引用本文: | 杨 茂,张书天,王 勃.基于因果正则化极限学习机的风电功率短期预测方法[J].电力系统保护与控制,2024,52(11):127-136.[点击复制] |
YANG Mao,ZHANG Shutian,WANG Bo.Short-term wind power forecasting method based on a causal regularized extreme learning machine[J].Power System Protection and Control,2024,52(11):127-136[点击复制] |
|
摘要: |
随着风电并网比例的逐年提高,电力系统对风电功率预测的准确性和稳定性提出了更高要求。对于同一风电场而言,为了避免不同特征选择方法所选择的风电场特征子集不同,从因果关系的角度出发,提出了一种基于因果正则化极限学习机(causal regularized extreme learning machine, CRELM)的风电功率短期预测方法。首先将极限学习机(extreme learning machine, ELM)建模为结构因果模型(structural causal model, SCM),在此基础上计算隐藏层神经元与输出层神经元之间的平均因果效应向量。然后将该平均因果效应向量与输出层权重相结合构成因果正则化项,在最小化训练误差的同时最大化网络的因果关系,以进一步提升模型的预测准确性和预测稳定性。最后,以国内蒙西某风电场数据为例,与采用特征选择或不采用特征选择的预测模型相对比,验证了所提方法的有效性和适用性。 |
关键词: 特征选择 因果正则化 结构因果模型 平均因果效应向量 极限学习机 |
DOI:10.19783/j.cnki.pspc.231097 |
投稿时间:2023-08-25修订日期:2023-12-29 |
基金项目:国家重点研发计划项目资助“大规模风电/光伏多时间尺度供电能力预测技术”(2022YFB2403000) |
|
Short-term wind power forecasting method based on a causal regularized extreme learning machine |
YANG Mao1,ZHANG Shutian1,WANG Bo2 |
(1. Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education,
Northeast Electric Power University, Jilin 132012, China; 2. State Key Laboratory of Operation and Control of Renewable
Energy & Storage Systems, China Electric Power Research Institute, Beijing 100192, China) |
Abstract: |
With the increasing proportion of wind power connected to the grid year by year, the power system has higher requirements for the accuracy and stability of wind power forecasting. For the same wind farm, to avoid different feature subsets of wind farms selected by different feature selection methods, this paper proposes a short-term wind power forecasting method based on a causal regularization extreme learning machine from the perspective of causality. First, the extreme learning machine (ELM) model is modeled as a structural causal model, and then the average causal effect vector between hidden layer neurons and output layer neurons is calculated. Then the average causal effect vector is combined with the weight of the output layer to form a causal regularization term. This minimizes the training error and maximizes the causal relationship of the network, further improving the forecasting accuracy and stability of the model. Finally, taking the data of a wind farm in Mengxi, China as an example, and comparing with the forecasting model with or without the feature selection method, the effectiveness and applicability of the proposed method are verified. |
Key words: feature selection causal regularization structure causal model average causal effect vector extreme learning machine |