Optimized Scheduling Of Composite Energy Power Systems With Wind Power Grid-connected

As a clean energy,wind power has a rapid development in the world,the proportion of wind power installed capacity is growing.Although wind power has certain advantages,mainly in the reduction of pollutant emissions and power generation costs,etc.,but the attendant is the large-scale wind power grid will have a certain impact on the power system.The most striking feature of wind power is the greater randomness.Large-scale wind power grid will challenge the safe operation of the power grid,and has a certain adverse impact on the system scheduling plan.But the wind power is not taken into account in the initial planning of the grid.Therefore,this thesis mainly studies two aspects:improving the prediction accuracy of wind power and optimizing the power system of complex energy with clean renewable energy.Increasing the forecast accuracy of wind power generation has a great significance for the reasonable arrangement of scheduling plans and the reduction of reserve capacity of the system.In this thesis,BP neural network is used to test the power of wind turbine directly and indirectly.For the low predicting accuracy of a single BP neural network,the thesis establish the time series model to select the network input variables,the training process of BP neural network is optimized by genetic algorithm.Taking Two Units of a Wind Farm in China as an example,BP neural network method,GA-BP and time series optimization method are used to predict wind power respectively.The simulation results show that the genetic algorithm and time series optimize the selection of neural network structure and input variables,and improve the prediction accuracy.On the basis of improving the accuracy of wind power generation prediction,the thesis establishes a multi-objective optimal dispatching model for Wind-Fire-Water energy power system.For a multi-objective and multi-constrained model.The use of traditional linear or dynamic programming solutions fails.This paper mainly uses particle swarm intelligence algorithm to solve it.Based on the increase of the perturbed LDW,this thesis proposes an improved adaptive particle swarm optimization algorithm for the adaptive variable inertia weight coefficient and the smaller probability,and the test system of 10 sets of thermal power units is used to simulate the test function with the lowest running cost as the objective function.The simulation results show the superiority of the improved particle swarm optimization algorithm.In this thesis,a small number of wind turbines and hydropower units are used to establish the optimal dispatching model in the 24-node system,so as to provide the theoretical and practical basis for the large new energy grid-connected power system.On the basis of considering the traditional scheduling model,the economic scheduling of the thermal power unit is taken as the objective function.According to the characteristics of the hydropower station during the flood season,the plain water period and the dry season,the paper uses the improved particle swarm optimization algorithm to reflect the influence of the regulating ability of the hydropower station on the optimal dispatching of the power system.