基于GTO优化CNN-LSTM的多变量负荷预测  

Multivariate Load Forecasting Based on GTO-optimised CNN-LSTM

作　　者：黄亚南 王宇驰 王诗博 Huang Yanan;Wang Yuchi;Wang Shibo(School of Electrical and Control Engineering,Liaoning Technical University,Huludao Liaoning 125105,China)

机构地区：[1]辽宁工程技术大学电气与控制工程学院,辽宁葫芦岛125105

出　　处：《现代工业经济和信息化》2024年第8期182-183,186,共3页Modern Industrial Economy and Informationization

摘　　要：提出了一种基于CNN-LSTM多变量负荷预测方法,分别介绍了CNN-LSTM、GTO算法,构建了多变量负荷预测模型,描述了多变量负荷预测思路,最后通过对比GTO优化前后的根均方差(RMSE)、平均绝对误差(MAE)、平均相对百分误差(MAPE)、决定系数(R2)四个指标,以及预测数据和真实数据的变化趋势图,证明GTO可以有效提高CNN-LSTM预测模型的鲁棒性以及精确性。A multivariate load forecasting method based on CNN-LSTM is proposed,which introduces CNN-LSTM,GTO algorithm respectively,followed by constructing a multivariate load forecasting model,describing the idea of multivariate load forecasting,and lastly,by comparing the root mean squared error(RMSE),the mean absolute error(MAE),and the mean relative percentage error(MAPE)before and after the optimisation of GTO,coefficient of determination(R2)four indicators,as well as the trend graphs of changes between predicted and real data,it proves that GTO can effectively improve the robustness as well as the accuracy of the CNN-LSTM prediction model.

关 键 词：人工大猩猩部队算法 卷积长短期记忆神经网络 多变量负荷预测 适应度优化 

分 类 号：TM715[电气工程—电力系统及自动化]