基于混沌时间序列法的微网短期负荷预测  

Short-term Load Forecasting for Microgrid Based on Method of Chaotic Time Series

作　　者：李东东[1] 覃子珊[1] 林顺富[1] 郑小霞[1] 王天祥 

机构地区：[1]上海电力学院上海市电站自动化技术重点实验室,上海200090 [2]金华电业局,金华321015

出　　处：《电力系统及其自动化学报》2015年第5期14-18,共5页Proceedings of the CSU-EPSA

基　　金：国家自然科学基金项目(50807035;51177098);上海市重点科技攻关项目(10110502100);上海市教委创新项目(11ZZ169);上海市教委重点学科建设项目(J51303)

摘　　要：针对微网中居民小区用电量较低、负荷波动大的特点,提出了结合混沌理论重构相空间并建立最大Lyapunov指数模型的方法。该方法不直接考虑影响负荷的气候、电价等因素,输入数据参数较少,采用C-C方法求延迟时间与嵌入维,运用改进的最大Lyapunov指数方法进行预测。将此方法用于安徽某一小区的实际负荷数据预测,预测结果表明该算法的预测精度较高,可以为微网的优化运行提供负荷依据,仿真结果验证了算法的有效性和实用性。On the basis of the low power consumption and severe fluctuation load of residential area in microgrid, a model of maximum Lyapunov exponent via the phase space reconstruction is constructed combined with chaos theory. This method does not directly consider the impact of factors such as climate, electricity price, thus it requires less input and parameters. It utilizes C-C method to solve the delay time and the embedding dimension, and uses the improved maximum Lyapunov exponent method to forecast. The model is applied to forecast actual load data of a certain community in Anhui province. According to the time of use （TOU）, a relative error indicator for time period based on the control of microgrid energy storage charge and discharge system is proposed. Simulation results demonstrate the efficiency and practicality of the algorithm.

关 键 词：短期负荷预测 混沌 LYAPUNOV指数 微网 分时电价 

分 类 号：TM715[电气工程—电力系统及自动化]