Towards the use of Unsupervised Causal Learning in Wireless Networks Operation
The current paradigm in Mobile Wireless Networks (MWNs) operation is being defied by the increasing importance of Machine Learning (ML) and Artificial Intelligence (AI). Nevertheless, another paradigm shift is rising with recent developments in causal inference and causal discovery, which, although...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S131915782300318X |
| _version_ | 1827763899433222144 |
|---|---|
| author | Marco Sousa Pedro Vieira Maria Paula Queluz António Rodrigues |
| author_facet | Marco Sousa Pedro Vieira Maria Paula Queluz António Rodrigues |
| author_sort | Marco Sousa |
| collection | DOAJ |
| description | The current paradigm in Mobile Wireless Networks (MWNs) operation is being defied by the increasing importance of Machine Learning (ML) and Artificial Intelligence (AI). Nevertheless, another paradigm shift is rising with recent developments in causal inference and causal discovery, which, although having the potential to be applied to MWNs, have been relatively unexplored. This paper aims to develop a data-driven methodology using unsupervised ML and Conditional Independence Tests (CITs), typically used in causal discovery tasks, to identify distinct network performance patterns and pinpoint causal factors to explain them. The proposed methodology was first evaluated with crowdsourcing data from User Equipments (UEs). Afterwards, a dataset from a Long-Term Evolution (LTE) network, composed of a set of arbitrary performance indicators and configuration parameters, was considered. The crowdsourcing dataset, containing multiple network speed tests, revealed that the measured uplink throughput contributed the most to the observed performance patterns due to the used Radio Access Technologies (RATs). Furthermore, the LTE dataset revealed a causal relationship between the number of reserved signalling resources in the Physical Uplink Control Channel (PUCCH) and the UE uplink throughput. Notwithstanding, the key contribution of this paper is the consideration of causal-based concepts and methods for network operations enhancement. |
| first_indexed | 2024-03-11T10:58:12Z |
| format | Article |
| id | doaj.art-65c9cbf01a1846e3bbcc67893d6de457 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-11T10:58:12Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-65c9cbf01a1846e3bbcc67893d6de4572023-11-13T04:09:01ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-10-01359101764Towards the use of Unsupervised Causal Learning in Wireless Networks OperationMarco Sousa0Pedro Vieira1Maria Paula Queluz2António Rodrigues3Instituto de Telecomunicações, Av.Rovisco Pais, 1, Lisbon 1049-001, Portugal; Instituto Superior Técnico, Av.Rovisco Pais, 1, Lisbon 1049-001, Portugal; Celfinet - A Cyient Company, R. João Chagas 53, Lisbon 1495-072, Portugal; Corresponding author.Instituto de Telecomunicações, Av.Rovisco Pais, 1, Lisbon 1049-001, Portugal; Instituto Superior de Engenharia de Lisboa, R. Conselheiro Emídio Navarro 1, Lisbon 1959-007, PortugalInstituto de Telecomunicações, Av.Rovisco Pais, 1, Lisbon 1049-001, Portugal; Instituto Superior Técnico, Av.Rovisco Pais, 1, Lisbon 1049-001, PortugalInstituto de Telecomunicações, Av.Rovisco Pais, 1, Lisbon 1049-001, Portugal; Instituto Superior Técnico, Av.Rovisco Pais, 1, Lisbon 1049-001, PortugalThe current paradigm in Mobile Wireless Networks (MWNs) operation is being defied by the increasing importance of Machine Learning (ML) and Artificial Intelligence (AI). Nevertheless, another paradigm shift is rising with recent developments in causal inference and causal discovery, which, although having the potential to be applied to MWNs, have been relatively unexplored. This paper aims to develop a data-driven methodology using unsupervised ML and Conditional Independence Tests (CITs), typically used in causal discovery tasks, to identify distinct network performance patterns and pinpoint causal factors to explain them. The proposed methodology was first evaluated with crowdsourcing data from User Equipments (UEs). Afterwards, a dataset from a Long-Term Evolution (LTE) network, composed of a set of arbitrary performance indicators and configuration parameters, was considered. The crowdsourcing dataset, containing multiple network speed tests, revealed that the measured uplink throughput contributed the most to the observed performance patterns due to the used Radio Access Technologies (RATs). Furthermore, the LTE dataset revealed a causal relationship between the number of reserved signalling resources in the Physical Uplink Control Channel (PUCCH) and the UE uplink throughput. Notwithstanding, the key contribution of this paper is the consideration of causal-based concepts and methods for network operations enhancement.http://www.sciencedirect.com/science/article/pii/S131915782300318XWireless networksArtificial intelligenceUnsupervised learningCausal inferenceRoot cause analysisPerformance management |
| spellingShingle | Marco Sousa Pedro Vieira Maria Paula Queluz António Rodrigues Towards the use of Unsupervised Causal Learning in Wireless Networks Operation Journal of King Saud University: Computer and Information Sciences Wireless networks Artificial intelligence Unsupervised learning Causal inference Root cause analysis Performance management |
| title | Towards the use of Unsupervised Causal Learning in Wireless Networks Operation |
| title_full | Towards the use of Unsupervised Causal Learning in Wireless Networks Operation |
| title_fullStr | Towards the use of Unsupervised Causal Learning in Wireless Networks Operation |
| title_full_unstemmed | Towards the use of Unsupervised Causal Learning in Wireless Networks Operation |
| title_short | Towards the use of Unsupervised Causal Learning in Wireless Networks Operation |
| title_sort | towards the use of unsupervised causal learning in wireless networks operation |
| topic | Wireless networks Artificial intelligence Unsupervised learning Causal inference Root cause analysis Performance management |
| url | http://www.sciencedirect.com/science/article/pii/S131915782300318X |
| work_keys_str_mv | AT marcosousa towardstheuseofunsupervisedcausallearninginwirelessnetworksoperation AT pedrovieira towardstheuseofunsupervisedcausallearninginwirelessnetworksoperation AT mariapaulaqueluz towardstheuseofunsupervisedcausallearninginwirelessnetworksoperation AT antoniorodrigues towardstheuseofunsupervisedcausallearninginwirelessnetworksoperation |