Accurate prediction of daily inflow runoff is crucial for optimizing reservoir operation. To enhance the precision of daily inflow runoff forecasting, a prediction model integrating Wavelet Packet Transform (WPT), Dung Beetle Optimizer (DBO),Giant Trevally Optimizer (GTO), and Mud Ring Algorithm (MRA) optimized Randomized Extreme Learning Machine (RELM) is proposed and applied to forecasting daily inflow runoff in the Three Gorges Reservoir. Initially, WPT is utilized to decompose the daily runoff time series into a periodic term component and a fluctuation term component. Subsequently, by employing DBO, GTO, and MRA to optimize the input layer weights and hidden layer bias of RELM, the WPT-DBO-RELM, WPT-GTO-RELM, and WPT-MRA-RELM models are established. These models are then employed to predict and reconstruct the periodic and fluctuation components of daily inflow runoff. Comparative models such as WPT-DBO-ELM, WPT-GTO-ELM, and WPT-MRA-ELM based on Extreme Learning Machine (ELM), as well as WPT-DBO-BP, WPT-GTO-BP, and WPT-MRA-BP based on BP neural network, along with unoptimized WPT-RELM, WPT-ELM, and WPT-BP models and undecomposed DBO-RELM, GTO-RELM, and MRA-RELM models are utilized for analysis. Results indicate that: 1) The mean absolute percentage error (MAPE) of WPT-DBO-RELM, WPT-GTO-RELM, and WPT-MRA-RELM models for predicting the daily inflow in Three Gorges Reservoir is 0.512%, 0.519%, and 0.762% respectively, with Mean Absolute Error (MAE) of 54.05 m3/s, 55.97 m3/s, and 86.76 m3/s, Root-Mean-Square Error (RMSE) of 84.99 m3/s, 84.81 m3/s, and 128.18 m3/s, a determination coefficient ≥0.999 4, Theil Inequality Coefficient ≤0.005 17, showing superior prediction accuracy and generalization ability when compared to the other 12 models. 2) DBO, GTO, and MRA effectively optimize the parameters of RELM networks and enhance prediction performance. 3) Incorporating a regularization term in RELM prevents overfitting, boosts model generalization ability, and outperforms ELM and BP networks. 4) The proposed models exhibit high prediction accuracy, low computational complexity, proving to be efficient for estimating daily inflow runoff time series.
Key words
daily runoff forecast /
regularized extreme learning machine /
Dung Beetle Optimizer /
Giant Trevally Optimizer /
Mud Ring Algorithm /
wavelet packet transform /
Three Gorges Reservoir
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] 段 勇, 任 磊. 基于BP神经网络的黄河中游日径流预测研究[J]. 人民黄河, 2020, 42(增刊2): 5-8. (DUAN Yong, REN Lei. Study on Daily Runoff Prediction of the Middle Yellow River Based on BP Neural Network[J]. Yellow River, 2020, 42(Supp.2): 5-8.(in Chinese))
[2] 胡庆芳, 曹士圯, 杨辉斌, 等. 汉江流域安康站日径流预测的LSTM模型初步研究[J]. 地理科学进展, 2020, 39(4): 636-642. (HU Qing-fang, CAO Shi-yi, YANG Hui-bin, et al. Daily Runoff Predication Using LSTM at the Ankang Station, Hanjing River[J]. Progress in Geography, 2020, 39(4): 636-642.(in Chinese))
[3] 郑 勇,马炳焱,成静清,等.基于多种学习方案LSTM的信江流域径流预测[J].水力发电,2022,48(7):22-27.(ZHENG Yong, MA Bing-yan, CHENG Jing-qing, et al. Runoff Prediction of Xinjiang River Basin Based on Multiple Learning Schemes LSTM[J]. Water Power, 2022, 48(7): 22-27.(in Chinese))
