Model-based optimal control of VAV air-conditioning system using genetic algorithm

A control strategy using a system approach based on predicting the responses of overall system environment and energy performance to the changes of control settings of VAV air-conditioning systems is developed. Incremental dynamic models with 'self-tuning' of the VAV system are developed and used. A genetic algorithm is used by the strategy to solve the on-line optimisation problem of multiple parameters. The strategy is tested and evaluated in a simulated 'living' environment under various weather conditions.Department of Building Services Engineerin