Computationally intelligent heating controller optimization

Abstract

Computationally intelligent optimization of the controller in a building radiator heating system performed by several metaheuristic methods has been considered in this paper. Presented results compare conventional controller tuning using integral of time absolute error criterion and six metaheuristic methods-Simulated Annealing (SA), Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), reported in our previous research, and by Ant Colony Optimization (ACO), Grey Wolf Optimizer (GWO) and Bat Algorithm (BA) presented in this paper. Performance of the tuned heating controller has been tested for the typical winter day in the building geographical region. General conclusions are presented confirming that metaheuristic computationally intelligent optimization of thermal controllers is a feasible concept with strong potentials in providing improved performance, comfort and energy efficiency.