Application of Genetic Algorithms and Particle Swarm Optimization in the Optimization of Thermal Power Plant Cold-End Systems

In the actual operation of thermal power plant cold-end systems, parameters such as unit load, environmental temperature, cycle water temperature, and cycle water flow rate may deviate from their design values. This can lead to excessive energy consumption, reduced energy efficiency, higher power generation costs, and even increased unit temperatures that affect overall system stability. This study optimizes cycle water flow rate under certain variable operating conditions using a genetic algorithm to determine the optimal back pressure and ensure the unit operates under optimal conditions. For comparison, particle swarm optimization is also used under the same initial conditions, and the results are compared. The optimization model uses unit load, cycle water flow rate, and cycle water temperature as variables, with net power output as the objective function, to achieve optimization goals for various parameter variables. This ensures the unit operates with maximum economic efficiency under the best possible conditions.