Intelligent Streetlight Control System

This dataset is designed to simulate the Intelligent Streetlight Control System (ISCS) for energy optimization in urban environments, as described in the provided abstract. The dataset includes a range of features that influence streetlight management, such as traffic flow, ambient light levels, time of day, and weather conditions, and it aims to predict Energy Consumption (kWh), which serves as the target column for optimization.

Features (Columns):
Timestamp:

The exact date and time when the data was logged. It helps track temporal patterns and changes in traffic and lighting conditions over time.
Example: 2024-12-18 18:00:00
Street ID:

A unique identifier for the streetlight. This could represent different regions or sections of a city.
Example: 1, 2, 3
Day/Night:

A binary variable that indicates whether the data was recorded during the day or night. This is important for determining the baseline ambient light levels, as streetlights are generally only required at night.
Example: Night, Day
Traffic Count:

The number of vehicles passing a given streetlight in a specific time frame. This reflects the amount of traffic in the area and is important for adjusting streetlight brightness or status based on traffic flow.
Example: 50, 200
Traffic Density:

The number of vehicles per unit area (e.g., vehicles per square kilometer). This helps assess the level of congestion, influencing how much light is required.
Example: 20, 35
Traffic Speed:

The average speed of vehicles in the area, indicating congestion levels. Lower speeds can indicate heavy traffic, which might require different lighting adjustments.
Example: 30 km/h, 50 km/h
Ambient Light (lux):

The amount of natural light (in lux) detected by sensors in the environment. This is used to determine how much artificial lighting is necessary.
Example: 12 lux, 250 lux
Weather:

The weather conditions (Clear, Cloudy, or Rainy). This feature affects ambient light levels and can influence energy consumption patterns. For example, cloudy or rainy conditions might necessitate more artificial lighting.
Example: Clear, Cloudy, Rainy
Energy Consumption (kWh):

The target variable, representing the amount of energy consumed by the streetlight during the given time frame. This is the outcome of the intelligent streetlight control system and is impacted by factors like traffic, ambient light, and weather.
Example: 0.5 kWh, 1.2 kWh
Power State:

A binary variable indicating whether the streetlight is on (1) or off (0). This directly affects energy consumption and is adjusted based on traffic and ambient lighting conditions.
Example: 1 (on), 0 (off)
Dim Level:

The brightness level of the streetlight (in percentage). This adjusts dynamically based on traffic flow and ambient light, allowing for energy-saving optimizations (e.g., dimming the light when traffic is low or ambient light is high).
Example: 100%, 50%
Latitude:

The geographic latitude of the streetlight, helping to locate the streetlight for mapping or regional analysis purposes.
Example: 40.7128
Longitude:

The geographic longitude of the streetlight.
Example: -74.0060
Special Event:

A binary flag indicating whether there is a special event in the area (e.g., a concert, sports game, etc.). This can increase traffic, requiring more light.
Example: 0 (No), 1 (Yes)
Holiday/Weekend:

A binary flag indicating whether the data corresponds to a holiday or weekend. This is relevant because traffic and streetlight needs can be different on holidays or weekends.
Example: 0 (No), 1 (Yes)
Target Variable:
Energy Consumption (kWh):
This is the primary target variable for the intelligent streetlight control system. It represents the amount of energy consumed by the streetlight based on the various influencing factors like traffic count, ambient light, weather, and dimming adjustments. The goal is to predict and optimize this variable to minimize energy usage while maintaining streetlight performance.
Dataset Characteristics:
Total Entries: 1000 rows
Data Source: Synthetic, based on realistic assumptions for streetlight control in urban environments.
Time Span: Data is simulated for random time points in January 2024.
Data Generation: Includes random values for traffic, ambient light, weather, and other features to model real-world scenarios.