Enhanced multi-objective evolutionary mating algorithm with improved crowding distance and levy flight for optimizing comfort index and energy consumption in smart buildings
This paper introduces a novel Multi-Objective Evolutionary Mating Algorithm (MOEMA) designed to address the inherent challenges of optimizing comfort index and energy consumption in smart building systems. While current Evolutionary Mating Algorithms (EMA) primarily focus on single-objective optimiz...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier B.V.
2025
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/44973/ http://umpir.ump.edu.my/id/eprint/44973/1/1-s2.0-S2773186325000763-main.pdf |
| Summary: | This paper introduces a novel Multi-Objective Evolutionary Mating Algorithm (MOEMA) designed to address the inherent challenges of optimizing comfort index and energy consumption in smart building systems. While current Evolutionary Mating Algorithms (EMA) primarily focus on single-objective optimization and rely on weighted functions for handling multiple objectives, such approaches prove impractical for the complex trade-offs between comfort index and energy efficiency. The proposed MOEMA enhances the original EMA framework through two key innovations: an improved crowding distance function inspired by the Non-dominated Sorting Genetic Algorithm (NSGA) to enhance solution diversity and selection pressure, and the integration of Levy flight mechanics to improve exploration efficiency by balancing local and global searches. These enhancements enable MOEMA to effectively navigate complex multi-objective landscapes, leading to more diverse and well-converged Pareto-optimal solutions. The algorithm's performance is thoroughly assessed using the chosen benchmark functions and validated through practical applications in smart building environments. It simultaneously optimizes various comfort parameters, including temperature, illuminance, and air quality, while minimizing energy consumption and maximizing the comfort index. Comparative analysis against established algorithms, like NSGA-II demonstrates MOEMA's effectiveness in achieving superior solution diversity and convergence characteristics. The results indicate that MOEMA offers a robust framework for handling the complex balance between the smart building's comfort index and energy usage where it achieves 0.03 better at comfort index and with 10.65 lower energy consumption than NSGA-II. It contributing to the broader fields of building automation and sustainable development while aligning with Industry 4.0 initiatives. |
|---|