Intelligent Streetlight Control System Using Machine Learning Algorithms for Enhanced Energy Optimization in Smart Cities

In the USA, where large-scale city infrastructure uses huge amounts of energy, street lighting collectively makes up a large percentage of city-wide electricity consumption. As cities become smarter and greener, there is an immediate demand to update the management of public lighting networks. This research's prime objective was to create an adaptive machine learning system for streetlight control that can react automatically to the environment and human activity patterns in real time. The development of our intelligent streetlight control system led us to build a complete dataset that contains the necessary elements for context-based lighting decisions. The dataset contains contemporary, along with historical readings of ambient light intensity expressed in lux units, which delivers an essential understanding of natural illumination and lighting needs. The primary performance metric is accuracy, which indicates the number of accurately predicted instances against the number of overall predictions. Furthermore, a Confusion Matrix is utilized to present an in-depth breakdown of the outcomes of classification, illustrating the number of examples that were accurately or inaccurately classified into each class. The application of an intelligent streetlight system using machine learning is directly in line with the strategic policies of the U.S. Department of Energy (DOE), specifically its requirements regarding the modernization of the smart grid, energy efficiency, and carbon reduction. By providing real-time data-driven control of street lighting in response to environmental and usage conditions, the system makes full integration of municipal infrastructure into the smart grid possible. At the policy level, the system is an effective and pragmatic tool for municipalities looking to achieve federal and local climate action targets. Greenhouse gas (GHG) mitigation is achieved through the reduction of electricity consumption through adaptive lighting, and the machine learning function minimizes human interaction, maximizing operational autonomy and cost savings. One of the strongest ramifications of using the intelligent streetlight system is the possibility of huge cost reductions on city utility budgets.