Implementation of Artificial Intelligence Technology to Improve Energy Efficiency in Street Lighting Systems

Abstract

Public street lighting (PSL) systems are one of the major components of urban infrastructure that consume a significant amount of electrical energy, often accounting for 20–40% of a city's total electricity expenditure. As the demand for energy efficiency and the development of smart cities continue to grow, innovation in street lighting systems has become increasingly important. This paper explores the implementation of artificial intelligence (AI) technologies to improve energy efficiency in public street lighting systems. Through a systematic literature review of studies published between 2020 and 2025, this paper examines various AI approaches, ranging from machine learning to deep learning, that have demonstrated significant potential for optimizing energy consumption. The reviewed methods include adaptive control based on real-time object detection using Convolutional Neural Networks (CNNs), such as YOLOv5, load forecasting and renewable energy availability prediction using Long Short-Term Memory (LSTM) networks, as well as dynamic optimization through reinforcement learning. The review findings indicate that AI-based street lighting systems can reduce energy consumption by 30% to 86%, while simultaneously improving public safety and traffic management. This paper concludes that the adoption of AI in public street lighting systems not only provides substantial energy and cost savings but also serves as a key driver for accelerating the development of smarter, more sustainable, and environmentally friendly cities.