Abstract
This paper introduces a novel multi-agent model for simulating water sharing scenarios under various irrigation policies, together with a novel self adaptive learning algorithm that achieves efficient resource allocation. The main contribution of this work lies in the fact that both the multi-agent model and the proposed learning algorithm operate under the lack of communication between the users of the resource, thus, no assumptions about the development of relations of trust between them are made. Moreover, the proposed learning algorithm uses only local information and operates in a decentralized manner, thus its implementation does not entail significant costs. The model was calibrated using data from a real world ecosystem and experimental results provided statistical and qualitative figures of merit for assessing typical irrigation policies. For all the irrigation policies examined, even if the users of the resource acted under profit maximization criteria, the proposed learning algorithm provided a means of achieving efficient resource allocation, despite the lack of communication. Thus, the proposed model and learning algorithm are valuable tools for assessing alternative irrigation policies and providing the best policy for any given scenario.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.