Development of a distributed artificial fish swarm algorithm to optimize pumps working in parallel mode

The existing control systems for the parallel pumps in HVAC systems are mostly based on a centralized structure in which all the data from sensors and control instructions are processed by a master controller. This structure has somehow limited the stability, expandability and the universality of the control system. The strategies are always case by case ones which cannot be easily transplanted to other systems and when some devices are out-of-order the entire control system will be influenced. In this paper, a distributed control structure has been proposed for the parallel pumps in which the master controller is replaced by several independent distributed controllers cooperating together to handle the global task. An evolutionary algorithm AFSA (artificial fish swarm algorithm) has been transplanted to the proposed structure to optimize the pumps working in parallel mode. Simulation studies have been conducted based on the models of a physical pump system and the performance of the proposed algorithm is...