DPO—BP在电力负荷短期预测中的应用

Application of DPO—BP in Short-Term Load Forecasting

摘要: 电力系统运行过程中，负荷的短期预测具有十分重要的意义。可以将影响负荷的多种因素如气象，待预测日前几天的负荷数据，以及日平均负荷等作为BP神经网络的输入节点，输出负荷值作为网络的输出。本文先将BP神经网络运用到电力负荷的短期预测中，但网络的训练效果受其初始权值、阈值的影响较大，预测效果并不理想。鉴于海豚群算法(DPO)具有收敛速度快、鲁棒性好等优点，将其运用到BP神经网络的权值、阈值优化问题上，并与PSO-BP算法相比，证明了其在短期负荷预测中优越性。

Abstract: The short-term load forecasting is of great significance for the power system operation. The factors such as weather, load data and average load before forecasting, etc., have been used as the input nodes of the neural network, and the output load value has been used as the output of the network. In this paper, the BP neural network is applied to short-term load forecasting, but the training effect of the network is influenced by the initial weights and thresholds, and the generalization ability is poor. Because of the advantages of fast convergence, good robustness, the Dolphin Partners Optimization Algorithm (DPO) is applied to the BP neural network weights and threshold optimization. The practical experiment results show that the results of DPO-BP are superior to the results of PSO-BP.