Similarity-based load adjustment for static real-time transaction systems

How to exploit application semantics to improve the performance of a real-t ime data-intensive application has been an active research topic in the pas t few years. Weaker correctness criteria and semantics-based concurrency co ntrol algorithms were proposed to provide more flexibility in reordering re ad and write events [4], [7], [8], [9], [8], [9], [22]. Distinct from past work, this paper exploits the trade-off between data consistency and system workload. The definition of similarity [8] is combined with the idea of tr ansaction skipping to provide a theoretical foundation for reducing the wor kload of a transaction system. We also propose guidelines to adjust the exe cution frequencies of a static set of transactions and prove their correctn ess. The strengths of this work were verified by simulation experiments on an air traffic control example [20].