收稿日期: 2024-07-04
网络出版日期: 2024-09-23
基金资助
国家自然科学基金(62377012); 上海市大数据管理系统工程研究中心开放基金(HYSY21022)
Study on short-term electricity load forecasting based on SF-Transformer for intelligent education platform
Received date: 2024-07-04
Online published: 2024-09-23
建设智能教育平台是推动教育智能化的一个重要过程, 但智能教育平台依赖的人工智能模型在训练过程中会消耗大量电力, 因此, 开展短期电力负荷预测对建设智能教育平台具有重要意义. 针对在考虑多个属性开展短期电力负荷预测时, 由于部分属性与电力负荷数据的相关性不强并且Transformer无法捕捉电力负荷数据的时间相关性, 而导致电力负荷预测不够准确的问题, 基于SR (Székely and Rizzo)距离相关系数、融合时间定位编码和Transformer, 提出了一种短期电力负荷预测模型SF-Transformer. SF-Transformer通过SR距离相关系数对影响电力负荷数据的属性进行筛选, 选择与电力负荷数据之间SR距离相关系数较大的属性. SF-Transformer采用一种全局时间编码与局部位置编码相结合的融合时间定位编码, 有助于模型全面获取电力负荷数据的时间定位信息. 在数据集上开展了实验, 实验结果表明SF-Transformer与其他模型相比, 在两种时长上进行电力负荷预测具有更低的均方根误差和平均绝对误差.
关键词： 智能教育平台; 短期电力负荷预测; SR距离相关系数; 融合时间定位编码; Transformer
冯艳丽 , 周宇 , 黄福兴 , 万俊岭 , 袁培森 . 基于SF-Transformer的智能教育平台短期电力负荷预测研究[J]. 华东师范大学学报（自然科学版）, 2024 , 2024(5) : 173 -182 . DOI: 10.3969/j.issn.1000-5641.2024.05.016
Building an intelligent education platform is an important process in the promotion of the intelligence of education. However, the artificial intelligence model on which intelligent education platforms rely consumes a large amount of electricity and energy during its training process, therefore, it is of great significance to carry out a short-term power load prediction for building an intelligent education platform. However, the major issue is the weak correlations between some attributes and power load data when considering multiple attributes during short-term power load forecasting, and the Transformer cannot capture the temporal correlation of power load data, which leads to a lack of accuracy in power load forecasting. Therefore, a short-term power load forecasting model, SF-Transformer is proposed that is based on the SR (Székely and Rizzo) distance correlation coefficient, fusion temporal localization coding and Transformer. The SF-Transformer filters the attributes that affect the power load data by using the SR distance correlation coefficient and selects the attributes that have higher SR distance correlation coefficients with the power load data. The SF-Transformer adopts fusion time localization coding, thereby combining global time coding and local position coding, which helps the model to comprehensively obtain time and localization information regarding power load data. Experiments conducted on the dataset show that SF-Transformer has a lower RMSE (root mean square error) and MAE (mean absolute error), compared with those of other power load forecasting models over two-time durations.
| 1 | 田永健, 付涛, 刘玉武, 等.. 基础教育数字化转型的实践探索. 中国电化教育, 2022, (8): 106- 132. |
| 2 | 胡学钢, 刘菲, 卜晨阳.. 教育大数据中认知跟踪模型研究进展. 计算机研究与发展, 2020, 57 (12): 2523- 2546. |
| 3 | 宋苏轩, 杨现民, 宋子强.. 教育信息化2.0背景下新一代高校智慧校园基础平台建设研究. 现代教育技术, 2019, 29 (8): 18- 24. |
| 4 | 崔建伟, 赵哲, 杜小勇.. 支撑机器学习的数据管理技术综述. 软件学报, 2021, 32 (3): 604- 621. |
| 5 | 高劲松, 方晓印, 刘思洋, 等.. 基于关联数据的馆藏文物资源知识关联与智能问答研究. 情报科学, 2021, 39 (5): 12- 20. |
| 6 | 汪诚愚, 何晓丰, 宫学庆, 等.. 面向上下位关系预测的词嵌入投影模型. 计算机学报, 2020, 43 (5): 868- 883. |
| 7 | 陈晓红, 曹廖滢, 陈姣龙, 等.. 我国算力发展的需求、电力能耗及绿色低碳转型对策. 中国科学院院刊, 2024, 39 (3): 528- 539. |
| 8 | 宋杰, 李甜甜, 朱志良, 等.. 云数据管理系统能耗基准测试与分析. 计算机学报, 2013, 36 (7): 1485- 1499. |
| 9 | 陈晓朋, 许可欣, 梁宇栋.. 人工智能促进数据中心绿色节能研究. 信息通信技术与政策, 2024, 50 (2): 33- 39. |
| 10 | PAPPAS S, EKONOMOU L, KARAMPELAS P, et al.. Electricity demand load forecasting of the hellenic power system using an ARMA model. Electric Power Systems Research, 2009, 80 (3): 256- 264. |
| 11 | LEE C M, KO C N.. Short-term load forecasting using lifting scheme and ARIMA models. Expert Systems With Applications, 2011, 38 (5): 5902- 5911. |
| 12 | CHAUHAN M, GUPTA S, SANDHU M.. Short-term electric load forecasting using support vector machines. ECS Transactions, 2022, 107 (1): 9731. |
| 13 | 吴潇雨, 和敬涵, 张沛, 等.. 基于灰色投影改进随机森林算法的电力系统短期负荷预测. 电力系统自动化, 2015, 39 (12): 50- 55. |
| 14 | XIE Z Y, YANG Y, ZHANG Y L, et al.. Correction to: Deep learning on multi-view sequential data: A survey. Artificial Intelligence Review, 2022, 56 (8): 9009. |
| 15 | ELMAN J L.. Finding structure in time. Cognitive Science, 1990, 14 (2): 179- 211. |
| 16 | HOCHREITER S, SCHMIDHUBER J.. Long short-term memory. Neural Computation, 1997, 9 (8): 1735- 1780. |
| 17 | BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate [EB/OL]. (2015-03-22)[2024-06-20]. https://arxiv.org/pdf/1409.0473v5. |
| 18 | 陈卓, 孙龙祥.. 基于深度学习LSTM网络的短期电力负荷预测方法. 电子技术, 2018, 47 (1): 39- 41. |
| 19 | CHO K, VAN MERRIENBOER B, GULCEHRE C. Learning phrase representations using RNN encoder–decoder for statistical machine translation [C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014: 1724-1734. |
| 20 | MOBARAK A, YOUSEF A O, MAJDI O.. Electrical load forecasting using LSTM, GRU, and RNN algorithms. Energies, 2023, 16 (5): 2283. |
| 21 | GONG G J, AN X N, MAHATO K N, et al.. Research on short-term load prediction based on Seq2seq model. Energies, 2019, 12 (16): 3199. |
| 22 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st Conference on Neural Information Processing Systems. 2017: 6000-6010. |
| 23 | SZéKELY J G, RIZZO L M, BAKIROV K N.. Measuring and testing dependence by correlation of distances. The Annals of Statistics, 2007, 35 (6): 2769- 2794. |
| 24 | ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting [C]// Proceedings of the 35th Association for the Advancement of Artificial Intelligence. 2021: 11106-11115. |
| 25 | WU H X, XU J H, WANG J M, et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting [C]// Proceedings of the 34th Advances in Neural Information Processing Systems. 2021: 22419-22430. |
/
| 〈 |
|
〉 |
中国综合性科技类核心期刊(北大核心)