Computer Management

This work presents the use of artificial intelligence (AI) techniques for aiding in the improvement of the performance of a high-speed networks management system. An intelligent agent is responsible for collect information and compare these information with a database that contains parameters for each information type in order to detect facts which identify proactively the possible existence of a problem. Such detection is conducted by means of AI techniques making possible proactive actions and, as such, may prevent the occurrence of problems.

This work presents the use of artificial intelligence (AI) techniques for aiding in the improvement of the performance of a high-speed networks management system. An intelligent agent is responsible for collect information and compare these information with a database that contains parameters for each information type in order to detect facts which identify proactively the possible existence of a problem. Such detection is conducted by means of AI techniques making possible proactive actions and, as such, may prevent the occurrence of problems.

The increased popularity of the proactive security paradigm aggravated the need for distributed surveillance systems. These systems are built using smart sensor networks which cover large areas of civilian concentration. Such networks need intelligent management systems to control the large number of sensor nodes and the large volume of data. Sensor Management Frameworks (SMF) aim to coordinate the sensor nodes in a manner that improves the process of system control and situation awareness. Most SMFs proposed in literature are point solutions that do not use generic development architectures to allow reusability and extendability of different research projects. This work introduces an organizational development suite based on the service-oriented architecture to address the requirements of SMF from a stacked layer perspective. Furthermore, this paper discusses the important functional properties of such systems, and categorizes these functional properties according to their processing level. A case study was proposed that shows the extendability and reusability of the proposed organizational suite.

Network self-management, among other objectives, looks for solutions (systems, frameworks and/or strategies) in which the human intervention is drastically reduced in the analysis and planning of new network states, which in turn, is based on a set of SLAs (Service Level Agreement) definitions and traffic profile. The self-management system/framework has to find a solution meeting SLA and traffic requirements within a reasonable computational time (execution time) in order to achieve a near real time operation. In general, it is necessary to adopt approaches based on reasoning and learning in self-management systems in order to avoid and/or reduce human intervention [1]. As such, self-management systems/frameworks do require the storage of network states. In this context, it is important to identify critical states and, if possible, to predict when they will occur in order to facilitate the self-management process. In this paper, a proposal for pseudo-predictability based on Case-Based Reasoning (CBR) is presented. The pseudo-predictability CBR method considers previous network states to infer future network state scenario. It was developed for the self-management framework defined in [2] and, in general, further promotes the scalability of self-managed systems.