智能电网的部署及应用——代码案例分析

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# 生成模拟的智能电网数据
np.random.seed(42)
date_rng = pd.date_range(start='2023-01-01', end='2023-01-31', freq='H')
data = np.random.randn(len(date_rng)) * 20 + 100  # 模拟电力消耗数据

# 创建DataFrame
df = pd.DataFrame(date_rng, columns=['date'])
df['power_consumption'] = data

# 显示数据的前几行
print(df.head())

# 数据可视化
plt.figure(figsize=(12, 6))
plt.plot(df['date'], df['power_consumption'], label='Power Consumption')
plt.xlabel('Date')
plt.ylabel('Power Consumption (kWh)')
plt.title('Power Consumption Over Time')
plt.legend()
plt.grid(True)
plt.show()

# 计算每日的总电力消耗
daily_consumption = df.resample('D', on='date').sum()
print(daily_consumption.head())

# 数据分析
mean_consumption = df['power_consumption'].mean()
max_consumption = df['power_consumption'].max()
min_consumption = df['power_consumption'].min()

print(f"Mean Power Consumption: {mean_consumption:.2f} kWh")
print(f"Max Power Consumption: {max_consumption:.2f} kWh")
print(f"Min Power Consumption: {min_consumption:.2f} kWh")

import numpy as np

# 生成模拟的电力价格和需求数据
np.random.seed(42)
hours = np.arange(0, 24)
base_demand = 50  # 基本需求
demand = base_demand + 10 * np.sin(2 * np.pi * hours / 24) + 5 * np.random.randn(24)
price = 0.1 + 0.05 * np.cos(2 * np.pi * hours / 24) + 0.02 * np.random.randn(24)

# 需求响应模拟
def demand_response(demand, price, threshold=0.15):
    new_demand = demand.copy()
    for i in range(len(demand)):
        if price[i] > threshold:
            new_demand[i] -= 5  # 减少需求
        else:
            new_demand[i] += 5  # 增加需求
    return new_demand

# 应用需求响应
new_demand = demand_response(demand, price)

# 数据可视化
plt.figure(figsize=(12, 6))
plt.plot(hours, demand, label='Original Demand')
plt.plot(hours, new_demand, label='Demand Response')
plt.xlabel('Hour')
plt.ylabel('Demand (kWh)')
plt.title('Demand Response Simulation')
plt.legend()
plt.grid(True)
plt.show()

import numpy as np
from scipy.optimize import minimize

# 生成模拟的电力需求和可再生能源发电数据
np.random.seed(42)
hours = np.arange(0, 24)
demand = 50 + 10 * np.sin(2 * np.pi * hours / 24) + 5 * np.random.randn(24)
renewable = 20 + 5 * np.sin(2 * np.pi * hours / 24 + np.pi / 4) + 2 * np.random.randn(24)

# 目标函数：最小化化石燃料发电
def objective(x):
    return np.sum(x)

# 约束条件：电力供需平衡
def constraint(x):
    return renewable + x - demand

# 初始猜测值
x0 = np.zeros(24)

# 设置约束和边界
con = {'type': 'eq', 'fun': constraint}
bounds = [(0, None) for _ in range(24)]

# 求解优化问题
solution = minimize(objective, x0, bounds=bounds, constraints=con)
fossil_fuel = solution.x

# 数据可视化
plt.figure(figsize=(12, 6))
plt.plot(hours, demand, label='Demand')
plt.plot(hours, renewable, label='Renewable')
plt.plot(hours, fossil_fuel, label='Fossil Fuel')
plt.xlabel('Hour')
plt.ylabel('Power (kWh)')
plt.title('Renewable Energy Integration')
plt.legend()
plt.grid(True)
plt.show()

# 结果分析
print(f"Total Demand: {np.sum(demand):.2f} kWh")
print(f"Total Renewable: {np.sum(renewable):.2f} kWh")
print(f"Total Fossil Fuel: {np.sum(fossil_fuel):.2f} kWh")