In embedded network applications, typically a very large part of the area c
ost is due to memory units. Also the power for such applications is heavily
dominated by the storage and transfers. Given its importance, we have deve
loped a systematic memory management methodology in which the storage relat
ed issues are optimized as a first step, In this paper, we present our meth
odology for embedded network applications. It includes both a dynamic memor
y management stage, where the data types and virtual memory managers are de
fined, and a physical memory management stage, where the custom memory arch
itecture is defined. As demonstrated on an industrial example, the applicat
ion of the methodology results in a heavily power and/or area optimized cus
tom memory architecture for a given application.