稀疏广义导纳交流潮流用于快速事故分析与校正措施评估
Sparse Generalized-Admittance AC Power Flow for Fast Contingency Analysis and Remedial-Action Assessment
查看机构详情
- N-SIDE
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文提出稀疏广义导纳交流潮流方法，通过低秩更新和LU分解重用加速事故分析与校正措施评估，在大型电网测试中比pandapower快14.4至18倍。
中文摘要 AI 辅助
在输电系统运行中，重复的交流潮流计算是常见任务，特别是在事故分析和校正措施评估中。对于大型网络，其累积运行时间可能成为运行过程中的计算瓶颈。本文开发了广义母线导纳潮流方法（称为PFPD）的稀疏重构。负荷和发电机通过导纳矩阵对角线上的固定并联导纳项表示，而校正节点电流通过迭代计算以满足恒功率和稳压约束。与原始公式不同，松弛母线被视为固定电压边界，并从导纳块分解中移除。所得迭代重用初始广义非松弛矩阵及其PQ块的稀疏LU分解，而无需显式形成稠密逆矩阵。同一公式支持两种初始化模式：使用与主PFPD方法相同的平启动并联导纳启发式的未求解基态，以及从已求解运行点初始化的重复动作后计算。局部拓扑和参数变化表示为低秩导纳更新，所得导纳矩阵通过Woodbury恒等式求逆。可选的局部网络公式可在全网络细化之前提供热启动。在1354母线和9241母线PEGASE系统以及6717母线合成德克萨斯系统上的N-1实验，相对于pandapower实现了每次事故平均加速14.4至18.0倍。在变压器抽头位置动作上，该方法比pandapower快2.8至2.9倍，比PowSyBl OpenLoadFlow快7.2至29.9倍。
英文摘要
Repeated AC power-flow calculations are common tasks in transmission system operations, in particular for contingency analysis and remedial-action assessment. For large networks, their cumulative runtime can become a computational bottleneck in operational processes. This paper develops a sparse reformulation of the generalized bus-admittance power-flow method known as PFPD. Loads and generators are represented by fixed shunt admittance terms on the diagonal of the admittance matrix, while corrective nodal currents are iteratively computed to match the constant-power and regulated-voltage constraints. In contrast to the original formulation, the slack bus is treated as a fixed-voltage boundary and removed from the admittance block decomposition. The resulting iteration reuses sparse LU factorizations of the initial generalized non-slack matrix and its PQ block, without explicitly forming dense inverse matrices. The same formulation admits two initialization modes: an unsolved base case using the same flat-start shunt heuristic as in the primary PFPD method, and repeated post-action calculations initialized from a solved operating point. Localized topology and parameter changes are expressed as low-rank admittance updates and the resulting admittance matrices are inverted by means of the Woodbury identity. An optional local-network formulation can provide an warm start before full-network refinement. N-1 experiments on the 1354-bus and 9241-bus PEGASE systems and the 6717-bus synthetic Texas system yield average per-contingency speedups between 14.4 and 18.0 relative to pandapower. On transformer tap-position actions, the method is 2.8--2.9 times faster than pandapower and 7.2--29.9 times faster than PowSyBl OpenLoadFlow.
