自适应卡尔曼滤波在电力系统短期负荷预测中的应用

将卡尔曼滤波原理运用于电力系统负荷预测通常是针对线性定常系统,并在定常噪声协方差的前提下进行,模型的灵敏度差和预报精度不高.作者考虑了电力系统负荷自身的变化特点,根据不同日期同一时刻的负荷历史数据建立了含有时变系数的负荷系统模型、观测模型和系统参数模型,采用两段自适应卡尔曼滤波方法,同时考虑噪声协方差对预测精度的影响,运用时变噪声统计估值器对噪声协方差进行自适应估计,用预测方程预测次日的负荷.结合实际电网数据进行的预测计算取得了较好的结果.

APPLICATION OF ADAPTIVE KALMAN FILTER IN POWER SYSTEM SHORT-TERM LOAD FORECASTING

In most references applying the Kalman filtering theory to load forecasting the power system was regarded as a linear system with constant parameters and constant noise covariances, therefore, such a premise led to the inaccuracy of load forecasting models and inevitably the forecast accuracy was reduced. Considering the variation features of power load its own and according to the historical load data at same moment in different days the load model with time-varying coefficient as well as the observation model and system parameter model are built. Using two-stage adaptive Kalman filtering method and at the same time considering the influence of noise covariance on forecast accuracy, the adaptive estimation of noise covariances is conducted by time-varying noise estimator, then the load of the next day is forecasted by forecasting equation. The relative error analysis of the short-term load forecasting results of actual power network by the proposed method shows that the proposed method is effective.