基于粗糙集和元胞自动机的配电网空间负荷预测

Spatial Load Forecasting for Distribution Networks Based on Rough Sets and Cellular Automata

该文提出一种新颖的配电网空间负荷预测方法,采用元胞自动机(cellular automata,CA)模拟城市土地利用动态发展过程,预测规划区域各小区土地的未来使用类型。根据城市发展的实际情况,确定CA的迭代时间和转换规则调整时间,并采用粗糙集(roughsets,RS)理论逐步对每个调整时间段中可能影响小区土地使用决策的因素进行属性约简,获取动态的元胞自动机转换规则,消除冗余属性,克服了传统方法在获取小区土地使用决策受主观因素影响较大以及在规划年内一直采用静态的土地使用决策规则的缺陷。最后通过1个实例验证了该方法的有效性。

A new spatial load forecasting （SLF） method for distribution network by using cellular automata （CA） theory to simulate the process of urban land-use dynamic development and forecast future land-use types of each small-area is introduced. The iteration time and adjusting time of transition rules of CA are determined by the practical situation of urban development. In order to eliminate redundancies, overcome faults such as land-use rules which are always static and suffer influence from subjectivity by traditional methods, rough sets （RS） theory is used to carry out step-by-step attribute reduction for potential influencing factors and obtain dynamic transition rules of CA. Finally, the validity of this method is validated by an actual example.