Research On Microgrid Optimal Dispatching Method Considering Intermittent Energy Uncertainty

With the shortage of traditional fossil energy and the increase of environmental pollution,clean and renewable energy technology is bound to become a key means to achieve the harmonious development of man and nature.As the new energy with the largest installed capacity,photovoltaic and wind power have a large impact on the output power due to environmental factors and show strong uncertainties,which poses great challenges to the user’s power quality and the reliable operation of the microgrid system.At the same time,the imbalance of supply and demand caused by the uncertainty of the side also brings difficulties to the formulation of the scheduling plan.In the future smart power market environment,the supply and demand of renewable energy,load-side resources,and energy storage will be adjusted to each other,closely integrated,and developed in a unified manner.The research contents of the paper are as follows:First,for the uncertainty of photovoltaic power generation power,based on the orthogonal decomposition theory,the principal components affecting photovoltaic power generation are analyzed,and the variables in descending order and the cumulative variance contribution rate of 85% are selected as PSO-PCA-RBF neural The input data of the network model improves the training speed of the model.At the same time,the PSO algorithm with strong global search ability is used to optimize the weight and threshold of the RBF neural network.By improving the prediction accuracy of photovoltaic power generation,the uncertainty of new energy power generation is reduced.At the same time,considering that more and more electric vehicles will participate in the electric power dispatching of the microgrid in the future,it will bring a larger peak-to-valley margin to the original system.It is considered that electric vehicles can be used as a backup power source for system requirements,and can also use photovoltaic charging requirements to absorb photovoltaic power generation.By studying the driving,charging and discharging characteristics of electric vehicles,and simulating the system load based on Monte Carlo simulation method,it guides the electric vehicle to reasonably perform the charging and discharging behavior,and further grasps the demand laws of electric vehicles.The simulation comparison shows that considering the time-of-use electricity price,the charge and discharge requirements of electric vehicles are more consistent with the stability and economy of the system than the disordered state.Finally,on this basis,in order to improve the consumption of new energy and reduce the startstop costs of thermal power units,the price-based demand response strategy is used to guide the adjustable load in the system to reduce demand at the peak of the dispatch cycle and expand demand at the bottom In order to reduce the peak-valley difference of the system.With the goal of the highest operating efficiency of the microgrid,constrained by the output of the micropower source and the adjustable load cost,the wind-solar-fire-storage joint optimal scheduling model of price-type demand response is established,and the flexibility of the adjustable load is used to optimize energy contribute to realize economic optimal dispatch of micro-grid system.At the same time,in order to ensure the richness of the sample population of the particle swarm optimization algorithm,based on the improved PSO-ACM algorithm,the population convergence degree is checked.Finally,MATLAB simulation results show that this strategy effectively improves the difficulty of power system optimal dispatching,while reducing the load peak-valley difference and improving economy.