Comfort Level and Increased Utilization in Smart Buildings by Promoting Sustainability: A New Hybrid Genetic and Bat Algorithms

The challenge of effectively managing energy consumption in smart buildings has become increasingly significant in recent years. Both macroeconomic and microeconomic frameworks stand to benefit from efficient energy management strategies. Additionally, it is essential to ensure that tenants in smart buildings experience acceptable levels of comfort. By utilizing optimization algorithms, we can minimize energy consumption while maximizing user convenience. In this paper, we propose an agent-based optimization method grounded in a multi-layered architectural framework and its architecture comprises an intelligent agent that communicates with one another within a three-tier network system. Our research specifically focuses on reducing energy consumption costs and peak demand rates while simultaneously enhancing user comfort to the highest possible standard. However, this optimization challenge is notably complex due to the vast array of electrical devices and their varying functionalities. To address this complexity, we propose a hybrid optimization approach that leverages both Genetic Algorithms (GA) and Bat algorithms and evaluated the performance of our method using specific objective functions and drawn comparisons with recent studies on Smart Home and CU-BEM datasets. The switch layer is responsible for monitoring user preferences and comfort levels. The coordination layer features a coordinating agent tasked with determining the optimal scheduling of electrical appliances to achieve cost reductions in electricity consumption while maximizing user comfort. Finally, the execution layer consists of performing agents directly managing device operations. This comprehensive approach seeks to create a more sustainable energy management system in smart buildings, contributing to both economic efficiency and enhanced tenant satisfaction.