[4] 孙望良, 周建中, 彭利鸿, 等. DFA＿VMD＿LSTM组合日径流预测模型研究[J]. 水电能源科学, 2021, 39(3): 12-15. (SUN Wang-liang, ZHOU Jian-zhong, PENG Li-hong, et al. Study on DFA＿VMD＿LSTM Hybrid Daily Runoff Forecasting Model[J]. Water Resources and Power, 2021, 39(3): 12-15.(in Chinese))
[5] 马乐宽, 邱 瑀, 赵 越, 等. 基于改进的神经网络与支持向量机的小流域日径流量预测研究[J]. 水资源与水工程学报, 2016, 27(5): 23-27. (MA Le-kuan, QIU Yu, ZHAO Yue, et al. Prediction of Daily Runoff in a Small Watershed Based on Improved Neural Network and Support Vector Machine(SVM)[J]. Journal of Water Resources and Water Engineering, 2016, 27(5): 23-27.(in Chinese))
[6] 黄景光,吴 巍,程璐瑶,等.基于小波支持向量机特征分类的日径流组合预测:以宜昌三峡水库为例[J].中国农村水利水电,2018(6):33-39.(HUANG Jing-guang,WU Wei,CHENG Lu-yao,et al. Daily Runoff Combination Prediction Based on Wavelet Support Vector Machine Feature Classification:Taking the Three Gorges Reservoir in Yichang as an Example[J]. China Rural Water and Hydropower,2018(6):33-39.(in Chinese))
[7] 黄巧玲, 粟晓玲, 杨家田. 基于小波分解的日径流支持向量机回归预测模型[J]. 西北农林科技大学学报(自然科学版), 2016, 44(4): 211-217. (HUANG Qiao-ling, SU Xiao-ling, YANG Jia-tian. Wavelet Based Support Vector Machine Regression Model for Daily Runoff Prediction[J]. Journal of Northwest A & F University (Natural Science Edition), 2016, 44(4): 211-217.(in Chinese))
[8] 任化准,陈 琼,何有良,等.WPSO-SVR耦合日径流预测模型研究及应用[J].人民长江,2017,48(10):40-43.(REN Hua-zhun, CHEN Qiong, HE You-liang, et al. Research on Wavelet-PSO-support Vector Regression Coupled Daily Runoff Prediction Model and Application[J]. Yangtze River, 2017, 48(10): 40-43.(in Chinese))
[9] 钱立鹏, 刘长征, 陈翠忠, 等. 一种基于深度信念网络的径流量预测方法[J]. 石河子大学学报(自然科学版), 2021, 39(2): 259-264. (QIAN Li-peng, LIU Chang-zheng, CHEN Cui-zhong, et al. A Method of the Runoff Prediction Based on Deep Belief Network[J]. Journal of Shihezi University (Natural Science), 2021, 39(2): 259-264.(in Chinese))
[10]李新华, 崔东文. 基于小波包分解的EHO-ELM与EHO-DELM日径流多步预报模型研究[J/OL]. 中国农村水利水电, 2022: 1-12. (2022-05-12). https://kns.cnki.net/kcms/detail/42.1419.TV.20220512.0856.002.html. (LI Xin-hua, CUI Dong-wen. Research on Multi-step Forecast Models of EHO-ELM and EHO-DELM Daily Runoff Based on Wavelet Packet Decomposition[J/OL]. China Rural Water and Hydropower, 2022: 1-12. (2022-05-12). https://kns.cnki.net/kcms/detail/42.1419.TV.20220512.0856.002.html.(in Chinese))
[11]郭博臻,白一鸣,赵永生.基于PSO-RELM的绞吸挖泥船产量预测及其可视化辅助决策[J].水运工程,2021(9):147-151,193.(GUO Bo-zhen,BAI Yi-ming,ZHAO Yong-sheng.Production Prediction and Visual Decision Support of Cutter Suction Dredger Based on PSO-RELM[J]. Port & Waterway Engineering, 2021(9): 147-151, 193.(in Chinese))
[12]张 壮, 曹玲玲, 林文辉, 等. 基于IPSO-RELM转炉冶炼终点锰含量预测模型[J]. 工程科学学报, 2019, 41(8): 1052-1060. (ZHANG Zhuang, CAO Ling-ling, LIN Wen-hui, et al. Improved Prediction Model for BOF End-point Manganese Content Based on IPSO-RELM Method[J]. Chinese Journal of Engineering, 2019, 41(8): 1052-1060.(in Chinese))
[13]王振东, 刘尧迪, 杨书新, 等. 基于天牛群优化与改进正则化极限学习机的网络入侵检测[J]. 自动化学报, 2022, 48(12): 3024-3041. (WANG Zhen-dong, LIU Yao-di, YANG Shu-xin, et al. Network Intrusion Detection Based BSO and Improved RELM[J]. Acta Automatica Sinica, 2022, 48(12): 3024-3041.(in Chinese))
[14]金秀章, 刘 岳, 赵文杰, 等. 基于mRMR和MA-RELM的火电厂出口SO2质量浓度预测[J]. 动力工程学报, 2022, 42(7): 664-670, 676. (JIN Xiu-zhang, LIU Yue, ZHAO Wen-jie,et al. Prediction of SO2 Mass Concentration at Outlet of the Thermal Power Plant Based on MRMR and MA-RELM[J]. Journal of Chinese Society of Power Engineering, 2022, 42(7): 664-670, 676.(in Chinese))
