Load Forecasting of Distribution Network in High Load Density Area by Integrating on Improved BiLSTM and DRL Models
DOI:
https://doi.org/10.52152/4270Keywords:
Distribution network, Load forecasting, High load density area, Bidirectional long short-term memory, Deep reinforcement learningAbstract
The load of power grids in high load density areas fluctuates violently, and traditional prediction models are difficult to capture dynamic changes, resulting in insufficient prediction accuracy and scheduling efficiency. This paper constructs a joint optimization model that integrates the improved bidirectional long short-term memory network (BiLSTM) and deep reinforcement learning (DRL), taking advantage of bidirectional learning and dynamic optimization to improve load forecasting accuracy and dynamic scheduling capabilities. Multi-source heterogeneous load data is integrated through data cleaning and standardization and normalization technology to enhance the consistency of input data. For the BiLSTM model, the optimized network structurethe and attention mechanism is introduced to improve the ability to capture key features of historical loads, and multi-layer perceptrons are combind to enhance nonlinear feature extraction. The dynamic feedback mechanism of DRL is further used to adjust the load scheduling strategy in real-time to achieve collaborative iteration of prediction and optimization. The experimental results show that the improved model has superior performance in short-term to long-term load forecasting, with a mean absolute error (MAE) of 0.05-0.12, a mean square error (MSE) of 0.005-0.025, and a determination coefficient () of 0.97-0.99, which is more accurate than the traditional model. In the 100% high load scenario, the scheduling time is reduced by 6 minutes after joint training, and the energy loss rate is reduced by 1.4%, significantly optimizing the operation efficiency of the power grid. This study provides a high-precision, low-latency solution for the intelligent scheduling of power grids in high-load density areas.
References
H.B. Zhang, Y.K. Hu, Z.R. Li, G.R. Wang. Optimal Configuration of Energy Storage Considering the Risk of Insufficient Flexibility in High Load Density Areas. Power System Technology, 2023, 47(12), 4926-4936. DOI: 10.13335/j.1000-3673.pst.2023.1325
V. Krishnan, B. Bugbee, T. Elgindy, C. Mateo, P. Duenas, et al. Validation of synthetic US electric power distribution system data sets. IEEE Transactions on Smart Grid, 2020, 11(5), 4477-4489. DOI: 10.1109/TSG.2020.2981077
Q.M. Li, X. Zhang, J.B. Guo, X.S. Shan, Z.W. Wang, et al. Integrating reinforcement learning and optimal power dispatch to enhance power grid resilience. IEEE Transactions on Circuits and Systems II: Express Briefs, 2021, 69(3), 1402-1406. DOI: 10.1109/TCSII.2021.3131316
Y. Dong, X. Shan, Y.Q. Yan, X.W. Leng, Y. Wang. Architecture, key technologies and applications of load dispatching in China power grid. Journal of Modern Power Systems and Clean Energy, 2022, 10(2), 316-327. DOI: 10.35833/MPCE.2021.000685
D. Obst, J. De Vilmarest, Y. Goude. Adaptive methods for short-term electricity load forecasting during COVID-19 lockdown in France. IEEE Transactions on Power Systems, 2021, 36(5), 4754-4763. DOI: 10.1109/TPWRS.2021.3067551
