 +342,96 @@ def generate_data(pv_capacity, pv_cost_per_kW, pv_lifetime, pv_loss, ess_capacit
     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)
+    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[ ]:
+
+# In[93]:
 
 
+from tqdm import tqdm
 months_results = []
 months_costs = []
 months_overload = []
 months_nettos = []
 months_gen_energy = []
 months_gen_energy2 = []
-for index, month_data in enumerate(months_data):
+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)
-    for pv_capacity in pv_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) = 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])
+            (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)
@@ -384,7 +450,6 @@ for index, month_data in enumerate(months_data):
                     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)
@@ -393,7 +458,6 @@ 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:
@@ -434,7 +498,48 @@ draw_overload(overload_cnt=annual_overload,
                 figure_size=figure_size)
 
 
-# In[ ]:
+# In[94]:
+
+
+def collapse_months_csv_data(months_csv_data, column_name,pv_capacies, ess_capacities):
+    data = {}
+    for pv_capacity in pv_capacities:
+        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()
+
+            data[pv_capacity][ess_capacity] = annual_data
+    return data 
+
+
+# In[102]:
+
+
+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")
+
+
+
+# In[96]:
 
 
 def save_data(data, filename):
@@ -442,7 +547,7 @@ def save_data(data, filename):
     data.to_json(filename + '.json')
 
 
-# In[ ]:
+# In[97]:
 
 
 if not os.path.isdir('data'):
@@ -453,13 +558,13 @@ save_data(annual_costs, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_
 save_data(annual_overload, f'data/{pv_begin}-{pv_end}-{pv_groups}-{ess_begin}-{ess_end}-{ess_groups}-overload_cnt')
 
 
-# In[ ]:
+# In[98]:
 
 
 draw_results(annual_result, 'plots/test.png', 'test', False)
 
 
-# In[ ]:
+# In[99]:
 
 
 draw_roi(annual_costs, annual_nettos, 'plots/annual_roi.png',  title_roi, 365, annot_benefit, figure_size)

read_data.py

@@ -1,57 +1,47 @@
 import pandas as pd
 import numpy as np
 import csv
+import json
 
-sunlight_file_name = 'lightintensity.xlsx'
+with open('config.json', 'r') as f:
-factory_demand_file_name = 'factory_power1.xlsx'
+    js_data = json.load(f)
-electricity_price_data = 'electricity_price_data.csv'
-electricity_price_data_sell = 'electricity_price_data_sell.csv'
 
-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
+pv_df = pd.read_csv(pv_yield_file_name, index_col='Time', usecols=['Time', 'PV yield[kW/kWp]'])
-hours = pd.date_range(start=start_date, periods=len(df_sunlight), freq='h')
+pv_df.index = pd.to_datetime(pv_df.index)
-df_sunlight['Time'] = hours
-df_sunlight.set_index('Time', inplace=True)
 
-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_power = pd.read_excel(factory_demand_file_name, 
+df_combined = pv_df.join(df_power)
-                         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)
-
-    
 
 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)
-
-print("Electricity price data generated and saved.")
 df_combined2 = df_combined.join(price_df)
 
 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','buy', 'sell'])
+    writer.writerow(['time', 'PV yield[kW/kWp]', 'demand','buy', 'sell'])
     cnt = 0
     for index, row in df_combined3.iterrows():
         time_formatted = index.strftime('%H:%M')
-        writer.writerow([time_formatted, row['SunlightIntensity'], row['FactoryPower'],row['ElectricityBuy'], row['ElectricitySell']])
+        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)