Learning to collaborate in distributed environments by means of an awareness-based artificial neural network

摘要

This paper is an extension of a previous work presented in International Work Conference on Artificial Neural Network 2009 (IWANN 2009). The paper contains more details and results of the strategy known as Collaborative Distributed Environment by means of an Awareness & Artificial Neural Network strategy (CAwANN). CAwANN is part of the structure of Awareness-based learning Model for distriButed collAborative enviRonment (AMBAR) which is an awareness-based learning model, developed for distributed environments, that allows nodes to accomplish an effective collaboration by means of a multi-agent architecture in which agents are aware of its surroundings by means of a parametrical and flexible use of this information. CAwANN is an ANN-based strategy used to include learning abilities into AMBAR aiming to improve the effectiveness and efficiency of collaboration process by learning three different processes: (1) to collaborate based on levels of awareness; (2) to select a potential candidate to negotiate on saturated conditions; and (3) to decide whether or not a node must change the information that describes its current conditions related with collaboration. Based on the definitions of efficiency and effectiveness presented in this paper and the results obtained from simulated conditions CAwANN has an average efficiency of 100% and an average effectiveness of 86%.