Ice Coating Prediction Based on Two-Stage Adaptive Weighted Ensemble Learning

被引:1
|
作者
Guo, Heng [1 ]
Cui, Qiushi [1 ]
Shi, Lixian [1 ]
Parol, Jafarali [2 ]
Alsanad, Shaikha [2 ]
Wu, Haitao [3 ]
机构
[1] Chongqing Univ, Sch Elect Engn, Chongqing 400044, Peoples R China
[2] Kuwait Inst Sci Res, Kuwait 999044, Kuwait
[3] State Grid Chongqing Elect Power Co, Elect Power Sci Res Inst, Chongqing 400020, Peoples R China
关键词
transmission line; ice coating prediction; data driven; multi-meteorological scenario; ensemble learning; MACHINE;
D O I
10.3390/pr12091854
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Severe ice accretion on transmission lines can disrupt electrical grids and compromise the stability of power systems. Consequently, precise prediction of ice coating on transmission lines is vital for guiding their operation and maintenance. Traditional single-model icing prediction methods often exhibit limited accuracy under varying environmental conditions and fail to yield highly accurate predictions. We propose a multi-scenario, two-stage adaptive ensemble strategy (MTAES) for ice coating prediction to address this issue. A combined clustering approach is employed to refine the division of ice weather scenarios, segmenting historical samples into multiple scenarios. Within each scenario, the bagging approach generates multiple training subsets, with the extreme learning machine (ELM) used to build diverse models. Subsequently, a two-stage adaptive weight allocation mechanism is introduced. This mechanism calculates the distance from the scenario cluster centers and the prediction error of similar samples in the validation set for each test sample. Weights are dynamically allocated based on these data, leading to the final output results through an adaptive ensemble from the base model repository. The experimental results show that the model is significantly better than traditional models in predicting ice thickness. Key indicators of RMSE, MAE, and R2 reach 0.675, 0.522, and 83.2%, respectively, verifying the effectiveness of multi-scene partitioning and adaptive weighting methods in improving the accuracy of ice cover prediction.
引用
收藏
页数:20
相关论文
共 50 条
  • [41] Two-Stage Sampling, Prediction and Adaptive Regression via Correlation Screening
    Firouzi, Hamed
    Hero, Alfred O., III
    Rajaratnam, Bala
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2017, 63 (01) : 698 - 714
  • [42] Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification
    Ding, Jiaqi
    Song, Jie
    Li, Jiawei
    Tang, Jijun
    Guo, Fei
    FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY, 2022, 9
  • [43] Two-stage transient stability assessment using ensemble learning and cost sensitivity
    Lei, Aoyu
    Mei, Yong
    Ma, Dexin
    Liu, Zining
    Tao, Wenwei
    Huang, Fangneng
    Frontiers in Energy Research, 2024, 12
  • [44] A Two-Stage Approach for Flight Departure Delay Forecasting Using Ensemble Learning
    Guan, Feng
    Hao, Mengyan
    Guo, Zhen
    CICTP 2020: TRANSPORTATION EVOLUTION IMPACTING FUTURE MOBILITY, 2020, : 209 - 220
  • [45] Two-stage consumer credit risk modelling using heterogeneous ensemble learning
    Papouskova, Monika
    Hajek, Petr
    DECISION SUPPORT SYSTEMS, 2019, 118 : 33 - 45
  • [46] Prediction of Financial Assets Income Based on Dynamic Weighted Ensemble Learning
    Yang, Qing
    Gong, Yun-Peng
    Gao, Cai
    Journal of Network Intelligence, 2024, 9 (04): : 1951 - 1965
  • [47] A new stepwise decomposition ensemble model based on two-stage particle swarm optimization algorithm for the runoff prediction
    Guo T.
    Song S.
    Zhang T.
    Wang H.
    Shuili Xuebao/Journal of Hydraulic Engineering, 2022, 53 (12): : 1456 - 1466
  • [48] Boosting Advanced Nasopharyngeal Carcinoma Stage Prediction Using a Two-Stage Classification Framework Based on Deep Learning
    Huang, Jin
    He, Ruhan
    Chen, Jia
    Li, Song
    Deng, Yuqin
    Wu, Xinglong
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2021, 14 (01)
  • [49] Boosting Advanced Nasopharyngeal Carcinoma Stage Prediction Using a Two-Stage Classification Framework Based on Deep Learning
    Jin Huang
    Ruhan He
    Jia Chen
    Song Li
    Yuqin Deng
    Xinglong Wu
    International Journal of Computational Intelligence Systems, 14
  • [50] Neuroelectric activity imaging based on a two-stage weighted pseudoinverse algorithm
    Wu, Q
    Li, Y
    Song, CY
    Zhao, DX
    Shen, XQ
    Yan, WL
    APPLIED ELECTROMAGNETICS (III), 2001, 10 : 333 - 336