
doi: 10.1109/ucc.2012.57
The increasing complexity of computer systems has led to the automation of administration functions, in the form of autonomic managers. One important aspect requiring such management is the issue of energy consumption of computing systems, in the perspective of green computing. As these managers address each a specic aspect, there is a need for using several managers to cover all the domains of administration. However, coordinating them is necessary for proper and eective global administration. Such coordination is a problem of synchronization and logical control of administration operations that can be applied by autonomous managers on the managed system at a given time in response to events observed on the state of this system. We therefore propose to investigate the use of reactive models with events and states, and discrete control techniques to solve this problem. In this paper, we illustrate this approach by integrating a controller obtained by synchronous programming, based on Discrete Controller Synthesis, in an autonomic system administration infrastructure. The role of this controller is to orchestrate the execution of reconfiguration operations of all administration policies to satisfy properties of logical consistency. We apply this approach to coordinate three managers : two energy-aware ones, which control server provisioning and processor frequency, and a repair manager.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 2 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
