一种快速求解大规模安全约束最优潮流的多核并行方法

A high-speed multi-core parallel method for solving large-scale security constrained OPF

针对传统安全约束最优潮流计算方法占用内存大、计算时间长的问题,提出了一种多核并行安全约束最优潮流算法。由正常运行状态检验预想故障状态,选取少量严重故障逐步修正正常运行状态,直到所有状态都得到满足。多核并行技术用于实现算法从高到低层次的高效率整体并行,以提高计算速度。其中,采用有向无环图并行数值分解算法实现正常运行状态修正过程的细粒度并行,并根据算法特性,直接实现预想故障状态检验过程的粗粒度并行。某省-3301节点系统(预设693个故障)等3个系统的计算结果表明:随着系统规模的扩大,所提方法占用内存不足传统方法的1%,且计算速度可快于传统方法三个数量级以上。

The traditional Security Constrained Optimal Power Flow（SCOPF） methods are limited for the realistic systems due to the high memory consumption and low computation efficiency. A high-speed multi-core parallel algorithm is proposed to overcome these disadvantages. The contingencies are checked using the pre-contingency configuration at first. Afterward, a few serious contingencies are extracted to correct gradually the normal operation status until all conditions are satisfied. The multi-core parallel technology is applied to the algorithm from both high and low levels for obtaining high efficient parallel computation. The high-level parallels are used during the contingencies checking procedure, and fine-grained parallels are used during the pre-contingency configuration correction process based on the directed acyclic graph（DAG） parallel numerical decomposition algorithm. The proposed method has been successfully tested on three systems, which include a realistic provincial 3301-bus system with 693 contingencies. The numerical results indicate that the proposed method is suitable for solving large SCOPF problems because of fast and steady computation time. Furthermore, the memory consumptions of the proposed method are less 1% than that of traditional method, and the computation speeds are three orders of magnitude faster than that of the traditional ones as the system scale enlarges.