Forecasting method for sources and loads in virtual power plant considering uncertainties of multiple sources and loads

Abstract Because of to the lack of primary energy and the deteriorating global environment, the key to getting rid of the existing difficulties is the development of clean and pollution-free new energy. On the one hand, to reduce the use of fossil energy, and on the other hand, to reduce emissions of polluting gases. So with the development of technology, more and more distributed power and load began to access the virtual power plant. This paper introduces PV and EVs(EVs) from the perspective of new energy applications and expounds on the background and significance of load forecasting and output power prediction. This paper introduces a variety of load prediction methods. Finally, Monte Carlo simulation is used to predict the EVs’ charging load, and BP neural network is used to build a photovoltaic power forecasting model. Based on the MATLAB R2017a simulation platform, this paper analyzes the EVs’ travel features in Beijing and takes the historical data and meteorological information of a photovoltaic power plant in Australia as an instance to analyze the influencing factors of PV.