马尔科夫理论在中长期负荷预测中的应用  

Application of Markov Theory in Mid-Long Term Load Forecasting

作　　者：黄银华[1,2] 彭建春[1] 李常春[3] 刘鼎[1] 孙广强[1] 

机构地区：[1]湖南大学电气与信息工程学院,长沙410082 [2]福建省电力勘测设计院,福州350003 [3]天津市电力科学研究院,天津300384

出　　处：《电力系统及其自动化学报》2011年第5期131-136,共6页Proceedings of the CSU-EPSA

摘　　要：针对灰色预测模型对随机波动性较大的数据序列拟合较差、预测精度较低的情况,提出了一种基于马尔科夫灰色残差修正的预测模型,该模型考虑到马尔科夫理论中转移概率可以反映随机因素的影响、适用于随机波动较大的动态过程的特点,将其与灰色预测模型进行有机结合。文中一方面利用马尔科夫链对电力负荷的未来残差值进行修正;另一方面运用马尔科夫状态转移矩阵对未来残差值的符号进行判定。该方法弥补了灰色预测模型的固有缺陷。预测结果表明该方法在提高组合预测精度上具有可行性。Based on the fact that using GM（1,1） model to the high waving peak load has low precision on simulation and forecast, a novel combinatorial forecasting algorithm based on Markov chain is proposed in this paper. Deliberate on the features of Markov theory which can reflects the influence on random factors and extend to the stochastic process which is dynamic and fluctuating is considered, and it is seamless integrated with GM （1,1） model. On the one hand, this paper uses Markov chain to correct the future residual of electrical load, on the other hand, the state transition matrix of Markov is adopted to forecast the sign of future residual. This method make up the fundamental disadvantages of GM（1,1）model. And the results of the load forecasting indicate the feasibility of the proved method.

关 键 词：中长期负荷预测 灰色模型 残差修正 马尔科夫理论 转移概率 

分 类 号：TM711[电气工程—电力系统及自动化]