Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps
Significant in lifestyle have reshaped the Internet landscape, resulting in notable shifts in both the magnitude of Internet traffic and the diversity of apps utilized. The increased adoption of communication-and-collaboration apps, also fueled by lockdowns in the COVID pandemic years, has heavily i...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10438860/ |
| _version_ | 1797272691803160576 |
|---|---|
| author | Idio Guarino Giuseppe Aceto Domenico Ciuonzo Antonio Montieri Valerio Persico Antonio Pescape |
| author_facet | Idio Guarino Giuseppe Aceto Domenico Ciuonzo Antonio Montieri Valerio Persico Antonio Pescape |
| author_sort | Idio Guarino |
| collection | DOAJ |
| description | Significant in lifestyle have reshaped the Internet landscape, resulting in notable shifts in both the magnitude of Internet traffic and the diversity of apps utilized. The increased adoption of communication-and-collaboration apps, also fueled by lockdowns in the COVID pandemic years, has heavily impacted the management of network infrastructures and their traffic. A notable characteristic of these apps is their multi-activity nature, e.g., they can be used for chat and (interactive) audio/video in the same usage session: predicting and managing the traffic they generate is an important but especially challenging task. In this study, we focus on real data from four popular apps belonging to the aforementioned category: <monospace>Skype</monospace>, <monospace>Teams</monospace>, <monospace>Webex</monospace>, and <monospace>Zoom</monospace>. First, we collect traffic data from these apps, reliably label it with both the app and the specific user activity and analyze it from the perspective of traffic prediction. Second, we design data-driven models to predict this traffic at the finest granularity (i.e., at packet level) employing four advanced multitask deep learning architectures and investigating three different training strategies. The trade-off between performance and complexity is explored as well. We publish the dataset and release our code as open source to foster the replicability of our analysis. Third, we leverage the packet-level prediction approach to perform aggregate prediction at different timescales. Fourth, our study pioneers the trustworthiness analysis of these predictors via the application of eXplainable Artificial Intelligence to <inline-formula> <tex-math notation="LaTeX">$(a)$ </tex-math></inline-formula> interpret their forecasting results and <inline-formula> <tex-math notation="LaTeX">$(b)$ </tex-math></inline-formula> evaluate their reliability, highlighting the relative importance of different parts of observed traffic and thus offering insights for future analyses and applications. The insights gained from the analysis provided with this work have implications for various network management tasks, including monitoring, planning, resource allocation, and enforcing security policies. |
| first_indexed | 2024-03-07T14:32:01Z |
| format | Article |
| id | doaj.art-7010931810824407a693ed5a8da0778e |
| institution | Directory Open Access Journal |
| issn | 2644-125X |
| language | English |
| last_indexed | 2024-03-07T14:32:01Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj.art-7010931810824407a693ed5a8da0778e2024-03-06T00:01:36ZengIEEEIEEE Open Journal of the Communications Society2644-125X2024-01-0151299132410.1109/OJCOMS.2024.336684910438860Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile AppsIdio Guarino0https://orcid.org/0009-0002-6141-0188Giuseppe Aceto1https://orcid.org/0000-0002-4445-6259Domenico Ciuonzo2https://orcid.org/0000-0002-6230-2958Antonio Montieri3https://orcid.org/0000-0003-4340-442XValerio Persico4https://orcid.org/0000-0002-7477-1452Antonio Pescape5https://orcid.org/0000-0002-0221-7444Department of Electrical Engineering and Information Technologies, University of Napoli “Federico II,”, Naples, ItalyDepartment of Electrical Engineering and Information Technologies, University of Napoli “Federico II,”, Naples, ItalyDepartment of Electrical Engineering and Information Technologies, University of Napoli “Federico II,”, Naples, ItalyDepartment of Electrical Engineering and Information Technologies, University of Napoli “Federico II,”, Naples, ItalyDepartment of Electrical Engineering and Information Technologies, University of Napoli “Federico II,”, Naples, ItalyDepartment of Electrical Engineering and Information Technologies, University of Napoli “Federico II,”, Naples, ItalySignificant in lifestyle have reshaped the Internet landscape, resulting in notable shifts in both the magnitude of Internet traffic and the diversity of apps utilized. The increased adoption of communication-and-collaboration apps, also fueled by lockdowns in the COVID pandemic years, has heavily impacted the management of network infrastructures and their traffic. A notable characteristic of these apps is their multi-activity nature, e.g., they can be used for chat and (interactive) audio/video in the same usage session: predicting and managing the traffic they generate is an important but especially challenging task. In this study, we focus on real data from four popular apps belonging to the aforementioned category: <monospace>Skype</monospace>, <monospace>Teams</monospace>, <monospace>Webex</monospace>, and <monospace>Zoom</monospace>. First, we collect traffic data from these apps, reliably label it with both the app and the specific user activity and analyze it from the perspective of traffic prediction. Second, we design data-driven models to predict this traffic at the finest granularity (i.e., at packet level) employing four advanced multitask deep learning architectures and investigating three different training strategies. The trade-off between performance and complexity is explored as well. We publish the dataset and release our code as open source to foster the replicability of our analysis. Third, we leverage the packet-level prediction approach to perform aggregate prediction at different timescales. Fourth, our study pioneers the trustworthiness analysis of these predictors via the application of eXplainable Artificial Intelligence to <inline-formula> <tex-math notation="LaTeX">$(a)$ </tex-math></inline-formula> interpret their forecasting results and <inline-formula> <tex-math notation="LaTeX">$(b)$ </tex-math></inline-formula> evaluate their reliability, highlighting the relative importance of different parts of observed traffic and thus offering insights for future analyses and applications. The insights gained from the analysis provided with this work have implications for various network management tasks, including monitoring, planning, resource allocation, and enforcing security policies.https://ieeexplore.ieee.org/document/10438860/Communication appscollaboration appsCOVIDdeep learningencrypted trafficmultitask approaches |
| spellingShingle | Idio Guarino Giuseppe Aceto Domenico Ciuonzo Antonio Montieri Valerio Persico Antonio Pescape Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps IEEE Open Journal of the Communications Society Communication apps collaboration apps COVID deep learning encrypted traffic multitask approaches |
| title | Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps |
| title_full | Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps |
| title_fullStr | Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps |
| title_full_unstemmed | Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps |
| title_short | Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps |
| title_sort | explainable deep learning approaches for packet level traffic prediction of collaboration and communication mobile apps |
| topic | Communication apps collaboration apps COVID deep learning encrypted traffic multitask approaches |
| url | https://ieeexplore.ieee.org/document/10438860/ |
| work_keys_str_mv | AT idioguarino explainabledeeplearningapproachesforpacketleveltrafficpredictionofcollaborationandcommunicationmobileapps AT giuseppeaceto explainabledeeplearningapproachesforpacketleveltrafficpredictionofcollaborationandcommunicationmobileapps AT domenicociuonzo explainabledeeplearningapproachesforpacketleveltrafficpredictionofcollaborationandcommunicationmobileapps AT antoniomontieri explainabledeeplearningapproachesforpacketleveltrafficpredictionofcollaborationandcommunicationmobileapps AT valeriopersico explainabledeeplearningapproachesforpacketleveltrafficpredictionofcollaborationandcommunicationmobileapps AT antoniopescape explainabledeeplearningapproachesforpacketleveltrafficpredictionofcollaborationandcommunicationmobileapps |