Optimization of Spatial Equilibrium Evaluation of Water Resources for BIGRU/BILSTM Using a New Group Intelligence Algorithm
-
摘要: 为科学评价云南省2006-2022年及2025年水资源空间均衡状态，建立基于社交网络搜索（SNS）算法、登山队优化（MTBO）算法优化双向门控循环单元（BIGRU）、双向长短时记忆（BILSTM）网络的水资源空间均衡评价模型。首先，从水资源支撑、水资源压力、水资源调控力3个方面遴选15个指标构建水资源空间均衡评价指标体系和等级标准，采用线性内插和随机选取的方法生成样本构建BIGRU、BILSTM适应度函数；其次，简要介绍SNS、MTBO算法原理，利用SNS、MTBO优化BiGRU、BiLSTM隐含层神经元数、学习率（超参数）构建SNS-BIGRU、MTBO-BIGRU、SNS-BILSTM、MTBO-BILSTM模型，通过不同样本大小和连续10次运行的方法验证SNS-BIGRU等4种模型的稳健性；最后利用SNS-BIGRU、MTBO-BIGRU、SNS-BILSTM、MTBO-BILSTM模型对云南省2006-2022年及2025年水资源空间均衡进行评价，并与SNS-支持向量机（SVM）、MTBO-SVM和模糊综合评价法的评价结果作对比。结果表明：(1)所建立的SNS-BIGRU等4种模型具有较好的识别精度和稳健性能；SNS、MTBO能有效优化BIGRU、BILSTM超参数，提升BIGRU、BILSTM预测性能。(2)SNS-BIGRU等4种模型对云南省2006-2011年水资源空间均衡评价为“不均衡”，2012-2013年评价为“较不均衡”，2014-2018年评价为“临界均衡”，2019-2022年评价为“较均衡”，2025年基本可达到“均衡”水平；4种模型评价结果与SNS-SVM、MTBO-SVM、模糊综合评价法有3年存在1个等级的差异。本文构建及提出的模型方法可为水资源空间均衡评价提供参考与借鉴。Abstract: This paper evaluates the spatial equilibrium status of water resources in Yunnan Province from 2006 to 2022 and 2025 scientifically, and proposes a water resource spatial equilibrium evaluation model based on social network search（SNS） algorithm, mountaineering team optimization（MTBO） algorithm, bi-directional gated loop unit（BIGRU） optimization, and bi-directional long short-term memory（BILSTM） network optimization. First, 15 indicators are selected from three aspects of water resources support, water resources pressure and water resources regulation to build the evaluation index system and grade standard of water resources spatial balance, and the samples are generated by linear interpolation and random selection methods to build BiGRU and BiLSTM fitness function. Secondly, the principles of SNS and MTBO algorithms are briefly introduced. SNS-BIGRU, MTBO-BIGRU, SNS-BILSTM, and MTBO-BILSTM models are constructed by using SNS and MTBO to optimize the number of neurons in the hidden layer of BiGRU and BilSTM and the learning rate（hyperparameter）. The robustness of four models, including SNS-BIGRU, MTBO-BIGRU, SNS-BILSTM, and MTBO-BILSTM, is verified through different sample sizes and 10 consecutive runs. Finally, SNS-BIGRU, MTBO-BIGRU, SNS-BILSTM, and MTBO-BILSTM models are used to evaluate the spatial balance of water resources in Yunnan Province from 2006 to 2022 and 2025, and the evaluation results are compared with those of SNS-Support Vector Machine（SVM）, MTBO-SVM, and fuzzy comprehensive evaluation methods. The results show that:（1）the models such as SNS-BIGRU have good recognition accuracy and robustness. SNS and MTBO can effectively optimize the hyper-parameter of BIGRU and BILSTM, and improve the prediction performance of BIGRU and BiLSTM.（2） SNS-BIGRU and other four models evaluate the spatial balance of water resources in Yunnan Province from 2006 to 2011 as “unbalanced”, from 2012 to 2013 as “relatively unbalanced”, from 2014 to 2018 as “critical equilibrium”, from 2019 to 2022 as “relatively balanced”, and by 2025, it can basically reach the level of “balanced”. There is a 3-year difference in the evaluation results of the four models compared to SNS-SVM, MTBO-SVM, and fuzzy comprehensive evaluation methods. The model method constructed and proposed in this paper serve as a reference for the spatial balance evaluation of water resources.
