Improved Deep Learning Model for Forecasting Short-Term Load Based on Random Forest Algorithm and Rough Set Theory

doi:10.12096/j.2096-4528.pgt.23013

Abstract

Abstract:

Accurate power load forecasting is conducive to ensuring the safe and economic operation of the power system. Aiming at the problems of low prediction accuracy and long time consuming of the current prediction algorithms, an improved deep learning (DL) short-term load forecasting model based on random forest (RF) algorithm and rough set theory (RST), namely RF-DL-RST, was proposed. Firstly, based on historical data, the model used RF algorithm to extract the key features that affected the load forecasting. Then, the key features and historical load data were trained as the input and output items of deep neural network (DNN), and the prediction results were corrected by RST. After that, the rough set method was used to revise the prediction results. Finally, the simulation was verified by an example. The results show that the prediction accuracy of the model is higher than that of a single DNN model and a model without RST revised.

Key words: power load forecasting, random forest (RF) algorithm, deep learning (DL), rough set theory (RST)

CLC Number:

TK 01

Yu FENG, Youbin SONG, Sheng JIN, Jiahuan FENG, Xuechen SHI, Yongjie YU, Xianchao HUANG. Improved Deep Learning Model for Forecasting Short-Term Load Based on Random Forest Algorithm and Rough Set Theory[J]. Power Generation Technology, 2023, 44(6): 889-895.

