Page 12 - 《中国电力》2026年第5期

2026 年 第 59 卷

WANG Huiqiang, CHEN Chuhao, LV Hongwu, et al. Multivariate as a precise method for reducing machine learning based feature sets
time series classification model based on bidirectional sparse to their minimum informative size[J]. Scientific Reports, 2023, 13:
transformer[J]. Journal of Chinese Computer Systems, 2024, 45(3): 5470.
555–561. [28] 徐宇颂, 邹山花, 卢先领. 基于特征选择和组合模型的短期电力负
[18] LLORENTE O, PORTELA J. A transformer approach for electricity 荷预测 [J]. 中国电力, 2022, 55(7): 121–127.
price forecasting[J/OL]. 2024: arXiv: 2403.16108[2025-03-30]. XU Yusong, ZOU Shanhua, LU Xianling. Short-term load
https://arxiv.org/abs/2403.16108. forecasting based on feature selection and combination model[J].
[19] 王艳阳, 李建朝, 刘景青, 等. 电碳耦合机制下多元主体综合成本分 Electric Power, 2022, 55(7): 121–127.
析 [J]. 中国电力, 2025, 58(6): 180–189. [29] 徐先峰, 赵依, 刘状壮, 等. 用于短期电力负荷预测的日负荷特性分
WANG Yanyang, LI Jianzhao, LIU Jingqing, et al. Comprehensive 类及特征集重构策略 [J]. 电网技术, 2022, 46(4): 1548–1556.
cost analysis of multiple entities under the coupling mechanism of XU Xianfeng, ZHAO Yi, LIU Zhuangzhuang, et al. Daily load
electricity and carbon[J]. Electric Power, 2025, 58(6): 180–189. characteristic classification and feature set reconstruction strategy for
[20] 李祥光, 谭青博, 李帆琪, 等. 电碳耦合对煤电机组现货市场结算电 short-term power load forecasting[J]. Power System Technology,
价影响分析模型 [J]. 中国电力, 2024, 57(5): 113–125. 2022, 46(4): 1548–1556.
LI Xiangguang, TAN Qingbo, LI Fanqi, et al. Analysis model to [30] NIE Y Q, NGUYEN N H, SINTHONG P, et al. A time series is
study the influence of electrocarbon coupling on settlement price of worth 64 words: long-term forecasting with transformers[J/OL].
coal power units in spot market[J]. Electric Power, 2024, 57(5): 2022: arXiv: 2211.14730[2025-03-30]. https://arxiv.org/abs/2211.
113–125. 14730.
[21] 刘超. 基于供需平衡的电力市场电价预测与调控研究 [J]. 中国集 [31] KAZEMI S M, GOEL R, EGHBALI S, et al. Time2Vec: learning a
体经济, 2024(22): 41–44. vector representation of time[J/OL]. 2019: arXiv: 1907.05321[2025-
LIU Chao. Research on electricity price prediction and regulation in 03-30]. https://arxiv.org/abs/1907.05321.
the power market based on supply and demand balance[J]. China [32] 杨楠, 毕贵红, 李玉洪, 等. 基于 Time2Vec-BiGRU-SA 深度学习模
Collective Economy, 2024(22): 41–44. 型的碳价格预测 [J]. 电力科学与工程, 2025, 41(9): 1–12.
[22] 王蕾, 李斌, 吴飞, 等. 基于改进极限学习机的电力市场实时电价预 YANG Nan, BI Guihong, LI Yuhong, et al. Carbon price prediction
测方法 [J]. 电子设计工程, 2024, 32(20): 21–25, 30. based on Time2Vec-BiGRU-SA deep learning model[J]. Electric
WANG Lei, LI Bin, WU Fei, et al. Real time electricity price Power Science and Engineering, 2025, 41(9): 1–12.
prediction method in the electricity market based on improved [33] 李滨, 黄佳, 吴茵, 等. 基于分形特性修正气象相似日的节假日短期
extreme learning machine[J]. Electronic Design Engineering, 2024, 负荷预测方法 [J]. 电网技术, 2017, 41(6): 1949–1955.
32(20): 21–25, 30. LI Bin, HUANG Jia, WU Yin, et al. Holiday short-term load
[23] MOON H, CHUNG S, SUH J, et al. Analysis of power system forecasting based on fractal characteristic modified meteorological
flexibility considering power system ramp rate[J]. Journal of similar day[J]. Power System Technology, 2017, 41(6): 1949–1955.
Electrical Engineering & Technology, 2024, 19(2): 867–876.
作者简介：

[24] YAO X T, FU X L, ZONG C F. Short-term load forecasting method
陈梓宏（1993），男，工程师，
based on feature preference strategy and LightGBM-XGboost[J].
从事电力市场、电力经济研究，E-mail：
IEEE Access, 2022, 10: 75257–75268.
chenzihong@geg.com.cn；
[25] XU C, CHEN S L, KONG X J, et al. Robust feature selection by
黄宁馨（1997），女，硕士研究
removing noise entropy within mutual information for limited-sample
生，从事电力经济、电力供需研究，
industrial data[J]. IEEE Transactions on Industrial Informatics, 2025,
E-mail：huangningxin@geg.com.cn；
21(5): 3913–3923.
陈硕楠（1999），男，通信作
[26] UNIEJEWSKI B, NOWOTARSKI J, WERON R. Automated
者，硕士研究生，从事人工智能、机器学习算法应用研
variable selection and shrinkage for day-ahead electricity price
究，E-mail：1025877071@qq.com。
forecasting[J]. Energies, 2016, 9(8): 621.
[27] LÖTSCH J, ULTSCH A. Recursive computed ABC (cABC) analysis （责任编辑 赵简）
8