-
-
[1] 王泽斌,陶佳辉,尹鑫,等.江苏省水资源空间均衡评价[J].中国农村水利水电,2022(11):37-43. WANG Z B,TAO J H,YIN X, et al. Water resources spatial equilibrium evaluation in jiangsu province[J].China Rural Water and Hydropower, 2022(11):37-43.
[2] 杨亚锋,巩书鑫,王红瑞,等.水资源空间均衡评估模型构建及应用[J].水科学进展,2021,32(1):33-44. YANG Y F, GONG S X, WANG H R, et al. New model for water resources spatial equilibrium evaluation and its application[J]. Advances in Water Science, 2021,32(1):33-44.
[3] 金菊良,徐新光,周戎星,等.基于联系数和耦合协调度的水资源空间均衡评价方法[J].水资源保护,2021,37(1):1-6. JIN J L, XU X G, ZHOU R X, et al. Water resources spatial balance evaluation method based on connection number and coupling coordination degree[J]. Water Resources Protection,2021,37(1):1-6.
[4] 黄锋华,黄本胜,邱静.基于均衡系数的广东省水资源空间均衡研究[J].中山大学学报(自然科学版),2021,60(5):86-93. HUANG F H, HUANG B H,QIU J. The spatial equilibrium of water resources of guangdong based on equilibrium coefficient[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2021,60(5):86-93.
[5] 金菊良,徐新光,崔毅,等.基于联系数和洛伦兹曲线的水资源空间均衡评价方法[J].水科学进展,2021,32(3):387-395. JIN J L, XU X G, CUI Y, et al. Water resources spatial equilibrium evaluation method based on connection number and lorenz curve[J].Advances in Water Science, 2021,32(3):387-395.
[6] 金菊良,苏维,周戎星,等.基于基尼系数和联系数的区域水资源空间均衡评价模型[J].人民黄河,2021,43(9):73-78. JIN J L, SU W, ZHOU R X, et al. Evaluation model of regional water resources spatial equilibrium based on gini coefficient and connection number[J].Yellow River,2021,43(9):73-78.
[7] 吴成国,王晓宇,金菊良,等.基于有序联系度熵的水资源空间均衡综合评价方法[J].水利学报,2022,53(11):1 304-1 316. WU C G,WANG X Y,JIN J L,et al.Ordered correlation degree entropy based approach for comprehensive evaluation analysis of water resource spatial equilibrium system[J]. Journal of Hydraulic Engineering,2022,53(11):1 304-1 316.
[8] 许建伟,崔东文.若干新型智能算法优化极限学习机在区域人水和谐度评价中的应用[J].三峡大学学报(自然科学版),2023,45(2):7-16. XU J W, CUI D W. Application of several newintelligent algorithm optimization extreme learning machines in regional human water harmony evaluation[J]. Journal of Three Gorges University(Natural Science Edition), 2023,45(2):7-16.
[9] TALATAHARI S, BAYZIDI H, SARAEE M. Social network search for global optimization[J]. IEEE Access, 2021,9:92 815-92 863.
[10] FARIDMEHR I, NEHDI M L, DAVOUDKHANI I F, et al. Mountaineering team-based optimization:a novel human-based metaheuristic algorithm[J]. Mathematics, 2023,11(5):1 273.
[11] 余本功,许庆堂,张培行.基于MAC-LSTM的问题分类研究[J].计算机应用研究,2020,37(1):40-43. YU B G, XU Q T, ZHANG P X. Research on problem classification based on MAC-LSTM[J] Computer Application Research, 2020,37(1):40-43.
[12] 胡顺强,崔东文.基于海洋捕食者算法优化的长短期记忆神经网络径流预测[J].中国农村水利水电,2021(2):78-82+90. HU S Q, CUI D W. Long-term and short-term memory neural network runoff prediction based on optimization of marine predators algorithm[J].China Rural Water and Hydropower, 2021(2):78-82+90.
