European Commission logo
English English
CORDIS - EU research results
CORDIS

Characterization and prediction of service-level traffic for future sliced mobile network

Periodic Reporting for period 1 - CORRELATION (Characterization and prediction of service-level traffic for future sliced mobile network)

Reporting period: 2020-02-01 to 2022-01-31

This project focuses on characterization and prediction of the service-level mobile network traffic.

The technical objectives of this project are: 1) to depict the spatial-temporal characteristics of individual services, especially for the dominating services in 5G mobile networks, at multi-scales; 2) to design appropriate predicting methods for individual services based on their spatial-temporal characteristics; 3) to reveal the hidden correlations of traffic patterns among diverse services; and 4) to improve the prediction accuracy for service-level traffic based on inter-service correlations and investigate whether we can forecast diverse services’ traffic via the historical records of only a few key services.

The achievement of the above objectives will influence the architecture design of future mobile networks and revolutionize how operators will tailor the network slices dynamically.

The project is timely. 1) Network slicing is an important trend of future mobile networks and the orchestration of network slices is highly depended on the fluctuations of individual services; 2) Characterization and prediction for service-level mobile traffic with BDA techniques is still a nascent research field; 3) With current prosperity of artificial intelligence, the emerging machine learning tools are offering brand-new opportunities for service-level mobile traffic analysis and forecast.
During the period of the project (from 01/02/2020 to 31/01/2022), the work packages (WPs) have been implemented completely and the corresponding technical objects of the project have been achieved. The work performed and the results obtained so far are summarized as follows:

For WP1, we have investigated the spatial-temporal characteristics of traffic patterns generated by some representative mobile network services. We have analysed the auto-correlations and the spatial correlations of each individual mobile network service. Based on the service-level traffic pattern characteristics, we have designed prediction frameworks to forecast the future traffic loads of different mobile network services using the services' own previous traffic loads.

For WP2, we have investigated the traffic correlations among different mobile network services. We have analysed the conditional entropy of future traffic load distribution of each certain mobile network service when previous traffic loads of the other mobile network services are given. We have proven that the inter-service traffic correlations indeed exist and that the future traffic loads of the instant message services are highly influenced by the historical load distributions of the short message traffic generated in a target cell's adjacent cells. We have investigated how the mobile network subscribers will influence the traffic distributions of different mobile network services.

For WP3, based on the inter-service traffic correlations we found, we have proposed novel service-level traffic predicting frameworks, each of which can provide precise prediction results for the future traffic loads generated by a certain mobile network service based on the historical traffic loads generated by this mobile network service and some other mobile network services. We have investigated whether we can help the prediction model of a target traffic prediction task related to a certain mobile network service improve the prediction accuracy and learning efficiency by utilizing the experience of existing traffic prediction tasks related to diverse mobile network services. We have proposed a deep meta-learning based mobile network traffic prediction framework that provides the proper hyper-parameter and initial weight vector for the prediction model of a new prediction task based on the traffic pattern's characteristics in the frequency domain. Our experimental results demonstrated that with meta-learning, our framework can enormously elevate the performance of prediction models of various mobile network traffic prediction tasks.

We have created a website, which is regularly maintained and updated, to constitute the main public source of information about the research, dissemination, and outreach activities. We have published in high-impact scientific journals and international conferences, such as IEEE Wireless Communications, IEEE Wireless Communications Letters, IEEE GLOBECOM, and IEEE NOMS, to report our achievements about this project. Ranplan has facilitated participation at high-impact industrial events such as Mobile World Congress for industrial dissemination and creating business from the project. For the exploitation of the research results of this project, the service-level traffic prediction frameworks are being integrated into Ranplan’s data analytics tools and marketed by Ranplan. Futhermore, from the new knowledge and results gained within the project, Ranplan, the University of Cambridge, and the Alan Turing Institute have offered consulting and training services in mobile network traffic characterization and prediction to the corresponding network engineers.
To the best of our knowledge, this project is the first to investigate the traffic correlations among different mobile network services and analyse the service usage profiles related to different well-defined user groups at different scales. Also, we think this project is the first to propose the service-level traffic predicting frameworks, each of which can provide precise prediction results for the future traffic loads generated by a certain mobile network service based on the correlations among different mobile network services.

The innovative ideas and technologies of the project have the potential to transform the structure as well as resource allocation and deployment for future mobile networks. (1) The project results will help operators reserve appropriate resources for services in advance, which will greatly improve user experience and network’s stability. (2) CORRELATION will contribute to the optimal orchestration of physical infrastructure like energy savings, opportunistic scheduling, and network anomaly detection. Thus, mobile networks’ performance could be further improved. (3) The project will promote inter-disciplinary research and create a wealth of research opportunities that involve a huge number of professionals in many specialties. (4) The project has trained some promising researchers and engineers in Europe by providing excellent collaboration opportunities with the experienced researchers. (5) The project has created new jobs, for example, hardware engineer for computing platform establish, software developers for BDA environment, and researchers focused on mobile network optimization with service-level traffic knowledge. (6) The public, businesses and organizations will benefit from intelligent sliced mobile networks and hassle-free provisioning of such networks.
The proposed meta-learning based mobile network traffic prediction framework
Spatial-temporal characteristic analyses for service-level traffic patterns
Analyses of traffic correlations among different mobile network services