论文部分内容阅读
电力系统实现经济运行的前提必须是迎合电力负荷的需要、这对电力系统的安全稳定运行有重要意义。BP神经网络是一种具有强大的非线性映射能力的人工神经网络,在解决复杂的非线性问题中普遍得到应用。比如将BP神经网络应用于电力系统负荷预算将有效提高电力公司的发电效率,但BP神经网络极易陷入局部极小值以及收敛速度慢等问题。因此对BP神经网络改进算法进行研究,得出了用于电力符合预算的模型训练速度及预测误差,结果表明,改进的算法对负荷预测是行之有效的。
The premise of the power system to achieve economic operation must meet the needs of the power load, which is of great significance to the safe and stable operation of the power system. BP neural network is an artificial neural network with strong nonlinear mapping ability, which is widely used in solving complex nonlinear problems. For example, applying BP neural network to power system load budget will effectively improve the power generation efficiency of power company, but BP neural network can easily fall into the local minimum and the convergence speed is slow. Therefore, the improved BP neural network algorithm is studied, and the model training speed and prediction error for the power budget are obtained. The results show that the improved algorithm is effective for load forecasting.