Research On Energy Dispatching Of Household Microgrid Considering Real-time Electricity Price

With increasingly severe energy and environmental issues,smart grids have gradually become the key to development.As an important part of the smart grid,the home microgrid has a close relationship with users.By dispatching the household microgrid,the energy can be allocated reasonably and the cost of electricity can be reduced at the same time,which has very important practical significance.Based on the demand-side response,this paper proposes a household microgrid energy dispatch method based on the real-time electricity price background considering the comprehensive user experience index.Aiming at the redundancy of sample set selection in real-time electricity price forecasting and the similarity of electricity price trends within a certain period of time,this paper proposes a real-time electricity price curve clustering method based on Multi-Dimensional Scaling(MDS).First,the MDS algorithm is used to reduce the dimension of the real-time electricity price curve,and then the CRITIC-entropy weight method is used for the weight configuration of the reduced samples,and then the weighted K-means algorithm is used for clustering,and the gray correlation degree is again used for similar day selection The method selects the cluster cluster with the largest correlation with the day to be predicted,and finally predicts the electricity price through the BP neural network.The calculation example shows that the clustered electricity price samples can reduce the redundant information between the data and improve the prediction accuracy.The MDS dimensionality reduction clustering algorithm is better than the traditional K-means clustering algorithm and has higher prediction accuracy.The user experience will be affected during the load energy dispatching of the household microgrid.This article first established a model of the family microgrid,built a model that includes wind power,photovoltaic power,storage batteries,and loads,and further subdivided the types of loads.The loads were divided into rigid loads,translatable loads,reduced loads,and interruptible loads.load.Then analyzed the factors that affect the user experience of each load,and concluded that: rigid loads cannot be moved during energy dispatch,translatable loads are affected by operating time,load reduction(air conditioning)is affected by temperature,and load can be interrupted(electric Cars)are affected by electricity consumption.Based on these influencing factors,a user experience model was established,and energy scheduling was performed with the lowest power cost,the highest comprehensive user experience index,and the lowest power cost and the highest comprehensive user experience index as the objective function for energy scheduling.Solving,calculation examples show the effectiveness of the proposed model.