首页|基于IWOA-KELM的船厂电力负荷超短期预测

基于IWOA-KELM的船厂电力负荷超短期预测

扫码查看
原文链接
  • 万方数据
  • 维普
根据船厂运维管理和电力负荷的特点,提出一种基于改进鲸鱼优化算法(IWOA)优化核函数极限学习机(KELM)的预测模型进行船厂电力超短期负荷预测:为了提高鲸鱼优化算法(WOA)优化性能,引入启发式概率搜索和自适应权重因子;将KELM参数正则化系数C和核参数λ作为优化对象,将均方根误差(RMSE)结合L1 正则化系数作为目标函数,利用IWOA对其进行优化.通过对某船厂实测数据进行对比、研究,结果表明:IWOA-KELM具备良好的泛化能力,预测误差更小,预测精度更高,具备良好的适应性,满足船厂运维人员的使用需求.
Ultra-Short-Term Power Load Forecasting for Shipyards Based on IWOA-KELM
Based on the characteristics of shipyard operation and maintenance management and power loads,a forecasting model is proposed for ultra-short-term power load forecast in shipyards.This model optimizes the kernel extreme learning machine(KELM)using an improved whale optimization algorithm(IWOA).To enhance the optimization performance of the whale optimization algorithm(WOA),heuristic probabilistic search and adaptive weight factors are introduced.The regularization coefficient C and kernel parameter λ of KELM are taken as optimization objects,and the root mean square error(RMSE)combined with the L1 regularization coefficient is used as the objective function,which is optimized by IWOA.Comparative studies on measured data from a shipyard show that IWOA-KELM has good generalization ability,smaller prediction errors,higher prediction accuracy,and good adaptability,meeting the needs of shipyard O&M personnel.

shipyardpower loadforecasting modelwhale optimization algorithm(WOA)kernel extreme learning machine(KELM)adaptive optimizationheuristic probabilistic searchadaptive inertia weight

王帅、孔令兵、王健、郭凤群

展开 >

中船第九设计研究院工程有限公司,上海市 200090

船厂 电力负荷 预测模型 鲸鱼优化算法(WOA) 核函数极限学习机(KELM) 自适应寻优 启发式概率搜索 自适应惯性权重

2024

10.3969/j.issn.1003-8493.2024.12.007

建筑电气
中国建筑西南设计研究院 中国建筑学会建筑电气分会 全国建筑电气设计技术协作及情报交流网

建筑电气

影响因子：0.56
ISSN：1003-8493
年,卷(期)：2024.43(12)