Home // ICAS 2025, The Twenty-First International Conference on Autonomic and Autonomous Systems // View article

Synthetic Data Generation for Autonomic Computing

Authors:
Catherine Saunders
Roy Sterritt
Peter Nicholl
Ian McChesney

Keywords: Autonomic Computing; conditional generative adversarial networks; ctgan; autonomic manager; mape-k loop

Abstract:
This paper discusses an approach that integrates data generation capabilities into the Autonomic Computing MAPE-K (Monitor Analyse Plan Execute and Knowledge Loop) to mitigate problems with data scarcity in autonomous space missions. The purpose of this work is to enhance the decision-making abilities of an Autonomic Manager by providing it with the ability to use simulation and data generation. A Conditional Tabular Generative Adversarial Network (CTGAN) is used to generate new synthetic datasets. Synthetic datasets are then evaluated to assess their utility. The evaluation results show that synthetic data can closely resemble the original data. However, this paper does not address the challenges of equipping a swarm with the necessary hardware, focusing instead on the feasibility of the proposed data generation pipeline.

Pages: 1 to 7

Copyright: Copyright (c) IARIA, 2025

Publication date: March 9, 2025

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-68558-241-8

Location: Lisbon, Portugal

Dates: from March 9, 2025 to March 13, 2025