Font Size: a A A

Research On The Power Ramp Prediction Method Of Large Wind Farm Based On Intelligent Algorithm

Posted on:2018-04-19Degree:MasterType:Thesis
Country:ChinaCandidate:Q Y HuangFull Text:PDF
GTID:2322330518488311Subject:Engineering
Abstract/Summary:PDF Full Text Request
Wind power ramp is the wide fluctuations of the wind power in a short time scale.With the connection of fluctuant wind power to the power grid,the influence of wind power ramp on the safety and stability of power system is becoming more and more serious.Especially in extreme weather conditions,wind power ramp can make the power system difficultly maintain the original power balance and frequency stability and even causes the outage.For the problems of low accuracy and poor stability of wind power ramp prediction,this paper presents a prediction method of wind power ramp.The specific research contents are as follows:(1)This paper analyzes the occurrence mechanism of wind power ramp and wind power ramp characteristics,studies the relationship between wind speed,wind direction,temperature,humidity,pressure and power ramp and determines the influence parameters of wind power ramp prediction.(2)The intrinsic mode decomposition is performed for the wind power ramp applied the adaptive sparse-time frequency analysis,then the model of wind power ramp prediction model is established by using extreme learning machine neural network which is combined with the weather information of numerical weather forecast,and the model can improve the prediction accuracy are verified by the example simulation.(3)In order to improve the convergence of the algorithm and prevent premature convergence performance,the particle swarm algorithm based on the information sharing mechanism is used to strengthen the exchange of information between the particles,and through the chaos and reverse learning strategies the diversity of particles is increased,so as to the algorithm to find the optimal path is optimized,jumped out the local optimal value.The effectiveness of the improved strategy is verified by testing the functions.(4)The combination prediction model is established and the improved particle swarm optimization algorithm is used to optimize the weight of the combined model.Combined with the practical engineering application,the design and development of the wind power climbing event prediction system are carried out,the feasibility of the prediction model is verified by the engineering example.
Keywords/Search Tags:wind power ramp prediction, adaptive and sparsest time-frequency analysis, extreme learning machine, particle swarm optimization algorithm
PDF Full Text Request
Related items