[13] 李校林,吴腾.基于PF-LSTM网络的高效网络流量预测方法[J].计算机应用研究,2019,36(12):3 833-3 836. LI X L, WU T. Efficient network traffic prediction method based on PF-LSTM network[J]. Computer Application Research, 2019,36(12):3 833-3 836.
[14] 史建楠,邹俊忠,张见,等.基于DMD-LSTM模型的股票价格时间序列预测研究[J].计算机应用研究,2020,37(3):662-666. SHI J N, ZOU J Z, ZHANG J, et al. Research on stock price time series prediction based on DMD-LSTM model[J]. Computer Application Research, 2020,37(3):662-666.
[15] 宋刚,张云峰,包芳勋,等.基于粒子群优化LSTM的股票预测模型.[J].北京航空航天大学学报,2019,45(12):2 533-2 542. SONG G, ZHANG Y F, BAO F X, et al. Stock forecasting model based on particle swarm optimization LSTM[J] Journal of Beijing University of Aeronautics and Astronautics, 2019,45(12):2 533-2 542.
[16] 胡顺强,崔东文.基于EMD-LSTM-ANFIS模型的年径流预测研究[J].人民珠江,2021,42(3):46-52. HU S Q, CUI D W. Research on annual runoff prediction based on EMD-LSTM-ANFIS model[J]. People′s the Pearl River, 2021,42(3):46-52.
[17] 金子皓,向玲,李林春,等.基于完备集合经验模态分解的SEBiGRU超短期风速预测[J].电力科学与工程,2023,39(1):9-16. JIN Z H, XIANG L, LI L C,et al. SE-BiGRU ultra-short-term wind speed prediction based on CEEMDAN[J]. Electric Power Science and Engineering, 2023,39(1):9-16.
[18] 徐冬梅,夏王萍,王文川.基于黏菌算法优化VMD-CNN-GRU模型的年径流预测[J].南水北调与水利科技(中英文),2022,20(3):429-439. XU D M, XIA W P, WANG W C. Annual runoff prediction based on VMD-CNN-GRU model optimized by slime mold algorithm[J].South to North Water Diversion and Water Conservancy Technology(Chinese and English), 2022,20(3):429-439.
[19] 黄永涛,刘晓青,季威,等.HCM-PSO-GRU组合预测模型在大坝变形预测中的应用[J].水电能源科学,2021,39(12):120-123+61. HUANG Y T, LIU X Q, JI W, et al. Application of the HCM-PSOGRU combined prediction model in dam deformation prediction[J].Journal of Hydroelectric Energy Science, 2021,39(12):120-123+61.
[20] 孟安波,陈顺,王陈恩,等.基于混沌CSO优化时序注意力GRU模型的超短期风电功率预测[J].电网技术,2021,45(12):4 692-4 700. MENG A B, CHEN S, WANG C E, et al. Ultra-short-term wind power prediction based on chaotic CSO optimized temporal attention GRU model[J].Power System Technology, 2021,45(12):4 692-4 700.
[21] 刘英,裴莉莉,郝雪丽.基于WOA-BiLSTM模型的空气质量指数预测[J].计算机系统应用,2022,31(10):389-396. LIU Y, PEI L L, HAO X L. Prediction of air quality index based on WOA-BiLSTM model[J]. Computer System Application, 2022,31(10):389-396.
[22] 李正,陈堂贤,张赟宁,等.基于ISSA-BiLSTM的多端柔性直流输电线路保护方案[J/OL].电测与仪表:1-9[2023-01-22].http://kns. cnki. net/kcms/detail/23.1202. TH. 20221103.1247.014.html LI Z, CHEN T X, ZHANG Y N, et al. Protection scheme for multi terminal flexible DC transmission lines based on ISSA-BiLSTM[J/OL]. Electrical Measurement and Instrumentation:1-9[2023-01-22] http://kns. cnki. net/kcms/detail/23.1202. TH. 20221103.1247.014.html. [23] 朱正林,张冕.基于AO优化VMD-CE-BiGRU的光伏发电功率预测[J].国外电子测量技术,2022,41(10):56-61. ZHU Z L, ZHANG M. Photovoltaic power generation prediction based on AO optimized VMD-CE-BiGRU[J]. Foreign Electronic Measurement Technology, 2022,41(10):56-61.
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
下载:
