【作者】 胡雨沙； 满奕； 李继庚； 洪蒙纳； 刘焕彬；

【Author】 HU Yu-sha;MAN Yi;LI Ji-geng;HONG Meng-na;LIU Huan-bin;State Key Laboratory of Pulp and Paper Engineering,South China University of Technology;

【机构】 华南理工大学制浆造纸工程国家重点实验室；

【摘要】 制浆造纸生产过程中需要消耗大量的电能,对制浆造纸厂的用电负荷进行预测有利于合理安排生产调度,从而降低能耗。本研究课题提出了一种最小二乘支持向量机(LSSVM)和粒子群优化技术(PSO)相结合的短期电力负荷预测方法(PSO-LSSVM),可对造纸企业未来每半个小时的电力负荷进行预测。结果表明,采用本研究课题提出的PSO-LSSVM方法进行短期电力负荷预测时,预测结果的平均相对误差值约为0.83%,精度高于其他行业的电力负荷预测值,模型具有良好的可行性和有效性。更多还原

【Abstract】 Pulp and papermaking processes consume large amount of electricity for production.The forecast of the power load of the paper mill is conducive to the production scheduling and energy consumption reduction.This paper proposes a short-term power load forecasting method based on least-squares support vector machine(LSSVM) and particle swarm optimization(PSO) algorithms,which is used to predict the power load for the future half hour in the paper mills.Combined with the industrial data from a paper mill,the forecasting results show that the mean relative error of the proposed PSO-LSSVM model is around 0.83%,which shows good feasibility of the model for the paper mills.更多还原