Short-Term Load Forecasting Based on TLBGA-GRU Neural Network

doi:10.19678/j.issn.1000-3428.0063153

Abstract

Abstract: Short-term load forecasting plays an important role in the power grid dispatching arrangement and power market transaction.The higher the forecasting accuracy is, the more beneficial it is to improve the utilization rate of power generation equipment and effectiveness of economic dispatching.To fully excavate the connection of time series features in load data and solve the problem of a decrease in the prediction accuracy owing to the random selection of super-parameters in a neural network, this paper proposes a Teaching-Learning-Based Genetic Algorithm(TLBGA), and Gates Recurrent Units(GRU) neural network for short-term load forecasting.First, the gray correlation method is used to analyze the correlation degree of the original data and eliminate the redundant features such that the input and output can maintain a good mapping relationship.A new mutation operator based on teaching and learning optimization is added to the GA algorithm to prevent premature convergence and improve the quality of solution.Then, the improved TLBGA algorithm is used to optimize the GRU neural network model, update its hyperparameters, and enable its performance to reach the best state to improve the accuracy of its load prediction.The proposed method is used to predict the power load dataset of a certain region in Europe and the open load dataset of PJM power market in the United States.The results show that the prediction accuracy of this method can reach 97.1% and 97.2%, respectively.Compared with the BP neural network, Recurrent Neural Network (RNN), and GRU neural network model, the method proposed in this paper has higher prediction accuracy.

Key words: load forecasting, mutation operator, Genetic Algorithm(GA), gated Recurrent Neural Network(RNN), hyperparameter optimization

摘要： 短期负荷预测在电网调度安排和电力市场交易中发挥着重要作用，预测精度高，有利于提高发电设备的利用率和经济调度的有效性。为充分挖掘负荷数据中时序性特征的联系，解决神经网络中由超参数的随机选取导致的预测精度下降问题，提出一种基于教与学的遗传算法（TLBGA）和门控循环单元（GRU）神经网络的短期负荷预测方法。利用灰色关联分析法对原始数据进行相关度分析，剔除冗余特征，使输入与输出保持较好的映射关系，在遗传算法中加入一种基于教与学优化的新型变异算子，用于防止其出现早熟收敛问题，从而提高解的质量。在此基础上，运用改进后的TLBGA算法对GRU神经网络模型进行超参数寻优，更新GRU的模型超参数并使其性能达到最佳状态，以提高负荷预测的精度。对欧洲某地区的电力负荷数据集和美国PJM电力市场公开负荷数据集进行预测，结果表明，该方法的预测精度分别达到了97.1%和97.2%，相比反向传播神经网络、循环神经网络及GRU神经网络模型，具有更高的预测精度。

关键词: 负荷预测, 变异算子, 遗传算法, 门控循环神经网络, 超参数寻优

CLC Number:

TP393

WU Tiezhou, ZOU Zhi, JIANG Ben, ZHANG Xiaoxing. Short-Term Load Forecasting Based on TLBGA-GRU Neural Network[J]. Computer Engineering, 2022, 48(11): 69-76.

吴铁洲, 邹智, 姜奔, 张晓星. 基于TLBGA-GRU神经网络的短期负荷预测[J]. 计算机工程, 2022, 48(11): 69-76.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0063153

http://www.ecice06.com/EN/Y2022/V48/I11/69

Figures/Tables 13

References

[1] 周潮, 邢文洋, 李宇龙.电力系统负荷预测方法综述[J].电源学报, 2012, 10(6):32-39. ZHOU C, XING W Y, LI Y L.Summarization on load forecasting method of electrical power system[J].Journal of Power Supply, 2012, 10(6):32-39.(in Chinese)
[2] 张凌云, 肖惠仁, 吴俊豪, 等.电力系统负荷预测综述[J].电力大数据, 2018, 21(1):52-56. ZHANG L Y, XIAO H R, WU J H, et al.Review of power system load forecasting[J].Power Systems and Big Data, 2018, 21(1):52-56.(in Chinese)
[3] 夏博, 杨超, 李冲.电力系统短期负荷预测方法研究综述[J].电力大数据, 2018, 21(7):22-28. XIA B, YANG C, LI C.Review of the short-term load forecasting methods of electric power system[J].Power Systems and Big Data, 2018, 21(7):22-28.(in Chinese)
[4] HERNANDEZ L, BALADRON C, AGUIAR J M, et al.A survey on electric power demand forecasting:future trends in smart grids, microgrids and smart buildings[J].IEEE Communications Surveys & Tutorials, 2014, 16(3):1460-1495.
[5] QUAN H, SRINIVASAN D, KHOSRAVI A.Short-term load and wind power forecasting using neural network-based prediction intervals[J].IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(2):303-315.
[6] HOSSEN T, PLATHOTTAM S J, ANGAMUTHU R K, et al.Short-term load forecasting using deep neural networks[C]//Proceedings of IEEE NAPSʼ17.Washington D.C., USA:IEEE Press, 2017:1-6.
[7] 魏华栋, 陶媛, 蔡昌春, 等.基于改进长短期记忆神经网络的短期负荷预测[J].电测与仪表, 2020, 57(19):93-98. WEI H D, TAO Y, CAI C C, et al.Short-term load forecasting based on improved long short-term memory neural network[J].Electrical Measurement & Instrumentation, 2020, 57(19):93-98.(in Chinese)
[8] 王增平, 赵兵, 纪维佳, 等.基于GRU-NN模型的短期负荷预测方法[J].电力系统自动化, 2019, 43(5):53-58. WANG Z P, ZHAO B, JI W J, et al.Short-term load forecasting method based on GRU-NN model[J].Automation of Electric Power Systems, 2019, 43(5):53-58.(in Chinese)
[9] 曾囿钧, 肖先勇, 徐方维, 等.基于CNN-BiGRU-NN模型的短期负荷预测方法[J].中国电力, 2021(9):17-23. ZENG Y J, XIAO X Y, XU F W, et al.A short-term load forecasting method based on CNN-BiGRU-NN model[J].Electric Power, 2021(9):17-23.(in Chinese)
[10] NIKBAKHT S, ANITESCU C, RABCZUK T.Optimizing the neural network hyperparameters utilizing genetic algorithm[J].Journal of Zhejiang University-Science A, 2021, 22(6):407-426.
[11] ZHU Y, LI G P, WANG R, et al.Intelligent fault diagnosis of hydraulic piston pump combining improved LeNet-5 and PSO hyperparameter optimization[J].Applied Acoustics, 2021, 183:108336.
[12] HORNG G J, LIN T C, LEE K C, et al.Prediction of prognosis in emergency trauma patients with optimal limit gradient based on grid search optimal parameters[J].Wireless Personal Communications, 2021, 120(2):1741-1751.
[13] TORRES J F, GUTIÉRREZ-AVILÉS D, TRONCOSO A, et al.Random hyper-parameter search-based deep neural network for power consumption forecasting[C]//Proceedings of International Conference on Computational Intelligence.Berlin, Germany:Springer, 2019:1157-1169.
[14] ALGORITHM S.Findings from fermi national accelerator laboratory in the area of algorithms described[J].Journal of Technology & Science, 2018, 45:643-658.
[15] 蒋腾旭, 谢枫.遗传算法中防止早熟收敛的几种措施[J].计算机与现代化, 2006(12):54-56. JIANG T X, XIE F.Several measures to prevent premature convergence of genetic algorithm[J].Computer and Modernization, 2006(12):54-56.(in Chinese)
[16] HASSANAT A, ALKAFAWEEN E, AL-NAWAISEH N A, et al.Enhancing genetic algorithms using multi mutations:experimental results on the travelling salesman problem[J].International Journal of Computer Science and Information Security, 2016, 14(7):1587-1594.
[17] ZHANG X, YUEN S Y.A directional mutation operator for differential evolution algorithms[J].Applied Soft Computing, 2015, 30:529-548.
[18] BEHROOZI F, HOSSEINI S M H, SANA S S.Teaching-learning-based genetic algorithm:an improved solution method for continuous optimization problems[J].International Journal of System Assurance Engineering and Management, 2021, 12(6):1362-1384.
[19] 谢崇波, 李强.基于GA-GRU环境空气污染物预测研究[J].测控技术, 2019, 38(7):97-103. XIE C B, LI Q.Prediction of environmental air pollutants based on GA-GRU[J].Measurement & Control Technology, 2019, 38(7):97-103.(in Chinese)
[20] 赵兵, 王增平, 纪维佳, 等.基于注意力机制的CNN-GRU短期电力负荷预测方法[J].电网技术, 2019, 43(12):4370-4376. ZHAO B, WANG Z P, JI W J, et al.A short-term power load forecasting method based on attention mechanism of CNN-GRU[J].Power System Technology, 2019, 43(12):4370-4376.(in Chinese)
[21] 朱伟, 孙运全, 钱尧, 等.基于CEEMD-GRU模型的短期电力负荷预测方法[J/OL].电测与仪表:1-8[2021-09-09].http://kns.cnki.net/kcms/detail/23.1202.TH.20200727.1613.026.html. ZHU W, SUN Y Q, QIAN Y, et al.Short-term load forecasting method based on complementary ensemble empirical mode decomposition and gated recurrent unit neural network[J/OL].Electrical Measurement and Instrumentation:1-8[2021-09-09].http://kns.cnki.net/kcms/detail/23.1202.TH.20200727.1613.026.html.(in Chinese)
[22] 姚程文, 杨苹, 刘泽健.基于CNN-GRU混合神经网络的负荷预测方法[J].电网技术, 2020, 44(9):3416-3424. YAO C W, YANG P, LIU Z J.Load forecasting method based on CNN-GRU hybrid neural network[J].Power System Technology, 2020, 44(9):3416-3424.(in Chinese)
[23] ZHAO J S, GU Y T, FENG Z G.Optimization of processing parameters of power spinning for bushing based on neural network and genetic algorithms[J].Journal of Beijing Institute of Technology, 2019, 28(3):606-616.
[24] 朱海振, 肖明清, 祁业兴, 等.基于改进GA-PSO的可重构测试资源匹配方法[J].测控技术, 2018, 37(6):24-28. ZHU H Z, XIAO M Q, QI Y X, et al.Reconfigurable test resource matching method based on improved genetic-particle swarm optimization algorithm[J].Measurement & Control Technology, 2018, 37(6):24-28.(in Chinese)
[25] ZHANG J J, SUN G M, SUN Y G, et al.Hyper-parameter optimization by using the genetic algorithm for upper limb activities recognition based on neural networks[J].IEEE Sensors Journal, 2021, 21(2):1877-1884.
[26] TORMOZOV V S, ZOLKIN A L, VASILENKO K A.Optimization of neural network parameters based on a genetic algorithm for prediction of time series[C]//Proceedings of 2020 International Conference on Industrial Engineering and Modern Technologies.Washington D.C., USA:IEEE Press, 2020:1-4.

Please choose a citation manager

Content to export