Applying smart models for energy saving in optimal chiller loading

•A new smart method NNPSO of optimal chiller load is proposed.•This paper used neural networks and particle swarm optimization algorithm.•This study can save 12.68–17.63% as the load varies from 0.55 to 0.95 PLR.•The NNPSO method had fast convergence and highly accurate results.•The results demonstrate the highly nonlinear process with sufficient accuracy. This study used neural networks (NN) to build models of power consumption of the chiller and particle swarm optimization (PSO) algorithm to optimize the chiller loading for minimal power consumption. We obtained 12.68% power saving on 55% chiller partial load rate (PLR) and 17.63% power saving on 70% PLR after analysis and comparison with the linear regression (LR) and equal loading distribution (ELD) methods. Therefore, the NNPSO method solved the problem of fast convergence on optimal chiller load (OCL), and produced highly accurate results within a short timeframe. The proposed approaches can be applied to air-conditioning systems and other related optimization problems.