摘要
该文通过研究海量的发电机组历史污染物排放数据,提出一种基于LSTM-RNN深度学习的改进型发电机组排放预测算法ALSTM-RNN(A-R)。A-R算法可以有效地提取出模型特征量,结合数据的归一化对模型的结果进行优化调整,以降低模型训练时间,提高预测精度。通过在不同的发电机组测试试验,A-R算法较最小二乘法(LSM),支持向量机回归(SVR)具有较小的均方误差值,较LSTM-RNN模型预测方差更小,更加稳定,具有较好的鲁棒性。
Through studying massive historical data of pollutant emissions in generation sets,this paper puts forward an improved algorithm ALSTM-RNN(A-R)for predicting emissions of generation sets based on deep learning algorithm LSTM-RNN. A-R algorithm can extract features of the model effectively. Through the normalization of data to optimize and adjust results of the model,which is able to reduce the training time of our model and improve the predictive accuracy. By testing on the different generator sets,A-R algorithm has a relatively small mean square error compared with the least squares method(LSM)and support vector machine regression(SVR). Meanwhile,compared with LSTM-RNN,A-R method owns small predictive variance,a stable model and good robustness.
作者
梁肖
李端超
黄少雄
高夏生
高卫恒
杨训政
LIANG Xiao LI Duan-chao HUANG Shao-xiong GAO Xia-sheng GAO Wei-heng YANG Xun-zheng(Dispatching and Control Center,Anhui Electric Power Corporation,Hefei 230022,China Sehool of Computer Science,University of Science and Technology of China,Hefei 230027,China)
出处
《自动化与仪表》
2017年第10期68-71,76,共5页
Automation & Instrumentation
基金
国家电网公司科技项目(52120015007W
521200160026)
关键词
深度学习
递归神经网络
节能减排
预测模型
改进算法
deep learning
recurrent neural networks (RNN)
energy-saving and emission-reduction
forecasting model
improved algorithm