[15]王应武,白栩嘉,崔东文.基于WPT-ISO-RELM模型的月径流时间序列预测研究[J].水力发电,2024,50(3):12-18,38. (WANG Ying-wu, BAI Xu-jia, CUI Dong-wen. Research on Monthly Runoff Time Series Prediction Based on WPT-ISO-RELM Model[J].Hydroelectric Power, 2024,50 (03): 12-18,38.(in Chinese))
[16]高雪梅,崔东文.WPT-FLA-RELM模型的马鹿塘水电站入库日径流多步预测[J].云南水力发电,2023,39(11):56-62. (GAO Xue-mei, CUI Dong-Wen Multi Step Prediction of Daily Inflow of Malutang Hydropower Station Using WPT-FLA-RELM Model[J].Yunnan Hydroelectric Power, 2023,39 (11):56-62.(in Chinese))
[17]张 祎, 刘 杨, 张释今. 三峡水库近20年水面蒸发量分布特征及趋势分析[J]. 水文, 2018, 38(3): 90-96. (ZHANG Yi, LIU Yang, ZHANG Shi-jin. Distribution and Trend Analysis of Surface Evaporation in Three Gorges Reservoir in Recent 20 Years[J]. Journal of China Hydrology, 2018, 38(3): 90-96.(in Chinese))
[18]李新华, 崔东文. 基于WPD-TSO-ELM模型的月径流时间序列预测[J]. 水力发电, 2022, 48(9): 9-15, 44. (LI Xin-hua, CUI Dong-wen. Forecast of Monthly Runoff Time Series Based on WPD-TSO-ELM Model[J]. Water Power, 2022, 48(9): 9-15, 44.(in Chinese))
[19]李新华, 崔东文. 基于WPD-RSA-ELM模型的水文时间序列多步预测[J]. 水利水电技术(中英文), 2022, 53(11): 69-77. (LI Xin-hua, CUI Dong-wen. Multi-step Prediction of Hydrological Time Series Based on WPD-RSA-ELM Model[J]. Water Resources and Hydropower Engineering, 2022, 53(11): 69-77.(in Chinese))
[20]XUE J, SHEN B. Dung Beetle Optimizer: a New Meta-heuristic Algorithm for Global Optimization[J]. The Journal of Supercomputing, 2023, 79(7): 7305-7336.
[21]SADEEQ H T, ABDULAZEEZ A M. Giant Trevally Optimizer (GTO): a Novel Metaheuristic Algorithm for Global Optimization and Challenging Engineering Problems[J]. IEEE Access, 2022, 10: 121615-121640.
[22]DESUKY A S, CIFCI M A, KAUSAR S, et al. Mud Ring Algorithm: a New Meta-heuristic Optimization Algorithm for Solving Mathematical and Engineering Challenges[J]. IEEE Access, 2022, 10: 50448-50466.
[23]许建伟, 崔东文. 战争策略算法与变色龙算法优化极限学习机的输沙量时间序列预测[J]. 水力发电, 2022, 48(11): 36-42. (XU Jian-wei, CUI Dong-wen. Time Series Prediction of Sediment Discharge by Optimizing Extreme Learning Machine with War Strategy and Chameleon Swarm Algorithm[J]. Water Power, 2022, 48(11): 36-42.(in Chinese))
[24]程国森,崔东文.黑猩猩优化算法-极限学习机模型在富水性分级判定中的应用[J].人民黄河,2021,43(7):62-66,103.(CHENG Guo-sen, CUI Dong-wen. Application of Chimp Optimization Algorithm-extreme Learning Machine Model in Judging Water Abundance Grade[J]. Yellow River, 2021, 43(7): 62-66, 103.(in Chinese))
[25]吴忠强,尚梦瑶,申丹丹,等.基于BSA-RELM的纯电动汽车锂离子电池SOC估计[J].计量学报,2019,40(4):693-699.(WU Zhong-qiang, SHANG Meng-yao, SHEN Dan-dan, et al. Estimation of SOC of Li-ion Battery in Pure Electric Vehicle by BSA-RELM[J]. Acta Metrologica Sinica, 2019, 40(4): 693-699.(in Chinese))
[26]刘 鑫,任海莉.基于QPSO正则化极限学习机的轴承故障诊断[J].组合机床与自动化加工技术,2021(3):36-40.(LIU Xin,REN Hai-li.Bearing Fault Diagnosis Based on QPSO Regularized Extreme Learning Machine[J]. Modular Machine Tool & Automatic Manufacturing Technique,2021(3):36-40.(in Chinese))
[27]张亚杰, 崔东文. 基于EMD-FBI-ELM模型的径流预测研究[J]. 人民珠江, 2022, 43(6): 94-100, 107. (ZHANG Ya-jie, CUI Dong-wen. Research on Runoff Prediction Based on EMD-FBI-ELM Model[J]. Pearl River, 2022, 43(6): 94-100, 107.
PDF(7089 KB)
