Time separation technique for large databases

Abstract

A time decomposition technique is suggested for large-database (DB) models. The problem of network aggregation is studied and the results used to create a meaningful decomposed model. Decomposition conditions and assumptions are discussed and illustrated by examples. A practical operating schedule is presented for the time-separated DB model. The schedule uses a sequence of decomposed models, which are to be constructed recursively. The application of the time separation technique for large-DB models is presented in the form of a closed-loop algorithm. The problem of decomposition stability with respect to variations in time constants is considered as well. Two alternative approaches to the problem are suggested. For a probabilistic approach, practical approximate formulas are obtained for subsystem time constants and recommendations are made with respect to the decomposition structure. An approximate performance analysis is done for both standard and time-decomposed models. A comparison of the results is given.