Distributionally robust optimal dispatching of integrated electricity and heating system considering source-load uncertainty

The robust optimal operation of integrated electricity and heating system is severe affected by the uncertainty of renewable energy output and load demand. On this basis，a distributionally robust optimal dispatching（DROD） model of integrated electricity and heating system based on the improved Wasserstein metric considering the uncertainty of source-load is proposed. The ambiguity set of wind power prediction value based on the improved Wasserstein metric in extreme scenarios is established to reduce the scale of the ambiguity set for wind power prediction value. Furthermore，the improved Wasserstein generative adversarial networks based on gradient normalization is proposed to model the uncertainty of load demand and improve the accuracy of load uncertainty modeling. Then，the DROD model considering generation cost，regulation cost and so on is constructed. And the model is transformed into a solvable mathematical model based on dual theory and the Lagrange multiplier method. Taking the modified 9-bus system and IEEE 118-bus system as the example，it is proved that the proposed model has higher solution efficiency，better economy and robustness. © 2023 Electric Power Automation Equipment Press. All rights reserved.