Research On Micro-Grid Short-Term Load Forecasting Based On Spark And Support Vector Regression

With the energy shortage and environmental pollution problems become more and more serious,comprehensive development and effective use of new energy sources is imperative.Micro-grid is one of the efficient paths that can use new energy and optimize energy construction.In order to ensure the efficient operation of the micro grid economy,accurate load forecasting is becoming more and more important.Therefore,this paper studies the load forecasting of micro grid,which has important theoretical significance and practical value for the safety,energy saving and efficient operation of micro grid.Firstly,aiming at artificial bee colony algorithm is e asy to fall into local optimum and its slow convergence,add the optimal food source and inertia weight function,improved algorithm for food source updating method;Then according to the parameter optimization of support vector regression,transformed int o a combinatorial optimization problem,and the improved artificial bee colony algorithm is used to solve the optimization problem.,and establishes the prediction model of artificial bee colony algorithm to optimize the SVR.Taking the short-term load forecasting data of the micro grid as an example,the prediction results of the model are compared and analyzed.The results show that the prediction effect of the model is optimal and the running time is the shortest,and the model has better learning ability and generalization ability.In recent years the development of power system intelligent leads to load data of large scale and high dimensional,load forecasting facing single computing resource shortage,poor predictive real-time.For the big load data in the power system,this paper designed the above parallel algorithms in the Spark platform to speed up the historical data processing.Building a Spark computing cluster with one master node and seven data nodes using the equipment in our laboratory.Tes t the parallel performance of the parallel algorithm designed in this paper,the simulation results show that the method has faster processing speed compared with the commonly in huge amounts of data processing.