Research On Optimal Load Dispatch Of Thermal Power Plant Considering Economy And Speediness

With the development of national economy and the continuous advancement of new energy power system,great changes have taken place in the power consumption structure.The peak-shaving situation of the power grid is becoming increasingly severe.Under the new normal,frequent and deep peak shaving poses great challenges to the economic operation and rapid response of thermal power units nationwide.On the basis of meeting the requirement of the total load instruction issued by the power grid dispatching department,it is of great significance to study how to optimize the distribution of power generation load of plant-level units on the premise of considering both economy and rapidity,which is to reduce the power supply cost and improve the competitiveness of thermal power plants.Considering the important influence of pulverizing output on units operation,this paper put the operation optimization of pulverizing system into the research scope of the plant-level optimal load dispatch.In order to reduce the unit consumption of pulverizing system,models of energy consumption characteristics of pulverizing system based on BP neural network were established.On this basis,the genetic algorithm was used to optimize the load dispatch of the pulverizing system.The simulation results showed that the difference between the predicted value and the actual value of the unit consumption of pulverizing system was mainly below 0.4kWh/t,indicating the reliability of the model.Compared with the pulverizing unit consumption before and after optimization,the optimized unit consumption decreased by up to 2kWh/t,most of which decreased by more than 1.5 kWh/t.The load disturbance was effectively reduced.On this basis,considering the operation cost and the speed of load response of thermal power units,this paper established a plant-level load optimal dispatch model considering economy and speediness,with strong flexibility and operability.Combined with the Equal Incremental Discharge Criterion,an improved genetic algorithm was proposed to overcome the disadvantage of slow convergence speed of the traditional genetic algorithm.The simulation results showed that the improved genetic algorithm effectively shortened the calculation time and enhanced the search rate,which provided an effective reference for the optimal load dispatch of coal-fired generating units during peak shaving.