Covering Disruptive Technology Powering Business in The Digital Age

Home > DTA news > News > NEC Develops Learning-based Communications Analysis Technology Without Network Specialists that Enables High Quality Local 5G
NEC Develops Learning-based Communications Analysis Technology Without Network Specialists that Enables High Quality Local 5G
May 14, 2020 News


NEC Corporation announced the development of a learning-based communications analysis technology for private radio communications networks, including local/private 5G networks (local 5G).

Without the assistance of a network specialist, this technology ensures that the quality of communications is constantly sufficient, avoiding quality degradation caused by congestion and competition.

Companies and local governments are considering the introduction of local 5G as a private radio communications network that can be used individually according to their needs.

It is essential to avoid communications congestion and competition to consistently enjoy the benefits of local 5G, such as high throughput, massive connectivity, and low latency.

This cannot be achieved simply by installing local 5G equipment. When communications quality degrades in the commercial mobile networks operated by telecom carriers, network specialists spend considerable time to adjust the priorities and data rate of communications based on the analysis of communication conditions. However, such analysis and operation is difficult in private mobile networks without such experts.

NEC has developed a technology that offers real-time analysis through artificial intelligence that matches the analytical know-how of trained specialists. This technology facilitates optimal operation of networks that fully demonstrates the capabilities of their performance. The technology achieves this by reliably estimating the amount of communications in real-time by communication type, such as video, still image, and text data, based on the features of the current communications traffic.

In addition, by learning without human intervention, the technology automatically tracks changes in usage conditions. As a result, even users who do not have network expertise can operate a large number of various devices and applications through local 5G with high performance and stable utilisation.

NEC will not only develop this technology for local 5G, but also as a technology that facilitates the optimisation of networks operated by a wide range of businesses, thereby contributing to the simplicity and quick realisation of flexible and secure communications infrastructure.

Technology Features:

  1. Hierarchical communications analysis enables high-precision estimation in real-time
    Conventionally, time taken to analyse with the variations in communications traffic caused by a mixture of application types, such as video, still image, and text data, and the effects of wireless communications, have made the results less accurate.

    This new technology uses hierarchical clustering to first identify the wireless communications among the current communications traffic and to then identify the application types.

    This has resulted in highly accurate estimations of communications in real-time.

  2. Learn autonomously and track changes in usage conditions automatically
    The method for learning beforehand requires enormous amounts of training data every time there is a change in the installation environment and the use situation of communications. This new method is based on unsupervised learning. The technology automatically updates model parameters based on the similarity between the past and the most recent model, allowing changes in usage conditions to be tracked.