This repository contains supplementary materials for the paper:
R. Lovas, E. Rigó, D. Unyi, B. Gyires-Tóth, Experiences with Deep Learning Enhanced Steering Mechanisms for Debugging of Fundamental Cloud Services, IEEE Access, accepted publication
Datasets:
- data/bufferv2: Simple buffered producer-consumer path simulation datasets with different generation parameters, including deadlocked and deadlock-free implementations.
- data/q5m: Queued buffered producer-consumer path simulation datasets with 2 and 3 consumers and different generation parameters, including deadlocked and deadlock-free implementations.
- data/rest-tree1: REST architecture SLA event simulation datasets with a moderate number of nodes (small, medium, large). Several simulation paths per graph.
- data/rest-tree2: REST architecture SLA event simulation datasets with a high number of architectures consisting of 15, 20, 25 and 30 nodes. One cyclic simulation path per graph.
If you need more data, code or information about our work, please contact the corresponding author: Róbert Lovas (robert.lovas (at) sztaki.hu)
The work reported in this paper, carried out as a collaboration between SZTAKI and BME, has been partly supported by the the European Union project RRF-2.3.1-21-2022-00004 within the framework of the Artificial Intelligence National Laboratory. This work was partially funded by the National Research, Development and Innovation Office (NKFIH) under OTKA Grant Agreement No. K 132838. The presented work of R. Lovas was also supported by the János Bolyai Research Scholarship of the Hungarian Academy of Sciences. On behalf of the 'MILAB - SmartLab' cloud project, we are grateful for the possibility to use ELKH Cloud which helped us achieve the results published in this paper.