Short-term Wind Speed And Wind Power Prediction Based On Cloud Computing

Among renewable energy sources,wind energy is considered as one of the most promising and alternative energy source for fossil fuel power generation.However,due to the obvious intermittent and uncertain wind,the output power of wind turbines is unstable,which brings severe challenges to the stable operation of the power system.High-precision wind speed and wind power forecasting is of great significance in the convenience of grid connection planning,safety benefits,and maintenance arrangements.At the same time,transmission system operators will be able to perform real-time scheduling more easily.This paper studies wind speed and power prediction based on historical data from a SCADA wind farm in North China.In view of the strong nonlinearity of wind speed,a short-term wind speed prediction model based on singular spectrum analysis and improved particle swarm optimization adaptive fuzzy inference system is proposed.The method uses singular spectrum analysis to decompose the original series into trend and harmonic components,establish a fuzzy neural network model for each component,and finally superimpose the prediction results of each component to obtain the predicted wind speed value.Aiming at the disadvantages of updating the membership function in adaptive fuzzy systems,an improved particle swarm algorithm is used to optimize and update the membership function,which effectively improves the accuracy of model prediction.In order to prove the accuracy,efficiency and robustness of the proposed model,simulation experiments were added to compare the different models,and wind speed predictions at different time intervals were used to verify the performance of the model.Wind power is predicted using the indirect prediction method.Based on the results of wind speed prediction,the power is predicted through the wind speed-power characteristic curve.In order to improve the accuracy of prediction,the Copula function is introduced to construct the probabilistic wind speed-power curve,and the transformation of the confidence interval is used to remove the abnormal points in the measured wind speed-power curve.The piecewise linear method is used to fit the probabilistic wind speed-power curve,and the predicted power value is obtained from the wind speed prediction result.Simulation experiments were performed on the wind power prediction of a single wind turbine and the whole field,respectively,and the validity of the model was verified.In view of the huge amount of wind farm data,this paper combines the wind speed and wind power prediction model with a cloud computing platform to develop a wind speed and wind power prediction system based on the cloud computing platform.The system uses the Hadoop platform to solve the problem of insufficient single-point computing power,and uses the Spark cloud computing framework for parallel computing.The experiments simulate the calculation time and calculation accuracy of different node numbers,and the results show that the cloud computing platform improves the calculation efficiency.The cloud platform model has guiding significance for wind power forecasting of large wind farms.