This paper proposes the usage of the fuzzy rule-based Bayesian algorithm to determine which residential appliances can be considered for the Demand Response program. In contrast with other related studies, this research recognizes both randomness and fuzziness in appliance usage. Moreover, the input data for usage prediction consists of nodal price values (which represent the actual power system conditions), appliance operation time, and time of day. The case study of residential power consumer behavior modeling was implemented to show the functionality of the proposed methodology. The results of applying the suggested algorithm are presented as colored 3D control surfaces. In addition, the performance of the model was verified using R squared coefficient and root mean square error. The conducted studies show that the proposed approach can be used to predict when the selected appliances can be used under specific circumstances. Research of this type may be useful for evaluation of the demand response programs and support residential load forecasting.

The paper presents Gupta's relational decomposition technique expanded on linguistic level. It allows to reduce the hardware cost of the fuzzy system or the computing time of the final result, especially when referring to First Aggregation Then Inference (FATI) relational systems or First Inference Then Aggregation (FITA) rule systems. The inference result of the hierarchical system using decomposition technique is more fuzzy than of the classical system. The paper describes a linguistic decomposition technique based on partitioning the knowledge base of the fuzzy inference system. It allows to decrease or even totally remove a redundant fuzziness of the inference result.