摘要
时间序列预测在金融、医疗、交通和气象等领域发挥着重要作用。在长时间序列预测中,迫切需要提高预测的精度,解决内存不足等问题。近年来,Transformer模型在自然语言处理领域得以成功应用的同时,在预测研究领域也引起了学者们的广泛关注,Transformer变体Informer模型的研究在时间序列预测中取得了较大进展。本研究以Informer框架为基础,与加性注意力机制相结合,提出了A^(2)former模型。利用A^(2)former模型在ETT,WTH,ECL和PM2.5数据集上进行了长时间序列预测的实验,实验结果表明所提模型在长时间序列预测中表现出比基线方法(如Informer模型和LSTMa模型)更好的性能。A^(2)former模型不仅将计算时间复杂度降低到线性,而且可以实现更有效的序列建模。本研究的工作为时间序列预测提供了有益参考。
Time series forecasting plays an important role in the fields of finance,medicine,transportation and meteorology.In long sequence time-series forecasting(LSTF),it is urgent to improve the forecast accuracy and solve the problems of insufficient memory.In recent years,the successful application of Transformer in natural language processing has also attracted a lot of attention forecasting studies.Informer model,a variant of Transformer,has made great progress in time series forecasting.In this paper,we proposed a A^(2)former model,which is based on Informer and additive attention mechanism.The A^(2)former model was experimented on ETT,WTH,ECL and PM2.5 datasets for LSTF.Experimental results show that A^(2)former exhibits better performance than existing baseline methods(e.g.,LSTMa and Informer)in LSTF.A^(2)former not only reduces time computational complexity to linearity and improves forecast accuracy,but also enables more efficient sequence modeling,our work provides a valuable input for time series forecasting.
作者
胡倩伟
王秀青
安阳
张诺飞
王广超
HU Qianwei;WANG Xiuqing;AN Yang;ZHANG Nuofei;WANG Guangchao(College of Computer and Cyber Security,Hebei Normal University,Shijiazhuang 050024,China;Hebei Provincial Key Laboratory of Network&Information Security,Hebei Normal University,Shijiazhuang 050024,China;Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics&Data Security,Hebei Normal University,Shijiazhuang 050024,China)
出处
《人工智能科学与工程》
CAS
北大核心
2024年第1期41-50,共10页
Journal of Southwest China Normal University(Natural Science Edition)
基金
国家自然科学基金项目(61673160)
河北省自然科学基金项目(F2018205102)
河北省高等学校科学技术研究重点项目(ZD2021063)。