Figures/Tables 8

References 26

1	狄曙光，刘峰，孙建宇，等．基于改进ABC和IDPC-MKELM的短期电力负荷预测[J]．智慧电力，2022，50(9)：74-81． doi:10.3969/j.issn.1673-7598.2022.09.012
	DI S G， LIU F， SUN J Y，et al ．Short term power load forecasting based on improved ABC and IDPC-MKELM[J]．Smart Power，2022，50(9)：74-81． doi:10.3969/j.issn.1673-7598.2022.09.012
2	朱文广，李映雪，杨为群，等．基于K-折交叉验证和Stacking融合的短期负荷预测[J]．电力科学与技术学报，2021，36(1)：87-95． doi:10.19781/j.issn.1673-9140.2021.01.010
	ZHU W G， LI Y X， YANG W Q，et al ．Short-term load forecasting based on the K-fold cross-validation and stacking ensemble[J]．Journal of Electric Power Science and Technology，2021，36(1)：87-95． doi:10.19781/j.issn.1673-9140.2021.01.010
3	杨胡萍，余阳，汪超，等．基于VMD-CNN-BIGRU的电力系统短期负荷预测[J]．中国电力，2022，55(10)：71-76．
	YANG H P， YU Y， WANG C，et al ．Short-term load forecasting of power system based on VMD-CNN-BIGRU[J]．Electric Power，2022，55(10)：71-76．
4	赵洋，王瀚墨，康丽，等．基于时间卷积网络的短期电力负荷预测[J]．电工技术学报，2022，37(5)：1242-1251．
	ZHAO Y， WANG H M， KANG L，et al ．Temporal convolution network-based short-term electrical load forecasting[J]．Transactions of China Electrotechnical Society，2022，37(5)：1242-1251．
5	陈皓勇．“双碳”目标下的电能价值分析与市场机制设计[J]．发电技术，2021，42(2)：141-150． doi:10.12096/j.2096-4528.pgt.21008
	CHEN H Y ．Electricity value analysis and market mechanism design under carbon-neutral goal[J]．Power Generation Technology，2021，42(2)：141-150． doi:10.12096/j.2096-4528.pgt.21008
6	付黎苏，王宁，王春虎，等．黑龙江电力现货市场建设建议及结算机制设计[J]．电力自动化设备，2023，43(5)：15-22．
	FU L S， WANG N， WANG C H，et al ．Construction suggestions and settlement mechanism design of Heilongjiang electricity spot market[J]．Electric Power Automation Equipment，2023，43(5)：15-22．
7	李兵抗．电力市场多元主体信用风险测度及防控模型研究[D]．北京：华北电力大学，2022．
	LI B K ．Research on the credit risk measurement and control model of multi power market entities[D]．Beijing：North China Electric Power University，2022．
8	陈伟，赵裕童．基于深度条件概率密度函数的居民电力负荷预测[J]．电网与清洁能源，2022，38(5)：36-41． doi:10.3969/j.issn.1674-3814.2022.05.005
	CHEN W， ZHAO Y T ．Residential power load forecasting based on the depth conditional probability density function[J]．Power System and Clean Energy，2022，38(5)：36-41． doi:10.3969/j.issn.1674-3814.2022.05.005
9	侯慧，王晴，赵波，等．关键信息缺失下基于相空间重构及机器学习的电力负荷预测[J]．电力系统保护与控制，2022，50(4)：75-82．
	HOU H， WANG Q， ZHAO B，et al ．Power load forecasting without key information based on phase space reconstruction and machine learning[J]．Power System Protection and Control，2022，50(4)：75-82．
10	张永伟，潘巧波．基于KPCA-SVM模型的电力负荷最大值短期预测方法[J]．发电技术，2019，40(6)：521-526． doi:10.12096/j.2096-4528.pgt.19010
	ZHANG Y W， PAN Q B ．Short-term prediction method of maximum power load based on KPCA-SVM model[J]．Power Generation Technology，2019，40(6)：521-526． doi:10.12096/j.2096-4528.pgt.19010
11	汤义勤，邹宏亮，蒋旭，等．基于VMD和贝叶斯优化LSTM的母线负荷预测方法[J]．电网与清洁能源，2023，39(2)：46-52． doi:10.3969/j.issn.1674-3814.2023.02.007
	TANG Y Q， ZOU H L， JIANG X， et al ．A bus load forecasting method based on VMD and Bayesian optimization LSTM[J]．Power System and Clean Energy，2023，39(2)：46-52． doi:10.3969/j.issn.1674-3814.2023.02.007
12	王臻，刘东，徐重酉，等．新型电力系统多源异构数据融合技术研究现状及展望[J]．中国电力，2023，56(4)：1-15．
	WANG Z， LIU D， XU C Y，et al ．Status quo and prospect of multi-source heterogeneous data fusion technology for new power system[J]．Electric Power，2023，56(4)：1-15．
13	李焱，贾雅君，李磊，等．基于随机森林算法的短期电力负荷预测[J]．电力系统保护与控制，2020，48(21)：117-124． doi:10.19783/j.cnki.pspc.191594
	LI Y， JIA Y J， LI L，et al ．Short term power load forecasting based on a stochastic forest algorithm[J]．Power System Protection and Control，2020，48(21)：117-124． doi:10.19783/j.cnki.pspc.191594
14	王民量，张伯明，夏清．电力系统短期负荷预测的共轭梯度ANN方法[J]．电力系统自动化，1999，23(1)：34-36． doi:10.3321/j.issn:1000-1026.1999.01.010
	WANG M L， ZHANG B M， XIA Q ．Short term load forecasting using a multilayer neural network with conjugate gradient learning algorithm[J]．Automation of Electric Power Systems，1999，23(1)：34-36． doi:10.3321/j.issn:1000-1026.1999.01.010
15	李程．基于量子神经网络的短期电力负荷预测研究[D]．长沙：湖南大学，2011． doi:10.1109/appeec.2011.5748765
	LI C ．Study on short term load forecasting based on quantum neural network[D]．Changsha： Hunan University，2011． doi:10.1109/appeec.2011.5748765
16	向德军，张维静，冯歆尧，等．考虑特征值细分的广义加性短期负荷预测模型[J]．电力需求侧管理，2023，25(1)：46-51． doi:10.3969/j.issn.1009-1831.2023.01.008
	XIANG D J， ZHANG W J， FENG X Y，et al ．Generalized additive short-term load forecasting model considering eigenvalue subdivision[J]．Power Demand Side Management，2023，25(1)：46-51． doi:10.3969/j.issn.1009-1831.2023.01.008
17	王健，易姝慧，刘俊杰，等．基于随机森林算法和稳态波形的非介入式工业负荷辨识[J]．中国电力，2022，55(2)：82-89．
	WANG J， YI S H， LIU J J，et al ．Non-intrusive industrial load identification based on random forest algorithm and steady-state waveform[J]．Electric Power，2022，55(2)：82-89．
18	董彦军，王晓甜，马红明，等．基于随机森林与长短期记忆网络的电力负荷预测方法[J]．全球能源互联网，2022，5(2)：147-156．
	DONG Y J， WANG X T， MA H M，et al ．Power load forecasting method based on random forest and long short-term memory[J]．Journal of Global Energy Interconnection，2022，5(2)：147-156．
19	颜建建．面向连续型属性的决策树分类算法研究[D]．厦门：厦门大学，2020． doi:10.1109/access.2019.2892083
	YAN J J ．Research on decision tree classification algorithms for continuous attributes[D]．Xiamen：Xiamen University，2020． doi:10.1109/access.2019.2892083
20	李庭洋，栾新，彭正洪．决策树学习算法在交通方式选择模型中的应用[J]．武汉大学学报(工学版)，2013，46(3)：354-358．
	LI T Y， LUAN X， PENG Z H ．Application of traffic mode choice model based on decision tree algorithm[J]．Engineering Journal of Wuhan University，2013，46(3)：354-358．
21	刘勇，兴艳云．基于改进随机森林算法的文本分类研究与应用[J]．计算机系统应用，2019，28(5)：220-225．
	LIU Y， XING Y Y ．Research and application of text classification based on improved random forest algorithm[J]．Computer Systems & Applications，2019，28(5)：220-225．
22	高林，刘英，盛子豪．随机森林算法在交通状态判别中的应用[J]．实验技术与管理，2017，34(4)：43-46．
	GAO L， LIU Y， SHENG Z H ．Application of random forest algorithm to traffic state identification[J]．Experimental Technology and Management，2017，34(4)：43-46．
23	黄弦超，封钰，丁肇豪．多微网多时间尺度交易机制设计和交易策略优化[J]．电力系统自动化，2020，44(24)：77-88． doi:10.7500/AEPS20200601001
	HUANG X C， FENG Y， DING Z H ．Design of multi-time scale trading mechanism and trading strategy optimization for multiple microgrids[J]．Automation of Electric Power Systems，2020，44(24)：77-88． doi:10.7500/AEPS20200601001
24	蒋玮，汤海波，祁晖，等．基于集成深度神经网络的配电网联络关系辨识技术[J]．电力系统自动化，2020，44(1)：101-108． doi:10.7500/AEPS20190411010
	JIANG W， TANG H B， QI H，et al ．Distribution network connectivity recognition based on ensemble deep neural network[J]．Automation of Electric Power Systems，2020，44(1)：101-108． doi:10.7500/AEPS20190411010
25	董骁雄，陈云翔，蔡忠义，等．基于粗糙集理论修正的后续备件指数平滑预测方法[J]．系统工程与电子技术，2018，40(4)：833-838． doi:10.3969/j.issn.1001-506X.2018.04.17
	DONG X X， CHEN Y X， CAI Z Y，et al ．Residual prediction method of subsequent spare parts based on exponential smoothing method and rough set theory[J]．Systems Engineering and Electronics，2018，40(4)：833-838． doi:10.3969/j.issn.1001-506X.2018.04.17
26	王国胤，姚一豫，于洪．粗糙集理论与应用研究综述[J]．计算机学报，2009，32(7)：1229-1246． doi:10.3724/sp.j.1016.2009.01229
	WANG G Y， YAO Y Y， YU H ．A survey on rough set theory and applications[J]．Chinese Journal of Computers，2009，32(7)：1229-1246． doi:10.3724/sp.j.1016.2009.01229

