Development of model predictive control method using ANN and metaheuristics (Part 6) Estimation of prediction and control horizon on optimal control in model predictive control

摘要

In this study, the effectiveness of a model predictive control (MPC) strategy for an office building subject to occupancy disturbance and time-varying electricity pricing was investigated. The energy system of the building included air-cooled chiller, stratified thermal energy storage (TES), and pumps. The operation of the chiller and TES was optimized by manipulating the pump mass flow rate. An artificial neural network and metaheuristics algorithm were employed for prediction and optimization, respectively. Prior to the MPC implementation, different condition of prediction and control horizon was estimated. As a result, the room temperature was well managed in the prediction horizon of 24 h and control horizon of either 30 min or 1 h. In conclusion, MPC saved the total operation cost approximately 3.48% and 7.99% when the control horizon was set as 1 h and 30 min, respectively, compared to the conventional rule-based control (RBC) strategy.