Content and Context based Adaptation in Mobile Networks – CANCAN

The Methodology of the project follows three steps:
1- Data collection. First novel high-detail datasets of contextualized user mobility and mobile service usage traffic data records (xDR) are collected. These datasets are obtained by leveraging passive probes deployed in the mobile network. These data sources have different levels of spatiotemporal accuracy. Once properly anonymized they will be made available for further study within the project.
2- Data analytics. Second, current cutting-edge state of the art methods of data analytics are leveraged and tailored to better characterize mobile network usage. This will lead to the understanding of the spatiotemporal trends and behaviors from the past and to the mobile service forecasting to anticipate spatiotemporal events and behaviors.
3- Algorithms for dynamic orchestration of the network. 5G network orchestration solutions will be enriched with dynamic or adaptive algorithms derived from the lessons learnt from the previous mobile network usage analyses. Virtualized mobile network resources, Mobile edge computing design and core network differentiated services management will be used to benchmark the performance benefits of the new orchestration methods.

Project CANCAN delivered in the first 18 months the following results:
- Successful data collection from a mobile operator at large scale: this dataset characterizes the mobile traffic and application usage. It covers a 3-month period and the whole national territory of France. The rules established by the GDPR and national telecom code of conduct have been followed. The data have now been erased but anonymized aggregates are available to the partners for further analyses.
- First studies have served to characterize user mobility, as well as to detect and predict anomalies in the mobile network, based on the analysis of recurring behaviours at application level.
- Data-driven algorithms based on deep neural network architectures have been designed to (i) classify service-level traffic from aggregates, (ii) solve the problem of preemptive resource allocation of dedicated network slices, and (iii) support anomaly detection in softwarized infrastructures leveraging on logs of an NFV/MEC infrastructure.. These techniques jointly ensure an automated and dependable orchestration of mobile network resources that adapts to the user demands.

The next steps involve additional data analysis studies, in particular with evaluation of predictive algorithms, as well as on-line detection methods.
Dynamic orchestration algorithms will be further developed and will be applied to virtualized mobile network resources management, Mobile edge computing strategies and core network differentiated services management.

The project has already published 10 papers (including 5 which are joint publications of partners in the project). Some of the publications appear in major conferences of the field (Infocom, Mobicom) and in leading IEEE journals (TNSM, JSAC).

Mobile telecommunication networks and services are complex systems that are today planned and dimensioned by expert engineers in a static fashion, based on a limited set of local measurements and long-term statistics. In practice, however, the whole milieu is far from static, as subscribers are mobile by definition, and their communication activity patterns are strongly time-varying and location-dependent. In addition, the user traffic is increasingly generated by services that entail very different offered loads and requirements.
The strong contextual and content heterogeneity that characterizes the mobile traffic demand makes the sheer increase of capacity an inefficient strategy towards next-generation mobile networks. The capacity growth must be coupled with a much more efficient usage of the resources: next-generation mobile networks are expected to be flexible enough to adapt themselves to spatiotemporal variations and content diversity, and to do so in a timely and automated manner. This results in so-called cognitive mobile networks. These networks will run big data analytics on traffic measurements from in-network monitoring probes, so as to extract important knowledge about the current status of the system. This knowledge will then become a fundamental input for automatic network functions to engineer traffic and allocate resources in concertation with the needs of end users.
This vision primarily builds on the effective orchestration of network resources and services across all network levels. There is thus an ongoing substantial effort to define architectures for dynamic resource allocation, which all include orchestrator components in charge of taking automated decisions about resource reconfiguration. However, the dynamic resource management algorithms and policies that will run inside network orchestrators are to be entirely investigated and defined.
Designing orchestrator policies and algorithms entails a number of scientific and technological challenges: (i) Which data analytics shall drive cognitive networks? (ii) How to ensure scalable and real-time orchestration? (iii) How to integrate analytics into current virtualized network architectures? and (iv) Which are the gains of cognitive management?
To address the challenges, the CANCAN project targets the following objectives:
1) Collecting novel measurement datasets that describe mobile network data traffic at unprecedented spatial and temporal accuracy levels, and for different mobile services separately. The datasets will be gathered in an operational nationwide network.
2) Evaluating existing analytics for classification, prediction and anomaly detection within real-world high-detail per-service mobile network data, and tailoring them to the specifications of the management of resources at different network levels.
3) Demonstrating the integration of data analytics within next-generation cognitive network architectures in three practical case studies, i.e., (i) predictive and differentiated radio scheduling in virtualized Radio Access Network (vRAN), (ii) dynamic management of virtual machines and containers in Mobile Edge Computing (MEC), and (iii) dynamic Service Level Agreements and Class of Service generation for resource sharing and bottleneck mitigation. The integration will build on recent advances in architectures that enable Network Functions Virtualization.
The CANCAN project brings together four partners: the networking and artificial intelligence teams of Thales Communications & Security (Thales) the Agora team of the Inria Rhone-Alpes center (Inria), the Computer Science laboratory (LIP6) of the Sorbonne University, and the SENSE department of Orange Labs (Orange). The consortium will leverage its expertise in mobile networks (Thales, Inria, LIP6), network data analytics (Thales, Inria, LIP6, Orange) and sociology (Orange) to achieve its proposed objectives.