AI Smart City Lighting Management System Development

Development of AI System for Smart City Lighting Management

Urban street lighting—one of municipality's largest electricity consumers: 30–40% of communal electricity expenses. Smart Lighting reduces this consumption by 40–70% while maintaining and improving safety.

Adaptive Lighting Level Management

Adaptive dimming logic:

Lighting intensity adjusts to real conditions:

• Time of day + astronomical calculation (dawn/dusk without sensors)
• Traffic flow: sensors or video analysis → low activity reduce to 30%
• Pedestrian activity: PIR or CV counters → people present → 100% brightness
• Weather: fog, snow → increase brightness above nominal

import numpy as np
from astral import LocationInfo
from astral.sun import sun
import datetime

class AdaptiveLightingController:
    """Adaptive lighting controller for group of fixtures"""

    def __init__(self, location_lat, location_lon, city_name):
        self.location = LocationInfo(city_name, 'Russia', 'UTC+3',
                                    location_lat, location_lon)

    def calculate_dimming_level(self, timestamp, sensor_data):
        """
        Calculate dimming level (0.0–1.0).
        sensor_data: {'traffic_count': int, 'pedestrians': int,
                     'visibility_km': float, 'weather': str}
        """
        # Astronomical calculation
        s = sun(self.location.observer, date=timestamp.date())
        civil_dusk = s['dusk']
        civil_dawn = s['dawn']

        # Is it dark?
        is_dark = not (civil_dawn < timestamp.replace(tzinfo=civil_dawn.tzinfo) < civil_dusk)
        if not is_dark:
            return 0.0  # turn off during day

        # Base level by time of night
        hour = timestamp.hour
        if 22 <= hour or hour <= 6:
            base_level = 0.5  # late night — economy
        else:
            base_level = 0.8  # evening/morning — standard

        # Correction by traffic and pedestrians
        activity = sensor_data.get('traffic_count', 0) + sensor_data.get('pedestrians', 0)
        if activity > 10:
            activity_level = 1.0
        elif activity > 3:
            activity_level = 0.8
        elif activity > 0:
            activity_level = 0.6
        else:
            activity_level = 0.3

        # Weather correction
        weather_factor = 1.3 if sensor_data.get('weather') in ['fog', 'snow'] else 1.0

        final_level = min(1.0, max(base_level, activity_level) * weather_factor)
        return final_level

Predictive Maintenance of Fixtures

LED health monitoring:

Smart fixtures with telemetry transmit:

• Power consumption: >20% decline from nominal → LED degradation
• Module temperature: overheating → shortened lifespan
• Supply voltage: spikes → damage risk

Lamp replacement forecast:

ML model on telemetry data + passport characteristics:

• Operating hours
• Thermal stress (cumulative temperature load)
• Number of on/off cycles (thermal cycling)
• Remaining service life forecast → planned replacement before emergency failure

Replacement savings: emergency replacement costs 2–3x more than planned (emergency crew call, urgency).

Video Data Analysis for Management

Traffic and pedestrian counting:

Cameras on lighting poles:

• YOLOv8 + SORT tracker → real-time vehicle and pedestrian counting
• Activity heat maps by time of day and day of week
• Activity forecast → proactive brightness increase

Accident and incident detection:

Anomaly detection on video stream: sudden scene change (collision, person falling) → alert to duty service. Reduce accident response time from 8–15 to 2–4 minutes.

Lighting Network Management

Topology and losses:

Lighting network map in GIS (QGIS, ArcGIS) → ML optimization of grouping:

• Zoning: different scenarios for residential, industrial, commercial zones
• Load balancing across feeders
• Detection of unauthorized connections (electricity theft)

System KPIs:

Development timeline: 2–4 months for Smart Lighting system with adaptive dimming, predictive maintenance and GIS integration.