Application of a novel time-delayed power-driven grey model to forecast photovoltaic power generation in the Asia-Pacific region

Abstract

Abstract Photovoltaic engineering is one of the most important ways for utilizing solar energy. With fast development and large investment, the photovoltaic market has become more complex, leading to less reasonable samples for accurate forecasting. In this work, a time-delayed power effect with high flexibility is considered to develop a new grey system model, which can be more efficient in dealing with small and complex time series and shares a more general formulation. The Grey Wolf Optimizer is used to select the optimal nonlinear parameter. Three real-world cases in energy forecasting are used to validate the new model, showing its significant advantages over eight existing grey system models. The cumulative installed capacity of photovoltaic in Asia-Pacific from 2009 to 2018 is used to assess the effectiveness of the new model. Results indicate that high accuracy forecasts can be obtained by using the new model, showing its high potential in installed capacity of photovoltaic forecasting, which may be very useful in photovoltaic marketing and policy making.