An intelligent agent model with awareness of workflow progress

Abstract

To support human functioning, ambient intelligent agents require knowledge about the tasks executed by the human. This knowledge includes design-time information like: (i) the goal of a task and (ii) the alternative ways for a human to achieve that goal, as well as run-time information such as the choices made by a human during task execution. In order to provide effective support, the agent must know exactly what steps the human is following. However, if not all steps along the path can be observed, it is possible that the agent cannot uniquely derive which path the human is following. Furthermore, in order to provide timely support, the agent must observe, reason, conclude and support within a limited period of time. To deal with these problems, this paper presents a generic focused reasoning mechanism to enable a guided selection of the path which is most likely followed by the human. This mechanism is based upon knowledge about the human and the workflow to perform the task. In order to come to such an approach, a reasoning mechanism is adopted in combination with the introduction of a new workflow representation, which is utilized to focus the reasoning process in an appropriate manner. The approach is evaluated by means of an extensive case study.

Agent-based Cloud service composition

“…The main structure of control is provided by a switch selector (lines [2][3][4][5][6][7][8][9][10][11][12][13], where the first instruction is the reception of a request to resolve a requirement from a SPA (line 3). In complex web services (web services that require exchanging more than one message to provide their output), ad-hoc agent behaviors should be created or added (lines 7-10), based on the web service workflow.…”

“…In addition, in a multiagent system, an agent may have incomplete information (e.g., information about Cloud providers and their services) as well as an incomplete list of capabilities (e.g., mapping consumer requirements to available Cloud resources or offering for leasing Cloud resources) for solving a given problem (e.g., Cloud service composition) [48]. Moreover, agent-based approaches have proved to be effective and efficient in a comprehensive range of application areas, from assisting humans in daily activities [9,26,33] and processing natural language [36] to supporting Grid and Cloud resource management [27,[41][42][43][44][45].…”