Predicting Energy Consumption Patterns with Advanced Machine Learning Techniques for Sustainable Urban Development
Syed Ali Reza, Md Sakibul Hasan, Mohammad Hamid Hasan Amjad, Mohammad Shahidul Islam, Md Masud Karim Rabbi, Arat Hossain, Md Shihab Sadik Shovon, Tanaya Jakir
Abstract
As urbanization continues to expand and evolve in the USA, power demand has increased manifold, and with it has arisen significant environmental problems in the form of increased greenhouse gas emissions and loss of resources. In this paper, we explore how future machine-learning techniques could predict power consumption in U.S. cities. The central aim of this research is to develop advanced machine learning models with the potential to effectively predict energy consumption in cities. This involves not only identifying the key variables behind energy consumption but also selecting and fine-tuning machine learning algorithms that are most capable of understanding the dynamics of urban energy intricacies. This study focuses on the energy consumption patterns in the large cities of the United States, recognizing the diversity of challenges and opportunities presented by different geographic and demographic situations. The dataset used in this research project offered a comprehensive view of energy consumption across various fields of household, commercial, and industrial consumption, giving a holistic view of energy dynamics within cities. It integrated data collected from smart meters that offer granular electricity consumption patterns at the level of individual households and businesses with weather reports that detail ambient conditions governing energy demand, such as temperature and humidity fluctuations. Government energy records add historical context and policy information, further enhancing the dataset and enabling close analysis of trends and patterns in energy consumption. The next phase was to select and train three distinct machine models to explore the energy consumption dataset, namely, Logistic Regression, Random Forest, and XG-Boost algorithms. Random Forest outperformed Logistic Regression and XG-Boost slightly in terms of accuracy and other evaluation metrics. However, all models exhibit relatively low accuracy, suggesting the need for further tuning, feature engineering, or alternative models to improve predictions. In major cities in the U.S. such as Los Angeles, Chicago, and New York, smart power forecasting based on AI is revolutionizing power distribution and power planning in cities. By utilizing advanced machine learning models, these cities can process vast amounts of information and predict power usage with high accuracy. The incorporation of artificial intelligence (AI) in urban power planning has been a defining feature of modern-day power management in the USA. Major cities such as Los Angeles, Chicago, and New York are increasingly adopting AI-powered power forecasting technologies to rationalize power distribution. The integration of machine learning insights in U.S. government-driven green construction is instrumental in driving sustainable construction in infrastructure. By utilizing data-driven approaches, policymakers are in a position to identify the optimal design methods and low-power technologies with high performance in buildings.