BIRCH Algorithm and Wasserstein Distance Metric Based Method for Generating Typical Scenarios of Wind Power Outputs

With the ever-increasing penetration of renewable energy generation such as wind power and solar photovoltaics, the power system concerned is suffering more extensive and significant uncertainties. Scenario analysis has been utilized to solve this problem for power system planning and operation, but heavy computation burden is involved especially for large-scale power systems. To better address this problem, an algorithm based on the BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) algorithm and Wasserstein distance metrics is proposed in this paper to reduce the scenarios of wind power outputs. First, the Wasserstein distance is employed to attain the optimal quantiles for discretizing the continuous density function of wind power outputs. Then, the BIRCH algorithm, which is suitable for large volume of data, is utilized to determine the typical scenarios. Finally, the effectiveness of the proposed algorithm is demonstrated through case studies and comparisons with some existing algorithms.