This repository includes data sets used to develop and evaluate data-driven methods for network analysis. The results of these analyses are published in several research papers and theses. We collect all traces from real testbeds (described in the presented papers) by running applications under different load patterns.
Data traces "VoD periodic - CNSM 2015.zip" and "VoD flashcrowd - CNSM 2015.zip" are first collected and used for the research published in:
- R. Yanggratoke, J. Ahmed, J. Ardelius, C. Flinta, A. Johnsson, D. Gillblad, and R. Stadler, “Predicting Service Metrics for Cluster-based Services using Real-time Analytics,” in Network and Service Management (CNSM), 2015 11th International Conference on. IEEE, 2015, pp. 135–143.
Date traces "KV flashcrowd - JNSM 2017.zip" and "KV periodic - JNSM 2017.zip" are first collected and used for the research published in: 2) 2) R. Stadler, R. Pasquini, and V. Fodor, “Learning from network device statistics,” Journal of Network and Systems Management, vol. 25, no. 4, pp. 672–698, 2017.
These research papers describe the testbed and the KV and VoD services. Later we use these data sets for the following research papers:
- Forough Shahab Samani, Rolf Stadler. "Predicting Distributions of Service Metrics using Neural Networks," 14th International Conference on Network and Service Management (CNSM), 2018.
- Forough Shahab Samani, Rolf Stadler, Andreas Johansson, Christofer Flinta, "Demonstration: Predicting Distributions of Service Metrics," IFIP/IEEE Symposium on Integrated Network and Service Management (IM), 2019.
- Forough Shahab Samani, Hongyi Zhang, Rolf Stadler, "Efficient Learning on High-dimensional Operational Data," 15th International Conference on Network and Service Management (CNSM), 2019.
- Forough Shahab Samani, Rolf Stadler, Christofer Flinta, Andreas Johansson, "Conditional Density Estimation of Service Metrics for Networked Services," IEEE Transactions on Network and Service Management, 2021.
- Xiaoxuan Wang, Forough Shahab Samani, Rolf Stadler, "Online feature selection for rapid, low-overhead learning in networked systems," 16th International Conference on Network and Service Management (CNSM), 2020.
- Xiaoxuan Wang, Forough Shahab Samani, Andreas Johnsson, Rolf Stadler, "Online feature selection for low-overhead learning in networked systems," 17th International Conference on Network and Service Management (CNSM), 2021.
- Zhang, Hongyi. "Efficient learning on high-dimensional operational data." (2019).
- Xiaoxuan Wang, “Dimensionality reduction for performance prediction in networked systems,” master thesis, KTH Royal Institute of Technology, 2020.
- Tang Chen, "Forecasting Service Metrics for Network Services," master thesis, KTH Royal Institute of Technology, (2020).
Another set of data traces ("data - CNSM 2022 - TNSM 2024.zip") is related to a microservice-based application developed by Forough Shahabsamani presented in our framework and application and application use case of the framework. We deploy this application as our testbed which is explained mainly in the following publications:
- Forough Shahab Samani, Rolf Stadler, "Dynamically meeting performance objectives for multiple services on a service mesh," 18th International Conference on Network and Service Management (CNSM), 2022.
- Forough Shahab Samani, Rolf Stadler, "A Framework for dynamically meeting performance objectives on a service mesh". IEEE Transactions on Network and Service Management, 2024.
- Forough Shahab Samani, Kim Hammar, Rolf Stadler, "Online Policy Adaptation for Networked Systems using Rollout," NOMS 2024-2024 IEEE/IFIP Network Operations and Management Symposium, 2024.
- Forough Shahab Samani, Hannes Larsson, Simon Damberg, Andreas Johnsson, Rolf Stadler, "Comparing Transfer Learning and Rollout for Policy Adaptation in a Changing Network Environment," NOMS 2024-2024 IEEE/IFIP Network Operations and Management Symposium, 2024.
- Laura Macià Coll, "Efficiently Learning the System Model for Microservice-based Applications," master thesis, KTH Royal Institute of Technology, (2024).
The last set of traces is related to an open-source application called "online boutique" (https://github.com/GoogleCloudPlatform/microservices-demo). This data set is collected by Maria Halvarsson. The data set is "Online_boutique_application.zip". These datasets are explained and used in Maria's thesis.
- Maria Halvarsson, "Learning End-to-End QoS Metrics for a Microservice Application," master thesis, KTH Royal Institute of Technology, (2024).