Model Identification for Energy-Aware Management of Web Service Systems

In SOA environments, service providers need to comply with the service level objectives stipulated in contracts with their Customers while minimizing the operating costs of the physical infrastructure, mainly related to energy costs. The problem can be effectively formalized by using system identification and control theory: the service levels are translated into set-points for the response times of the hosted applications, and performance are traded-off with energy saving objectives based on suitable models for server dynamics. As the behavior of the incoming workload changes significantly within a single business day, control-oriented system identification approaches are very promising to model such systems, especially at a very fine grained time scales and in transient conditions. In this paper Linear Parameter Varying (LPV) state space system identification algorithms are analyzed for modeling Web services systems. The suitability of LPV models is investigated and their performance assessed by experimental data.