基于海量场景降维的配电网源网荷储协同规划

风电、光伏等新能源大规模接入配电网，给配电网规划方法的效率和规划结果的经济性带来了极大挑战。为了解决配电网中新能源海量运行数据与配电网源网荷储协调规划之间的配合问题，提出了基于海量场景降维的配电网源网荷储协同规划方法。首先，通过主成分-高斯混合聚类算法对风-光-荷海量高维场景进行降维聚类，得到风-光-荷的典型场景集；然后，构建了面向海量场景的配电网源网荷储协同规划模型，并采用二阶锥松弛技术将模型中非凸约束转凸处理；最后，在Portugal 54节点配电网算例上验证了海量场景降维聚类方法和规划模型的有效性。

Massive Scenario Reduction Based Distribution-Level Power System Planning Considering the Coordination of Source,Network, Load and Storage

The integration of high-proportion renewable power generation has brought great challenges to the efficiency of distribution network planning methods and the economy of planning results. In order to solve the problem of coordination between the massive operation data of renewable power generation and the coordinated planning of the source-network-load-storage, this paper proposes a coordinated planning method of the source-network-load-storage based on the massive scenario dimension reduction. Firstly, the dimensionality reduction clustering is carried out on the wind-light-load mass high-dimensional scenarios by the principal component Gaussian mixture clustering algorithm, and the typical scenario set of wind and power loads is obtained; then, a source-network-load-storage coordination planning model of distribution network for massive scenarios is constructed, and the second-order cone relaxation technique is adopted to convert the non-convex constraints to convex ones; finally, the effectiveness of the proposed massive scenario dimension reduction clustering method and distribution network planning model is verified on the Portugal 54-node distribution network.