Research On Short-Term Wind Power Forecasting In Dongying Wind Farm

In recent years,with the rapid development of national energy science and technology,wind power forecasting has received extensive attention as a renewable energy.As wind power is rich in resources and low in cost of mining and transportation,it is rapidly becoming a large-scale development and utilization of energy.In today's rapid development of power generation field and mature technology,compared with conventional energy comparison,wind power not only is favored by the people due to the non-pollution,but also its cost is relatively low.However,wind power also has its own defects,due to the characteristics of volatility and anti-peaking,wind farm is difficult to output the stable power,which bring many difficulties to wind power dispatching department.When the large-scale wind power is connected to grid,the work of the national grid dispatching department has been greatly challenged.Therefore,this thesis takes the Dongying wind farm as the research object and carries out the short-term prediction of wind power,which is of great significance for planning the power generation,scheduling of wind power system reserve capacity,reducing operation cost and ensuring the safe operation of power system.In this thesis,the short-term wind power forecasting of Dongying wind farm is studied.The main work is as follows:(1)The current situation and existing problems of wind power forecasting in Dongying wind farm are analyzed,and the basic principle and general process of wind power prediction are studied.(2)The prediction method of wind power of Dongying wind farm based on time series is studied.Based on the characteristics of historical data,the prediction model is established by using time series analysis method,and the short-term prediction of Dongying wind farm is carried out.The results of example analysis show that the power generation of wind farm can be predicted relatively accurately by using time series analysis method.(3)A prediction method of wind power based on improved BP artificial neural network is proposed.In order to improve the accuracy of wind power prediction,the basic principle of BP artificial neural network is studied,and the short-term wind power prediction of Dongying wind farm is carried out based on BP artificial neural network model.The prediction results show that the BP artificial neural network model can improve the forecasting effect of wind power and reduce the prediction error effectively.Furtherly,the programming of the prediction method is completed and applied to the short-term wind power prediction of Dongying wind farm in this thesis.Thus,the prediction accuracy is improved and the stability and economy of the power system are improved.