Design of an Intelligent Energy Management Prototype for an Electric Lighting Network on a Raspberry Pi Board
Efficient management of street lighting is crucial for cities seeking to reduce their energy consumption and greenhouse gas emissions. This paper proposes an innovative approach that dynamically adjusts the brightness of streetlights according to two key factors: traffic density and weather conditio...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | ITM Web of Conferences |
| Subjects: | |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2024/12/itmconf_maih2024_04012.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Efficient management of street lighting is crucial for cities seeking to reduce their energy consumption and greenhouse gas emissions. This paper proposes an innovative approach that dynamically adjusts the brightness of streetlights according to two key factors: traffic density and weather conditions. Traffic density is assessed in real time by an image processing system using the YOLOv8 algorithm, which identifies and counts vehicles captured by the cameras. At the same time, the level of cloud cover is measured by an LDR photosensor connected to a Raspberry Pi, which analyzes the ambient light intensity. These data are transmitted to the Raspberry Pi via the MQTT protocol, where a neural network model, trained beforehand, predicts the optimal operating cycle of the street lamps to adjust their brightness in real time. The results show that this method, combining machine vision, IoT and artificial intelligence, delivers significant energy savings without compromising user safety, offering a promising solution for modern cities. |
|---|---|
| ISSN: | 2271-2097 |