基于混沌理论和LSSVM的蒸汽负荷预测  

Steam load forecasting based on chaos theory and LSSVM

作　　者：张华强[1] 张晓燕[1] 

机构地区：[1]哈尔滨工业大学(威海)电气工程系,威海264209

出　　处：《系统工程理论与实践》2013年第4期1058-1066,共9页Systems Engineering-Theory & Practice

基　　金：山东省优秀中青年科学家科研奖励基金(BS2010NJ001)

摘　　要：蒸汽是一种重要的二次能源,如何预知热电厂在未来时刻需生产的蒸汽负荷,对于安全、经济地向用户提供高质量的热负荷具有重要意义.针对短期蒸汽负荷序列的预测问题,首先证明了蒸汽负荷序列具有混沌特性,根据Takens定理,重构蒸汽负荷时间序列相空间,分别采用C-C方法和Cao方法确定延迟时间和嵌入维数;然后在相空间中,利用最小二乘支持向量机(LSSVM)建立蒸汽负荷预测模型,并采用模拟退火算法(SA)改进的粒子群优化算法(PSO),即SA_WPSO算法对LSSVM参数的选择方法进行了优化,结果证明该方法能够取得很好的预测效果.The heating steam is an important secondary energy, so it is of great significance to predict the required steam load in the future hours, which is important for the thermal power plant to provide users with high quality heat load securely and economically. Steam load time series proves to be with chaos characteristics. According to Takens theorem, delay time and embedding dimension are calculated respectively using C-C method and Cao method, and the steam load time series is reconstructed in phase space, and then the steam load forecasting model is established using least squares support vector machine （LSSVM）. A SA_WPSO algorithm （improved particle swarm optimization （PSO） with simulated annealing algorithm （SA）） is proposed to implement the optimization of LSSVM parameters. The simulation results show that the method can achieve good prediction results.

关 键 词：混沌 最小二乘支持向量机 粒子群优化 模拟退火 预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]