X. Dong, S. Deng, D. Wang. A short-term power load forecasting method based on k-means and SVM. Journal of Ambient Intelligence and Humanized Computing, 2022, 13(11), 5253-5267. DOI: 10.1007/s12652-021-03444-x
M.A. Hammad, B. Jereb, B. Rosi, D. Dragan. Methods and models for electric load forecasting: a comprehensive review. Logistics, Supply Chain, Sustainability and Global Challenges, 2020, 11(1), 51-76. DOI: 10.2478/jlst-2020-0004
V. Veeramsetty, K.R. Reddy, M. Santhosh, A. Mohnot, G. Singal. Short-term electric power load forecasting using random forest and gated recurrent unit. Electrical Engineering, 2022, 104(1), 307-329. DOI: 10.1007/s00202-021-01376-5
X.Z. Xu, Z.R. Meng. A hybrid transfer learning model for short-term electric load forecasting. Electrical Engineering, 2020, 102(3), 1371-1381. DOI: 10.1007/s00202-020-00930-x
Y.Y. Wang, J. Chen, X.Q. Chen, X.J. Zeng, Y. Kong, et al. Short-term load forecasting for industrial customers based on TCN-LightGBM. IEEE Transactions on Power Systems, 2020, 36(3), 1984-1997. DOI: 10.1109/TPWRS.2020.3028133
A. Blazquez-Garcia, A. Conde, U. Mori, J.A. Lozano. A review on outlier/anomaly detection in time series data. ACM Computing Surveys, 2021, 54(3), 1-33. DOI: 10.1145/3444690
J.F. Torres, D. Hadjout, A. Sebaa, F. Martínez-Álvarez, A. Troncoso. Deep learning for time series forecasting: a survey. Big Data, 2021, 9(1), 3-21. DOI: 10.1089/big.2020.0159
S.M.J. Jalali, S. Ahmadian, A. Khosravi, M. Shafie-khah, S. Nahavandi. A novel evolutionary-based deep convolutional neural network model for intelligent load forecasting. IEEE Transactions on Industrial Informatics, 2021, 17(12), 8243-8253. DOI: 10.1109/TII.2021.3065718
V. Alvarez, S. Mazuelas, J.A. Lozano. Probabilistic load forecasting based on adaptive online learning. IEEE Transactions on Power Systems, 2021, 36(4), 3668-3680. DOI: 10.1109/TPWRS.2021.3050837
T.F. Wei, T.L. Pan. Short-term power load forecasting based on LSTM neural network optimized by improved PSO. Journal of System Simulation, 2021, 33(8), 1866-1874. DOI: 10.16182/j.issn1004731x.joss.20-0297
N.A. Mohammed, A. Al-Bazi. An adaptive backpropagation algorithm for long-term electricity load forecasting. Neural Computing and Applications, 2022, 34(1), 477-491. DOI: 10.1007/s00521-021-06384-x
P.L. Xie, J.M. Guerrero, S. Tan, N. Bazmohammadi, J.C. Vasquez, et al. Optimization-based power and energy management system in shipboard microgrid: A review. IEEE Systems Journal, 2021, 16(1), 578-590. DOI: 10.1109/JSYST.2020.3047673
Q.B. Ge, C. Guo, H.Y. Jiang, Z.Y. Lu, G.Yao, et al. Industrial power load forecasting method based on reinforcement learning and PSO-LSSVM. IEEE Transactions on Cybernetics, 2020, 52(2), 1112-1124. DOI: 10.1109/TCYB.2020.2983871
T. Van Chien, E. Bjornson, E.G. Larsson. Joint power allocation and load balancing optimization for energy-efficient cell-free massive MIMO networks. IEEE Transactions on Wireless Communications, 2020, 19(10), 6798-6812. DOI: 10.1109/TWC.2020.3006083
K.D. Bodha, V. Mukherjee, V.K. Yadav. A player unknown's battlegrounds ranking based optimization technique for power system optimization problem. Evolving Systems, 2023, 14(2), 295-317. DOI: 10.1007/s12530-022-09458-w
M. Ma, Z. Mao. Deep-convolution-based LSTM network for remaining useful life prediction. IEEE Transactions on Industrial Informatics, 2020, 17(3), 1658-1667. DOI: 10.1109/TII.2020.2991796
