论文部分内容阅读
短期负荷预测是电力系统安全稳定运行的前提与保证。误差修正模型是在考虑相关因素相似度识别的预测方法基础上,利用BP神经网络优秀的学习能力捕获相关因素与历史预测误差的非线性映射。针对BP网络存在的自身缺陷,采用改进粒子群算法优化BP网络参数,得到可靠的误差预测,建立误差修正模型对未来负荷进行修正预测。通过算例验证了其可行性和实用性,达到了提高短期负荷预测准确度的目的。
Short-term load forecasting is the premise and guarantee for the safe and stable operation of power system. The error correction model is based on the prediction method of recognizing the similarity of related factors, and utilizes the excellent learning ability of BP neural network to capture the nonlinear mapping of related factors and historical prediction errors. Aiming at the defects of BP network, the improved particle swarm optimization algorithm is used to optimize the parameters of BP network to obtain reliable error prediction. The error correction model is established to correct the future load. The feasibility and practicability of the proposed method are verified by an example, which achieves the goal of improving the short-term load forecasting accuracy.