K. Madhavi, S. Rajesh, R. Maliklal Naik, B. Naveen, T. Raviteja 02 06 Street lighting is essential for urban safety and security during nighttime but traditional maintenance methods are often reactive and inefficient Typically maintenance relies on scheduled inspections and manual fixes leading to delays in addressing faults higher operational costs and increased safety risks due to unexpected outages These challenges highlight the need for a proactive datadriven approach to managing street light operations Predictive analytics powered by data collected through sensors and IoT devices offers a promising solution By continuously monitoring street lights and analyzing environmental factors predictive models can anticipate potential failures before they occur This approach optimizes maintenance schedules reduces energy consumption and prevents service disruptions resulting in significant cost savings and improved reliability The absence of such predictive systems causes inefficient use of resources greater energy waste safety hazards and operational interruptions Integrating machine learning algorithms into street light management enables fault detection and diagnosis in realtime supporting faster and more accurate decisionmaking The proposed system focuses on building a comprehensive predictive analysis framework that includes data acquisition processing machine learningbased prediction fault diagnosis and decision support Continuous evaluation ensures system accuracy and adaptability Implementing this predictive maintenance system can transform urban lighting infrastructure by enhancing operational efficiency reducing maintenance costs and promoting sustainability Ultimately it improves public safety and the quality of urban life by ensuring wellmaintained energyefficient street lighting contributing to safer and more vibrant cities Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026