ecms_neu_mini.png

Digital Library

of the European Council for Modelling and Simulation

 

Title:

Using The CMA Evolution Strategy For Locating Submarine Groundwater Discharge

Authors:

Tarek A. El-Mihoub, Christoph Tholen, Lars Nolle

Published in:

 

 

2020). ECMS 2020 Proceedings Edited by: Mike Steglich, Christian Muller, Gaby Neumann, Mathias Walther, European Council for Modeling and Simulation.

 

DOI: http://doi.org/10.7148/2020

ISSN: 2522-2422 (ONLINE)

ISSN: 2522-2414 (PRINT)

ISSN: 2522-2430 (CD-ROM)

 

ISBN: 978-3-937436-68-5
ISBN: 978-3-937436-69-2(CD)

 

Communications of the ECMS , Volume 34, Issue 1, June 2020,

United Kingdom

 

Citation format:

Tarek A. El-Mihoub, Christoph Tholen, Lars Nolle (2020). Using The CMA Evolution Strategy For Locating Submarine Groundwater Discharge, ECMS 2020 Proceedings Edited By: Mike Steglich, Christian Mueller, Gaby Neumann, Mathias Walther European Council for Modeling and Simulation. doi: 10.7148/2020-0032

DOI:

https://doi.org/10.7148/2020-0032

Abstract:

For effective localisation of a search target by a swarm of Autonomous Underwater Vehicles (AUVs), a suitable cooperative search strategy should be utilised. Various aspects of the search task should be taken into account when selecting a search strategy. The nature of the search environment, the search target and the search agents should be considered. The Covariance Matrix Adaption Evolution Strategy (CMA-ES) is a well-known search strategy that proves its success in solving different continuous optimisation problems. This paper investigates utilising the CMA-ES to locate a Submarine Groundwater Discharge (SGD) using the temperature of water as a tracer. The impact of introducing some of the constraints, which are imposed by the search task, on the CMA-ES performance are studied. The influence of the number of the AUVs and their energy capacities on the search performance is investigated. The effect of the resolution of the temperature sensors together with the localisation and the navigation problems on the search behaviour are explored. The results show that these constrains have varying degrees of impact on the performance of the search strategy.

 

Full text: