An adaptive load dispatching and forecasting strategy for a virtual power plant including renewable energy conversion units

The increasing awareness on the risky state of conventional energy sources in terms of future energy supply security and health of environment has promoted the research activities on alternative energy systems. However, due to the fact that the power production of main alternative sources such as wind and solar is directly related with meteorological conditions, these sources should be combined with dispatchable energy sources in a hybrid combination in order to ensure security of demand supply. In this study, the evaluation of such a hybrid system consisting of wind, solar, hydrogen and thermal power systems in the concept of virtual power plant strategy is realized. An economic operation-based load dispatching strategy that can interactively adapt to the real measured wind and solar power production values is proposed. The adaptation of the load dispatching algorithm is provided by the update mechanism employed in the meteorological condition forecasting algorithms provided by the combination of Empirical Mode Decomposition, Cascade-Forward Neural Network and Linear Model through a fusion strategy. Thus, the effects of the stochastic nature of solar and wind energy systems are better overcome in order to participate in the electricity market with higher benefits.