XAI-Guided Optimization of a Multilayer Network Regression Model
Paper in proceeding, 2024
The recent technological advances create increased network capacity demand, highlighting the need for new network optimization methods. However, the proposed solutions require broad testing with numerous time-consuming simulations. Thus, estimation methods based on Machine Learning (ML) are developed to improve this process. In this work, we create a regression network model to predict four resource utilization metrics using the input set of connection requests. Using eXplainable Artificial Intelligence (XAI) tools, we optimize the proposed model for faster inference without a decrease in prediction quality.
multilayer network
explainable artificial intelligence
resource allocation
machine learning
Author
Katarzyna Duszynska
Wrocław University of Science and Technology
Pawel Polski
Wrocław University of Science and Technology
Micha Wlosek
Wrocław University of Science and Technology
Aleksandra Knapinska
Wrocław University of Science and Technology
Piotr Lechowicz
Wrocław University of Science and Technology
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Krzysztof Walkowiak
Wrocław University of Science and Technology
2024 IFIP Networking Conference, IFIP Networking 2024
769-774
9783903176638 (ISBN)
23rd International Federation for Information Processing on Networking Conference, IFIP Networking 2024
Thessaloniki, Greece,
Thessaloniki, Greece,
Subject Categories
Production Engineering, Human Work Science and Ergonomics
Control Engineering
DOI
10.23919/IFIPNetworking62109.2024.10619785