Climate change, primarily driven by human activities such as burning fossil fuels, is causing significant long-term changes in temperature and weather patterns. To mitigate these impacts, there is an increased focus on renewable energy sources. However, optimizing power consumption through effective usage control and waste recycling also offers substantial potential for reducing energy demands. This study explores non-intrusive load monitoring (NILM) to estimate disaggregated energy consumption from a single household meter, leveraging advancements in deep learning such as convolutional neural networks. The study uses the UK-DALE dataset to extract and plot power consumption data from the main meter and identify five household appliances. Convolutional neural networks (CNNs) are trained with transfer learning using VGG16 and MobileNet. The models are validated, tested on split datasets, and combined using ensemble methods for improved performance. A new voting scheme for ensembles is proposed, named weighted average confidence voting (WeCV), and it is used to create combinations of the best 3 and 5 models and applied to NILM. The base models achieve up to 97% accuracy. The ensemble methods applying WeCV show an increased accuracy of 98%, surpassing previous state-of-the-art results. This study shows that CNNs with transfer learning effectively disaggregate household energy use, achieving high accuracy. Ensemble methods further improve performance, offering a promising approach for optimizing energy use and mitigating climate change.

Electrical power systems are crucial, yet vulnerable, due to their complex and interconnected nature, necessitating effective fault detection and diagnostics to ensure stability and prevent disruptions. Advances in artificial intelligence (AI) and the Internet of Things (IoT) have transformed the ability to identify and resolve electrical system problems efficiently. Electrical systems operate at various scales, ranging from individual households to large-scale regional grids. In this study, we focus on medium-scale urban infrastructures. These environments present unique electrical challenges, such as phase imbalances and transient voltage fluctuations, which require robust fault detection mechanisms. This work investigates the use of AI with dynamic programming and a support vector machine (SVM) to improve fault detection. The data collected from voltage measurements in urban office buildings with smart meters over a period of six weeks was used to develop an AI model, demonstrating its applicability to similar urban infrastructures. This model achieved high accuracy in detecting system failures, identifying them with a performance greater than 99%, highlighting the potential of smart sensing technologies combined with AI to improve urban infrastructure management. The integration of smart sensors and advanced data analytics significantly increases the reliability and efficiency of energy systems, promoting sustainable and resilient urban environments.