影响因素	特征量	含义
时间因素	月	1—12月
	日	每月的具体日期
	工作日	正常上班，取值1
	节假日	周六日及其他节假日，取值0
	当日小时	00：00—24：00
天气因素	最高温度	当日最高温度，℃
	最低温度	当日最低温度，℃
	平均温度	当日平均温度，℃
	平均相对湿度	当日平均湿度，%
	天气条件	如晴、阴、雨、雪等
	空气质量	空气质量指数
	平均风速	当日平均风速，m/s
	日出时间	具体时刻
	日落时间	具体时刻
政策因素	是否封控	受疫情、天灾影响时取1，反之取0

影响因素	特征量	含义
时间因素	月	1—12月
	日	每月的具体日期
	工作日	正常上班，取值1
	节假日	周六日及其他节假日，取值0
	当日小时	00：00—24：00
天气因素	最高温度	当日最高温度，℃
	最低温度	当日最低温度，℃
	平均温度	当日平均温度，℃
	平均相对湿度	当日平均湿度，%
	天气条件	如晴、阴、雨、雪等
	空气质量	空气质量指数
	平均风速	当日平均风速，m/s
	日出时间	具体时刻
	日落时间	具体时刻
政策因素	是否封控	受疫情、天灾影响时取1，反之取0

模型	DL训练时间/s	MSE/MW²	MAE/%
RF-DL-RST	96.29	680.33	4.01
RF-DL	96.29	974.65	5.77
DL-RST	107.21	865.84	4.73

模型	DL训练时间/s	MSE/MW²	MAE/%
RF-DL-RST	96.29	680.33	4.01
RF-DL	96.29	974.65	5.77
DL-RST	107.21	865.84	4.73