E. Patel, D.S. Kushwaha. A hybrid CNN-LSTM model for predicting server load in cloud computing. The Journal of Supercomputing, 2022, 78(8), 1-30. DOI: 10.1007/s11227-021-04234-0
Z. Zheng, L. Tan, N. Zhou, J.W. Han, J. Gao, et al. Power load prediction based on multi-headed attentional convolutional network. Nanjing Xinxi Gongcheng Daxue Xuebao, 2022, 14(5), 535-542. DOI: 10.13878/j.cnki.jnuist.2022.05.004
M. Xia, H.D. Shao, X.D. Ma, C.W. de Silva. A stacked GRU-RNN-based approach for predicting renewable energy and electricity load for smart grid operation. IEEE Transactions on Industrial Informatics, 2021, 17(10), 7050-7059. DOI: 10.1109/TII.2021.3056867
T.Z. Liu, S.S. Liu, S.J. Wang, Y.J. Ma. Short‐term photovoltaic power prediction based on MDCM‐GA‐LSTM model. The Journal of Engineering, 2022, 2022(10), 994-1005. DOI: 10.1049/tje2.12186
R. Huang, L.L. Zhu, F. Gao, H.H. Wang, Y.L. Yang, et al. Short-term power load forecasting method based on variational modal decomposition for convolutional long-short-term memory network. Modern Electric Power, 2024, 41(1), 97-105. DOI: 10.19725/j.cnki.1007-2322.2022.0210
Y.K. Liu, D.X. Zhang, H.B. Gooi. Optimization strategy based on deep reinforcement learning for home energy management. CSEE Journal of Power and Energy Systems, 2020, 6(3), 572-582. DOI: 10.17775/CSEEJPES.2019.02890
Z.M. Yan, Y. Xu. Real-time optimal power flow: A lagrangian based deep reinforcement learning approach. IEEE Transactions on Power Systems, 2020, 35(4), 3270-3273. DOI: 10.1109/TPWRS.2020.2987292
Z.M. Yan, Y. Xu. A multi-agent deep reinforcement learning method for cooperative load frequency control of a multi-area power system. IEEE Transactions on Power Systems, 2020, 35(6), 4599-4608. DOI: 10.1109/TPWRS.2020.2999890
B. Wang, Y. Li, W.Y. Ming, et al. Deep reinforcement learning method for demand response management of interruptible load. IEEE Transactions on Smart Grid, 2020, 11(4), 3146-3155. DOI: 10.1109/tsg.2020.2967430
Y. Zhang, X.N. Wang, J.H. Wang, Y.C. Zhang. Deep reinforcement learning based volt-var optimization in smart distribution systems. IEEE Transactions on Smart Grid, 2020, 12(1), 361-371. DOI: 10.48550/arXiv.2003.03681
J.D. Wang, J.Y. Yu, X.Y. Kong. Medium-and Long-term Load Forecasting Model Based on Double Decomposition and BiLSTM. Power System Technology, 2024, 48(8), 3418-3426. DOI: 10.13335/j.1000-3673.pst.2024.0137
M.J. Chen, F.H. Qiu, X.Z. Xiong, Z.W. Chang, Y. Wei, et al. BILSTM-SimAM: An improved algorithm for short-term electric load forecasting based on multi-feature. Mathematical Biosciences and Engineering: MBE, 2024, 21(2), 2323-2343. DOI: 10.3934/mbe.2024102
F. Li, C.J. Sun, W. Han, T.Y. Yan, G. Li, et al. Medium‐term load forecasting of power system based on BiLSTM and parallel feature extraction network. IET Generation, Transmission & Distribution, 2024, 18(1), 190-201. DOI: 10.1049/gtd2.13083
P.P. Liu, Y.F. Zhang, F.X. Bao, X.X. Yao, C.M. Zhang. Multi-type data fusion framework based on deep reinforcement learning for algorithmic trading. Applied Intelligence, 2023, 53(2), 1683-1706. DOI: 10.1007/s10489-022-03321-w
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Yuanfang Zeng, Yongyuan Wang, Mingke Li, Junshu Su, Min Zhang (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
