基于门控多层感知机和Informer的多通道电力负荷预测
Multi-Channel Power Load Forecasting Based on Gated Multilayer Perceptron and Informer
DOI: 10.12677/airr.2024.132039, PDF,   
作者: 孙卓远：上海电力大学计算机科学与技术学院，上海；吕学文：上海电力大学计算机科学与技术学院，上海；全程上海智能科技有限公司，上海；王继军：赢科储能科技有限公司，湖南 长沙
关键词: 负荷预测；因果卷积；深度学习；注意力机制；Power Forecasting； Causal Convolution； Deep Learning； Attention Mechanism
摘要: 在电力领域，利用时间序列方法进行电力负荷预测已成为众多研究的热点。为了解决电力负荷预测准确率低的问题，本文提出了融合门控多层感知器和增强因果卷积的多通道时间序列融合网络GMEC-Informer，提高了模型捕捉长短期时间序列信息依赖的能力。为了证明本文模型的优越性，本文在广泛使用的数据集上与多个模型进行了比较，实验结果表明本文提出的GMEC-Informer具有更高的预测精度，可以为时间序列预测提供更好的研究方向。
Abstract: In the field of electric power, power load forecasting using time series methods has become a hot spot in many researches. In order to solve the problem of low accuracy of power load prediction, this paper adds gated multilayer perceptual units into the Informer model, and proposes GMEC-Informer, a multichannel time-series fusion network that fuses gated multilayer perceptron and enhanced causal convolution, which improves the model’s ability to capture long-short time series information dependence. In order to prove the superiority of the model in this paper, it is compared with several models on widely used datasets, and the experimental results show that GMEC-Informer has higher prediction accuracy and can provide a better research direction for time series prediction.
文章引用：孙卓远, 吕学文, 王继军. 基于门控多层感知机和Informer的多通道电力负荷预测[J]. 人工智能与机器人研究, 2024, 13(2): 375-387. https://doi.org/10.12677/airr.2024.132039

参考文献

[1] 史建楠, 邹俊忠, 张见, 等. 基于DMD-LSTM模型的股票价格时间序列预测研究[J]. 计算机应用研究, 2020, 37(3): 662-666.
[2] Song, W., Wang, C., Dong, T., et al. (2023) Hierarchical Extraction of Cropland Boundaries Using Sentinel-2 Time-Series Data in Fragmented Agricultural Landscapes. Computers and Electronics in Agriculture, 212, Article 108097. [Google Scholar] [CrossRef] 
[3] 张栗粽, 王谨平, 刘贵松, 等. 面向金融数据的神经网络时间序列预测模型[J]. 计算机应用研究, 2018, 35(9): 2632-2637.
[4] 江洋洋, 金伯, 张宝昌. 深度学习在自然语言处理领域的研究进展[J]. 计算机工程与应用, 2021, 57(22): 1-14.
[5] Ma, R., Angryk, R. and Scherer, R. (2022) Special Issue on Deep Learning for Time Series Data. Neural Computing and Applications, 34, 13147-13148. [Google Scholar] [CrossRef] 
[6] Singh, A., Srivastava, M.K. and Singh, N.K. (2019) AI-Based Short-Term Electric Time Series Forecasting. International Journal of Innovative Technology and Exploring Engineering, 8, 3255-3261.
[7] 谭风雷, 徐刚, 李义峰, 等. 基于相似日和相似时刻的变压器顶层油温预测方法[J]. 电力工程技术, 2022, 41(2): 193-200.
[8] Wang, X. and Wang, Y. (2016) A Hybrid Model of EMD and PSO-SVR for Short-Term Load Forecasting in Residential Quarters. Mathematical Problems in Engineering, 2016, Article ID: 9895639. [Google Scholar] [CrossRef] 
[9] 杨汪洋, 魏云冰, 罗程浩. 基于CVMD-TCN-BiLSTM的短期电力负荷预测* [J/OL]. 电气工程学报, 1-10.
http://kns.cnki.net/kcms/detail/10.1289.TM.20230601.1229.002.html, 2024-02-20.
[10] Salinas, D., Flunkert, V., Gasthaus, J., et al. (2020) DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks. International Journal of Forecasting, 36, 1181-1191. [Google Scholar] [CrossRef] 
[11] 崔星, 李晋国, 张照贝, 等. 基于改进粒子群算法优化LSTM的短期电力负荷预测[J]. 电测与仪表, 2024, 61(1): 131-136.
[12] Kim, M., Lee, S. and Jeong, T. (2023) Time Series Prediction Methodology and Ensemble Model Using Real-World Data. Electronics, 12, Article 2811. [Google Scholar] [CrossRef] 
[13] 田英杰, 苏运, 郭乃网, 等. 基于时间序列嵌入的电力负荷预测方法[J]. 计算机应用与软件, 2018, 35(11): 55-60, 73.
[14] Sesti, N., Garau-Luis, J.J., Crawley, E., et al. (2021) Integrating LSTMS and GNNS for COVID-19 Forecasting. arXiv preprint arXiv:2108.10052. [Google Scholar] [CrossRef] 
[15] 代业明, 周琼. 基于改进Bi-LSTM和XGBoost的电力负荷组合预测方法[J]. 上海理工大学学报, 2022, 44(2): 138-147.
[16] Knoll, G. and Lindner, B. (2022) Information Transmission in Recurrent Networks: Consequences of Network Noise for Synchronous and Asynchronous Signal Encoding. Physical Review E, 105, Article 044411. [Google Scholar] [CrossRef] 
[17] Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 600-601.
[18] 刘文婷, 卢新明. 基于计算机视觉的Transformer研究进展[J]. 计算机工程与应用, 2022, 58(6): 1-16.
[19] Zhou, H., Zhang, S., Peng, J., et al. (2021) Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 11106-11115. [Google Scholar] [CrossRef] 
[20] 张松慧, 熊汉江. 融合地理社交和时间序列信息嵌入排名位置推荐模型[J]. 计算机应用研究, 2019, 36(9): 2618-2624.
[21] Xu, H., Peng, Q., Wang, Y., et al. (2023) Power-Load Forecasting Model Based on Informer and Its Application. Energies, 16, Article 3086. [Google Scholar] [CrossRef] 
[22] Liu, H., Dai, Z., So, D., et al. (2021) Pay Attention to MLPs. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S. and Wortman Vaughan, J., Eds., Advances in Neural Information Processing Systems 34, MIT Press, Cambridge, 9204-9215.
[23] 宋绍剑, 姜屹远, 刘斌. 一种TCN的改进模型及其在短期光伏功率区间预测的应用[J]. 计算机应用研究, 2023, 40(10): 3064-3069.
[24] 周蜀杰, 曾园园, 江昊. 基于扩张因果卷积的城市客流量预测算法[J]. 武汉大学学报(工学版), 2023, 56(2): 218-225.

为你推荐