Application of Uncertainty Reasoning Based on Cloud Theory in Spatial Load Forecasting

The fuzzy logic method is a useful way in spatial load forecasting (SLF) simulation. However, the randomness is not fully considered in its key step. This paper proposes a new SLF model for distribution network, which brings in cloud theory. The knowledge representation based on cloud model is adopted to integrate fuzziness and randomness of qualitative concept. The uncertainty reasoning based on it is used to calculate the preference score of the partitioned small area. The randomness of land-use decision is indicated by hyper-entropy obtained from each rule confidence and the digital characters of each cloud model. The small area redevelopment criteria based on this model are provided. Furthermore, the linear multi-objective programming is introduced and improved for the whole-optimal land distribution in which the economic effect and redevelopment are considered. Finally, this model is implemented and the analysis for a real instance is described