Medical Services Optimization Using Differential Evolution

摘要

This paper proposes a method to compose and optimize medical services as business workflows. Such a work flow consists in a set of abstract services, and for each abstract service there are several concrete services. Since each medical service has different QoS (Quality of Service) parameters such as response time, rating, distance and cost, determining the optimal combination of concrete services that realize the ab stract services of the business workflow is an NP hard prob lem. Recent proposals for solving NP optimization problems indicate the Genetic Algorithms (GA) as the best approach for complex workflows. But this problem usually needs to be solved at runtime, a task for which GA may be too slow. We propose a new approach, based on Differential Evolution (DE), that converges faster and it is more scalable and robust than the existing solutions based on Genetic Algorithms.