Abstract
New trendy neighborhoods require trimming scientific and technological methods and equipment. Smart buildings (SB) use resources efficiently, save energy, and provide services to the community more easily for their occupants while reducing their environmental footprint. Smart cities have benefited from this growth in terms of smart buildings. Maximum accuracy and reduced latency are both required for smart building monitoring systems. Poor scheduling rules can lead to network congestion and latency that is too high for real-time monitoring on construction sites, which have restricted computing and networking capabilities. These devices can collect the data on on-site actions, achievements, and circumstances and send it back to the central dashboard for analysis. Model predictive control and Deep Reinforcement Learning (DRL) have significant drawbacks, and DRL addresses some drawbacks. Researchers are intrigued by DRL, a brand-new approach to quality control. The most important considerations for developing smart power grid systems are energy conservation, renewable energy integration, and a streamlined control system. Experiments have shown that the new video surveillance has a low loss rate and a consistent latency. The DRL-SB-IoT technique can successfully track multiple cameras in a wide monitoring situation. This technique results in excellent tracking performance and meets the criteria for developing an intelligent campus in the best way possible. Researchers analyzed studies using supervised learning to solve common building issues, such as health monitoring, security on building sites, accommodation modeling, and energy consumption prediction. Reinforcement learning has been used to solve these issues. The proposed method advances the smart gateway channel of 97.5%, the energy storage ratio of 96.9%, and the overall surveillance performance ratio of 98.6%.