[1]	Xin YUAN, Jun LIU, Heng CHEN, Peiyuan PAN, Gang XU, Xiuyan WANG. Effect of Carbon Capture Technology Application on Peak Shaving Capacity of Coal-Fired Units [J]. Power Generation Technology, 2024, 45(3): 373-381.
[2]	Jiahai YUAN, Yuelin HU, Jian ZHANG. The Carbon Emission Efficiency of China’s Listed Thermal Power Companies: An Improved Three-Stage Slack Based Measure-Data Envelopment Analysis Model [J]. Power Generation Technology, 2024, 45(3): 458-467.
[3]	Mingyi ZHANG, Peng HUANG, Yawu WANG. Research on Output Characteristics of a Circular Dielectric Elastomer Generator [J]. Power Generation Technology, 2024, 45(3): 517-526.
[4]	Jianqiang YE, Dunhu SUN. Research on Power Planning Based on Robust Optimization Under Carbon Trading Condition [J]. Power Generation Technology, 2024, 45(3): 566-574.
[5]	Lu GUO, Yongli LIU, Yuan ZHANG, Qian WU, Yuehui LI, Xiaoyu HOU, Yajing ZHANG. Application of Practical Data Synchronization Technology in Multi Person Cooperation Mechanism of New Distribution System Planning [J]. Power Generation Technology, 2024, 45(2): 363-372.
[6]	Hongjun FU, Shaoxuan ZHU, Buhua WANG, Yan XIE, Haoqing XIONG, Xiaojun TANG, Xiaoyong DU, Chenghao LI, Xiaomeng LI. Risk Prediction Method of Low Frequency Oscillation in Maintenance Power Network Based on Long Short Term Memory Neural Network [J]. Power Generation Technology, 2024, 45(2): 353-362.
[7]	Xiaobiao FU, Jiaqi HOU, Baoju LI, Yakun WEN, Xiaowen LAI, Lei GUO, Zhiwei WANG, Yao WANG, Haifeng ZHANG, Dexin LI. A Two-Modal Weather Classification Method and Its Application in Photovoltaic Power Probability Prediction [J]. Power Generation Technology, 2024, 45(2): 299-311.
[8]	Zheng YANG, Yipeng SUN, Zhiqiang WEN, Liang CHENG, Zhanguo LI. Research on Dry-Wet Conversion Strategy of Supercritical Thermal Power Units Under Deep Peaking Condition [J]. Power Generation Technology, 2024, 45(2): 233-239.
[9]	Zhan LI, Zhenyong YANG, Lei LIU, Zhensan CHEN, Weiming JI, Feng HONG. Analysis of the Influence of Furnace Side Heat Storage Coefficient on Primary Frequency Modulation Capacity Under Deep Modulation Condition of Thermal Power Unit [J]. Power Generation Technology, 2024, 45(2): 226-232.
[10]	Fangfang WANG, Pengwei YANG, Guangjin ZHAO, Qi LI, Xiaona LIU, Shuangchen MA. Development and Challenge of Flexible Operation Technology of Thermal Power Units Under New Power System [J]. Power Generation Technology, 2024, 45(2): 189-198.
[11]	Xiangyu WANG, Wuhui CHEN, Xiaolong GUO, Xiqiang CHANG. Review of Research on the Digitalization of Power Generation System [J]. Power Generation Technology, 2024, 45(1): 120-141.
[12]	Hongbo LIU, Shencheng LIU, Xueyang GAI, Yongfa LIU, Yutong YAN. Overview of Active Distribution Network Planning With High Proportion of New Energy Access [J]. Power Generation Technology, 2024, 45(1): 151-161.
[13]	Yeqing ZHANG, Wenbin CHEN, Lüjun XU, Xingwen JIANG. Multi-Virtual Power Plant-Oriented Dynamic Aggregation Control Strategy Based on Hierarchical Partition and Multi-Layer Complementation [J]. Power Generation Technology, 2024, 45(1): 162-169.
[14]	Minghui KE, Lin LAI. Experimental Research of Electrogasdynamic Power Generation With Exposed Electrode Structure Based on Normal Temperature Air [J]. Power Generation Technology, 2024, 45(1): 180-188.
[15]	Ruowei WANG, Yinxuan LI, Weichun GE, Shitan ZHANG, Chuang LIU, Shuai CHU. Summary of Desert Photovoltaic Power Transmission Technology [J]. Power Generation Technology, 2024, 45(1): 32-41.