Advanced State Fuzzy Cognitive Maps applied on nearly Zero Energy Building model

摘要

Fuzzy Cognitive Maps method combines the advantages of Fuzzy Logic, such as their human reasoning and linguistic features, with the advantages of Neural Networks, such as their low mathematical calculation requirements, in order to model complex dynamic systems on a wide variety of applications. The system variables and their interconnections are described using a graph and a weight matrix. Application of experts’ knowledge leads towards more realistic system models. In addition, the implementation of state-space theory in combination with learning algorithms, lead to a new generation of Fuzzy Cognitive Maps, the Advanced State Fuzzy Cognitive Maps. All the above are implemented on a nearly Zero Energy Building model, using real weather data and presenting its annual energy response.