Performance Analysis of View Maintenance Techniques for DW

TL;DR

This paper compares different view maintenance techniques for data warehouses, analyzing their space usage and efficiency in propagating updates from remote sources to materialized views.

Contribution

It provides a comprehensive classification and comparison of four major categories of view maintenance techniques in data warehouses.

Findings

Self maintainable incremental maintenance uses less space.

Not self maintainable recomputation accesses fewer rows.

Self maintainable recomputation requires more storage.

Abstract

A Data Warehouse stores integrated information as materialized views over data from one or more remote sources. These materialized views must be maintained in response to actual relation updates in the remote sources. The data warehouse view maintenance techniques are classified into four major categories self maintainable recomputation, not self maintainable recomputation, self maintainable incremental maintenance, and not self maintainable incremental maintenance. This paper provides a comprehensive comparison of the techniques in these four categories in terms of the data warehouse space usage and number of rows accessed in order to propagate an update from a remote data source to a target materialized view in the data warehouse.