基于GA-改进BP神经网络算法在大电网短路电流预测中的应用

Short-circuit current forecast application of big electrical network based on improved BP Artificial Neural Network combined with Genetic Algorithm

详细分析了目前我国电网的短路电流情况以及发展趋势,提出了基于遗传算法(GA)和改进的BP神经网络算法的三相短路电流预测方法,以一个实际的大区域电网为例,对其进行基于潮流的三相短路电流计算,找出短路电流水平薄弱点,并对较薄弱点的短路电流水平进行预测,仿真计算说明了本文所提出的算法的可行性和有效性。

In recent years, with the rapid growth of power load and network expansion, the problem of short circuit currents has become significant for the planning and operation of the power system. This paper analyzes in detail the short-circuit current situation as well as the development tendency in our country, proposes a new algorithm to forecast the three-phase short circuit current on the basis of Genetic Algorithm and improved BP Artificial Neural Network Algorithm. Taking a wide range electrical network as an example, the three-phase short-circuit current computation based on load flow is implemented. To find some weak points of short-circuit current level, two algorithms are used to carry out short- circuit current level forecast for those weak points. The feasibility and validity of the method proposed are shown by the simulation and computation. The forecast results provide scientific basis for decision-making for the power sector in the planning and construction of power grids which need some measures to limit the short-circuit current in time.