The rapid development of urban areas has considerably increased energy spending, particularly in street lighting system. Traditional streetlight managing method often lack optimization, leading to inefficiencies and higher operational costs. This research proposes an Intelligent Streetlight Control System (ISCS) to enhance energy efficiency by with passion adjusting lighting based on real-time data. The system combines multiple data sources, including time, location, ambient light levels, traffic count, and energy consumption, to optimize explanation. Data pre-processing engross Min-Max scaling for normalization and Fast Fourier Transform (FFT) for feature extraction. The Energy Valley Optimizer (EVO) fine-tunes the Dynamic Elman Neural Network (DENN) to predict traffic flow and adjust street lighting accordingly. The system is executed using Python, and experimental results display that ISCS effectively decreases energy consumption by optimizing streetlight presentation in response to environmental conditions.The EVO-DENN model outperforms conventional control methods in both energy efficiency and prediction accuracy, proving its likelihood for large-scale urban deployment. Key performance metrics include an operational duration of 12 hours, a power rating of 140W, power consumption of 0.698W, daily unit consumption of 0.695W, and an energy savings rate of 43.25%. The findings indicate that integrating intelligent streetlight control enhances sustainability in urban infrastructure, providing a foundation for smarter, adaptive cities. By implementing AI-driven energy management, the proposed system contributes to cost reduction and environmental conservation, making it a significant step toward the development of intelligent urban ecosystems. Future research could focus on incorporating renewable energy sources and expanding the system’s adaptability to different urban environments worldwide.
Yamanappa et al. (Fri,) studied this question.