NEC Corporation announced the development of a learning-based communications analysis technology for private radio communications networks, including local/private 5G networks (local 5G).
This technology ensures that the quality of communications is constantly sufficient, even without the assistance of a network specialist, 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.
In order to consistently enjoy the benefits of local 5G, such as high throughput, massive connectivity, and low latency, it is essential to avoid communications congestion and competition.
This cannot be achieved simply by installing local 5G equipment. In the commercial mobile networks operated by telecom carriers, when communications quality degrades, 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, the technology automatically tracks changes in usage conditions by learning without human intervention. 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 utilization.
NEC will develop this technology not only for local 5G, but also as a technology that facilitates the optimization of networks operated by a wide range of businesses, thereby contributing to the simplicity and quick realization of flexible and secure communications infrastructure.
1. Hierarchical communications analysis enables high-precision estimation in real-time
Conventionally, 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 taken time to analyze and 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.
The results of this study were presented at IEEE/IFIP Network Operations and Management Symposium (NOMS) 2020, held from April 20 to 24, 2020.
Part of this technology results from NEC’s joint research with Professor Akihiro Nakao of The University of Tokyo, Interfaculty Initiative in Information Studies.
About NEC Corporation
NEC Corporation is a leader in the integration of IT and network technologies that benefit businesses and people around the world. The NEC Group globally provides “Solutions for Society” that promote the safety, security, efficiency, and equality of society. Under the company’s corporate message of “Orchestrating a brighter world,” NEC aims to help solve a wide range of challenging issues and to create new social value for the changing world of tomorrow.