Application of distributed expert systems to the advanced control of smart houses

Abstract

A distributed expert system has been proposed for the smart house control. Its configuration is mainly based on the use of distributed nodes connected by means of a CAN network. This kind of systems allow the implementation of highly flexible control systems capable of adapting themselves to different situations. The expert system used is based on Rule Nets (RN), which are a formalism that seeks to express an automatism in a similar way to as would make it a human being: "IF antecedents THEN consequents". But at the same time Rule nets are a tool for the design, analysis and implementation of rule based systems (RBS), and consist on a mathematic-logical structure which analytically reflects the set of rules that the human expert has designed. Additionally, the RN is able to take decisions concerning possible malfunctions and has bounded response time.