Research On Demand Response Strategy Based On The Data Analysis Of Electric Consumption

Nowadays,with the rapid development of smart grid,various kinds of electric data about users is also increasing.The data mining technology is applied to the data analysis and the strategy optimization of demand response so that it can be used to explore some laws or patterns of user electricity consumption.So an urgent problem needs to be solved is how to effectively mine the electric data and use the information obtained to support the optimization of demand response policies and build the smart grid.In order to solve the above problems,this paper starts with data analysis of user's electricity consumption behavior and cluster analysis of data mining.The users are classified by load type,which is used as the characteristics of consumption behaviour.then data source is simplified by dimension reduction in this way.Then the demand response strategy research is carried out.Firstly,an intelligent electricity demand response scheduling strategy used to optimize the user daily load demand response scheduling in intelligent electricity cell about multi-type load is proposed in this paper.It is based on particle correction optimization.By solving constraint deviations of user load distribution in optimal solution,optimal operation is realized.Then a demand response optimization strategy considering uncertainty of participation rate is proposed on this basis,on account of user response uncertainty in the demand response process.The study of optimization strategy is improved further.Finally,the experimental results proves the effectiveness of the proposed optimization strategies from various aspects,and the two strategies both can realize the peak load shifting better.In addition,the strategy related to uncertainty can partly reduce the scheduling cost of grid side.Therefore,this paper partly provides theoretical support for the demand response strategy and the construction and development of smart grid.