Author Information

Julia Gorthey

Is this project an undergraduate, graduate, or faculty project?

Undergraduate

Project Type

individual

Campus

Daytona Beach

Authors' Class Standing

Julia Gorthey, Senior

Lead Presenter's Name

Julia Gorthey

Lead Presenter's College

DB College of Engineering

Faculty Mentor Name

Byran Watson

Abstract

Resource allocation in scenarios involving uncertainty, limited information, and potential threats can pose significant challenges and difficulties. Swarm intelligence, characterized by the cooperative dynamics of individuals, could enhance community resilience. This is particularly true for scenarios that involve the allocation of finite resources. This study examines a new biologically inspired distributed resource allocation algorithm, drawing inspiration from snapping shrimp colonies. Operating within environments with uncertainty and resource limitations, snapping shrimp colonies exhibit distributed resource allocation when they allocate a limited number of defenders to protect the nest. The hypothesis of the paper is if inspiration is drawn from the snapping shrimp colonies, then the distributed resource allocation can be improved. The result is a new Snapping Shrimp Resource Allocation Algorithm (SSRAA). The proposed algorithm is assessed on an Agent-Based Model of a wildfire response. Wildfire response requires distributed agents to make resource allocation decisions with limited situational knowledge. The proposed algorithm outperforms a current wildfire response strategy for 86% of the scenarios examined, saving an average of an additional 3% of the forest from burning. This is especially promising because the proposed algorithm does not require global knowledge, central coordination, or special technology to implement. Our goal is that future use of this algorithm will result in a long-term, smarter, and more sustainable world by providing an approach for distributed resource allocation for agents with limited knowledge.

Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?

Yes, Spark Grant

Share

COinS
 

A New Biological Inspired Resource Allocation Algorithm for Distributed Multi Agent Systems with Limited Knowledge

Resource allocation in scenarios involving uncertainty, limited information, and potential threats can pose significant challenges and difficulties. Swarm intelligence, characterized by the cooperative dynamics of individuals, could enhance community resilience. This is particularly true for scenarios that involve the allocation of finite resources. This study examines a new biologically inspired distributed resource allocation algorithm, drawing inspiration from snapping shrimp colonies. Operating within environments with uncertainty and resource limitations, snapping shrimp colonies exhibit distributed resource allocation when they allocate a limited number of defenders to protect the nest. The hypothesis of the paper is if inspiration is drawn from the snapping shrimp colonies, then the distributed resource allocation can be improved. The result is a new Snapping Shrimp Resource Allocation Algorithm (SSRAA). The proposed algorithm is assessed on an Agent-Based Model of a wildfire response. Wildfire response requires distributed agents to make resource allocation decisions with limited situational knowledge. The proposed algorithm outperforms a current wildfire response strategy for 86% of the scenarios examined, saving an average of an additional 3% of the forest from burning. This is especially promising because the proposed algorithm does not require global knowledge, central coordination, or special technology to implement. Our goal is that future use of this algorithm will result in a long-term, smarter, and more sustainable world by providing an approach for distributed resource allocation for agents with limited knowledge.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.