基于ARMA-GABP组合模型的电网大停电事故损失负荷预测

损失负荷作为衡量大停电事故风险的重要指标，如何对其进行准确预测对于电网的安全运行具有十分重要的参考意义。选取1981—2016年东北电网和西北电网的大停电事故损失负荷作为实验数据进行分析，为消除电网发展对数据分析产生的影响，采用相对值法对电网大停电事故损失负荷进行处理。根据实验数据的特点，将损失负荷相对值的数据结构分解为线性和非线性残差部分，建立自回归滑动平均(ARMA)模型和遗传算法(GA)优化的误差反向传播(BP)神经网络组合模型，对东北电网大停电事故进行综合分析与预测。将所提模型的预测结果与单一模型和ARMA-BP模型的预测结果相对比，结果表明，所提模型的预测精度更高，预测效果较为理想。为进一步验证该预测模型的有效性，将西北电网大停电事故数据代入预测模型，实验结果表明该预测模型在电网大停电事故损失负荷方面具有良好的预测效果。

Power Loss Prediction of Large Blackouts in Power Grid Based on ARMA-GABP Combined Model

Power loss is an important index to measure the risk of blackouts, and it is very important to accurately predict it for the safe operation of power grid. In this paper, the power loss of large blackouts in Northeast Power Grid and Northwest Power Grid from 1981 to 2016 are selected as experimental data. In order to eliminate the influence of power grid development on data analysis, the relative value method is used to process the power loss of grid blackouts. According to the characteristics of the experimental data, the data structure of the relative value of power loss is decomposed into linear and non-linear residuals. A combined ARMA and GABP neural network model is established to comprehensively analyze and predict the large-scale blackout accidents in Northeast China Power Grid. The prediction results of the proposed model are compared with those of the single model and the ARMA-BP model. The results show that the proposed model has higher prediction accuracy and better prediction effect. In order to further verify the validity of the forecasting model, the data of large blackouts in Northwest Power Grid are substituted into the forecasting model. The experimental results indicate that the forecasting model has a good forecasting effect in terms of power loss caused by large blackouts.