中长期电量的组合预测存在权重选择困难,适应性、抗干扰性较差的问题.文中结合目前广泛应用的组合预测技术,设计了以Odds-Matrix算法为核心的Odds-Matrix组合预测方法.该组合预测方法利用Odds-Matrix算法对单一预测模型的有效性进行定量分析,用权重概率分布函数来描述各个方法的优劣,然后根据权重进行单一预测模型的筛选和组合.利用实际数据对所设计的Odds-Matrix组合预测方法进行测试,结果表明,文中预测方法的精确度较其他常用组合预测法较高,说明该方法具有较强的适应性与抗干扰性.
For the combination forecasting of the medium and long term electricity consumption,there exists a difficulty in selecting weights as well as the problems of poor adaptability and low noise immunity. Aiming at the above issues,an odds-matrix combination forecasting method based on the odds-matrix algorithm is proposed by taking into account the widely-used combination forecasting technique. In this method,the odds-matrix algorithm is employed to carry out the quantitative analysis on the validity of single forecasting models,and the probability distribution function of the weight is adopted to describe the advantages and disadvantages of each method. Then,single forecasting models are selected and combined based on the weight. Finally,the proposed method is tested by using the actual data. The results show that the proposed method achieves a higher accuracy in comparison with other commonly-used combination forecasting methods,which means that it possesses stronger adaptability and better noise immunity.