Related Concept Videos
Transformers in Distribution System
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
Light Acquisition
Energy Losses in Transformers
There are four main reasons for energy losses in transformers.
The first cause can be the high resistance of the...
Distribution Reliability and Automation
Types Of Transformers
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language.
Developing an AI platform for voice-input medical records in Polish: a digital application for optimisation of physicians' workload.
Global coincident bursts of high frequency oscillations across the human cortex coordinate large-scale memory processing.
Related Experiment Video
Updated: Jan 15, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
Anomaly detection in urban lighting systems using autoencoder and transformer algorithms.
Tomasz Śmiałkowski1, Andrzej Czyżewski2
1TSTRONIC Sp. z o. o., 19 Benzynowa St., 83-011, Gdańsk, Poland. tomasz.smialkowski@tstronic.eu.
Machine learning algorithms effectively detect anomalies in road lighting systems. The Autoencoder model shows superior accuracy and efficiency for real-time energy consumption analysis and system management.
Area of Science:
- Electrical Engineering
- Computer Science
- Artificial Intelligence
Background:
- Road lighting management systems require continuous, real-time anomaly detection.
- Online anomaly detection is crucial for maintaining system reliability and efficiency.
Purpose of the Study:
- To evaluate the effectiveness of machine learning algorithms for anomaly detection in lighting systems.
- To compare the performance of Autoencoder and Transformer algorithms against traditional methods.
Main Methods:
- Analysis of electricity meter records using Autoencoder and Transformer machine learning algorithms.
- Comparison with a simple energy consumption comparison mechanism.
- Evaluation using classification metrics: error matrix, sensitivity, precision, and F1-score.
Main Results:
- Autoencoder achieved a high F1-score of 0.9565 with lower computational cost.
- Transformer demonstrated effective anomaly detection with an F1-score of 0.8125.
- Autoencoder implementation on an ILED platform provided anomaly detection within a 15-minute delay.
Conclusions:
- Machine learning algorithms offer significant advantages for anomaly detection in lighting systems.
- Autoencoder is a highly accurate and resource-efficient solution for urban lighting management.
- The study highlights the potential to improve lighting system reliability and efficiency through AI-driven anomaly detection.
