电力负荷多属性半结构性模糊优选组合预测

Combining forecast based on fuzzy optimal selection of multi attributes semi structural decision-making

在电力规划决策支持系统中,各种负荷预测方法计算中长期电力负荷预测所获得的结果相差较大,为科学准确地确定和推荐预测结果,需要采用相应的分析和决策方法。其决策分析的结构中总目标为获得满意预测推荐解；属性层中既有定量目标,又有定性准则；预测层则以决策支持系统中所有的预测方法和结果为基础。按照此结构采用多属性半结构性模糊优选方法,分别精确计算定量目标特征值矩阵,量化定性准则模糊比较判断矩阵,并计算具有统一标准的相对优属度矩阵,进而将模糊优选方法改进地应用于负荷预测的评价、筛选和组合。实例表明：该方法充分考虑了预测及其决策的相关因素,可用于规划及预测决策支持系统,具有准确、量化、科学和实用性。

In the decision-making support system of electric power planning, a corresponding approach using the decision-making method of fuzzy optimal selection was presented to recommend and confirm the long-middle term load forecasting result truely and scientifically. The hierarchy structure of decision-making for the satisfied forecasting was established. Either the quantitative objects were computed exactly as eigenvalue matrix, or the qualitative criteria were taken into account as fuzzy comparison matrix. The relative membership degrees of them were calculated according to same standard. The fuzzy optimal selection method of multi-attributes was improved and used to assess, select and combine the load forecasting results. The practice example shows that the approach takes account of interrelated factors sufficiency and can be applied in the support system of planning and forecasting, and is feasible, reasonable and practical.