Residential Comfort Index Maximization Using Simulated Kalman Filter Algorithms

Comfort has always been one of the main aspects researchers focus on in building smart homes. Thermal comfort, visual comfort, and air quality are the parameters of most interest. This paper proposes two Simulated Kalman Filter (SKF) algorithms to maximize the residential comfort index based on these three parameters. A population-based SKF and a single solution-based SKF. A dataset consisting of 48 environmental values is used for this purpose. The performance of the Simulated Kalman Filter algorithms is benchmarked against the Artificial Bee Colony algorithm, Firefly Algorithm, Genetic Algorithm, and Ant Colony Optimization algorithm. Friedman and Holm's statistical analysis shows that both algorithms outperformed others by quite a significant gap. Furthermore, the single solution-based SKF performed better than the original population-based SKF algorithm despite converging slower. In summary, Simulated Kalman Filter algorithms have proven to be a promising approach to ensuring optimal comfort for residential users.