Smart cities and smart homes are booming fields of development of pervasive systems. With the high stakes these systems have to manage, and their sheer complexity, anomalies have to be considered. In these complex systems are many connected components with computing capacities. They can manage anomalies, even if partially, and can act as some kind of expert systems. These expert systems can be relied upon to provide anomaly management. The complexity to manage generic expert systems brings us to suggest another approach. In this paper, the N-layers is discussed. It layers the various existing expert systems to organize them as a more generic expert system. It also aims to correct some difficulties to develop and integrate generic expert systems into various scales complex systems, such as smart cities or smart homes.