摘要
钢铁企业电力负荷作为电力负荷的重要组成部分,钢铁电力负荷的准确预测对于提高电力负荷预测精度具有重要意义。为了实现钢铁电力负荷的中长期预测,本文选取了经济因素和社会因素作为自变量,引入带有惯性权重的粒子群算法(WPSO)对传统的最小二乘支持向量机智能预测模型(LSSVM)参数进行优化,并利用某地区钢铁电力负荷样本数据进行验证,拟合结果显示,经过粒子群算法优化后的最小二乘智能向量机算法预测精度更高,收敛速度更快,具有良好的推广性和适应性。
Steel load is an important part of power load,the accurate steel load forecasting bring great improvement for the total power load forecast accuracy.To realize the medium and long-term steel load forecasting,the paper select the economic and social factor as independent variables.It also proposes a new load forecasting model based on the combination of least squares support vector machine (LSSVM) and weight particle swarm optimization (WPSO).WPSO is used to optimize the parameters of LSSVM.Finally it use the example test to verify the strength of this new intelligent algorithm,the results show the good adaptation and efficiency of the forecasting model.
出处
《华北电力大学学报(自然科学版)》
CAS
北大核心
2014年第6期104-108,共5页
Journal of North China Electric Power University:Natural Science Edition
基金
国家自然科学基金资助项目(71471059)
关键词
钢铁负荷预测
最小二乘支持向量机
粒子群优化
智能预测模型
steel load forecasting
least squares support vector machine (LSSVM)
weight particle swarm optimization (WPSO)
intelligent forecasting algorithm