The growing complexity of modern smart buildings necessitates robust and scalable frameworks for real-time sensing, data management, predictive analytics, and visualization. This paper presents an integrated machine learning-based framework designed for real-time monitoring and short-term forecasting in smart building environments, leveraging a diverse array of online sensor data streams.

Uncoordinated high-power electric vehicle (EV) charging can create substantial stress on distribution feeders, resulting in voltage violations, line and transformer overloads, increased peak demand, and congestion at charging stations, which leads to extended waiting times.

Vehicle-to-everything (V2X) communication and edge-assisted intelligence are essential for safety-critical connected and autonomous vehicle services, but their reliance on wireless channels, shared compute resources, and control-plane orchestration exposes them to cyber-physical disturbances such as jamming, compute starvation, spoofing, and misconfiguration.

Smart buildings are increasingly leveraging human-centric data to enhance operational efficiency, reduce energy consumption, and support long-term sustainability. This paper presents a review of Artificial Intelligence (AI) techniques applied to behavioral data collected from smartphones and wearable devices.

The growing complexity of urban environments renders the conventional approach of optimizing individual smart city subsystems, such as transportation and building energy management, ineffective, leading to fragmented decision-making and systemic inefficiencies.