Adaptive Robust Optimal Scheduling of Combined Heat and Power Microgrids Based on Photovoltaic Mechanism/Data Fusion-Driven Power Prediction

In order to effectively deal with the adverse effects of the randomness of photovoltaic output on the operation of combined heat and power (CHP) microgrids, this paper proposes an adaptive robust optimal scheduling strategy for CHP microgrids based on photovoltaic mechanism/data fusion-driven power prediction. Firstly, the mechanism of the clear sky radiation model is used to calculate the photovoltaic clear sky limit output and random output, and the latter is reorganized in different periods by using the idea of similar days. Then, the data-driven random prediction results are superimposed with the clear sky limit output, the photovoltaic mechanism/data fusion-driven power prediction model is established, and the fusion-driven power prediction framework is provided. Secondly, the boundary information of uncertain factors is deeply explored, and an adaptive robust uncertainty set considering the confidence interval of predictive error statistical information is constructed. On this basis, a robust optimization model of CHP microgrids with the lowest operating cost is proposed, and the optimization model is solved by column and constraint generation algorithm. Finally, the rationality and effectiveness of the proposed model are verified through simulation examples and analytical calculations.