Press Releases 2024

SoftBank Corp. and Ericsson Japan K.K. successfully
demonstrate high-speed automatic optimization of
5G networks through external control of base stations

Network data can be acquired at 1-minute intervals, and traffic fluctuations can be detected
and optimized in less than 5 minutes

February 22, 2024
SoftBank Corp.
Ericsson Japan K.K.

SoftBank Corp. (“SoftBank”) and Ericsson Japan K.K. (“Ericsson Japan”) announced their success in demonstrating a capability that optimizes a network automatically at high speed (“High-speed Automatic Optimization Capability”) in the commercial environment of a 5G non-standalone (“5G NSA”) network by controlling a device (server) outside the base station that acquires network performance data at 1-minute intervals, and controlling traffic outside the base station based on the information. In the Proof of Concept (“PoC”) conducted so far, SoftBank and Ericsson Japan confirmed that a series of automated controls from traffic fluctuation detection to optimization can be implemented in less than 5 minutes. This is one cutting-edge example that represents a step toward realizing a next-generation network that is controlled from the outside, rather than internal control provided by conventional radio equipment.

Image of High-speed Automatic Optimization Capability
Image of High-speed Automatic Optimization Capability

Background and Challenges in Network Optimization

In places where many users gather, such as stadiums and major railway stations, sudden traffic demand called “burst traffic” is likely to occur. In such an environment, not only internal control using various functions equipped with conventional radio equipment but also traffic control for large and wide areas through external control functions are required. In addition, the time the conventional method takes to detect fluctuations in traffic represents another challenge.

About the High-speed Automatic Optimization Capability

In order to solve these challenges, SoftBank and Ericsson Japan implemented a mechanism that can acquire network performance data at one-minute intervals with a control unit outside the base station and detect traffic fluctuations, and built a High-speed Automatic Optimization Capability that automatically controls wireless parameters for the corresponding base station based on the acquired data, and automatically determines optimization measures to improve performance, including multiple frequencies and base stations.

Differences from conventional base station internal control

Conventional internal control of base stations installed in radio equipment enables faster optimization that takes into account the coverage area of the base station and adjacent areas, but the scope of traffic control is limited. With the High-speed Automatic Optimization Capability, however, it is possible to control traffic with larger fluctuations by making high-speed judgments based on a bird's-eye view using external equipment for the entire area in each cluster. It is therefore a very effective means for controlling abrupt traffic fluctuations in a short period of time, such as in the case of a large event.

Differences from conventional base station internal control

PoC outcomes

In September 2023, SoftBank and Ericsson conducted a PoC in a commercial environment of a stadium where a sports event took place, and confirmed the following results*1.

  • In an evaluation time of about 3 hours, automatic control of wireless parameters was performed a total of 29 times without human intervention in a fully-automated closed loop
  • Optimization of radio resources improved the user's perceived speed of 5G NSA by approximately 53% in downlink and by approximately 10% in uplink*2

In addition to the PoC at the stadium, in November 2023, SoftBank and Ericsson conducted evaluations in a commercial network environment at a dome stadium where a music event was held and at major railway stations in Tokyo, confirming that the High-speed Automatic Optimization Capability was effective even for various traffic patterns.

The role of each company

Ericsson Japan: Developing High-speed Automatic Optimization Capability
SoftBank: Study of use cases, trial evaluation in a commercial network environment

Future development

In the future, SoftBank will expand the application area of the High-speed Automatic Optimization Capability, use it at stadiums and event venues nationwide, and expand it as a use case for a 5G standalone (5G SA) network, with the aim of providing a more comfortable mobile network with no “packet drops” in 4G and 5G. In the future, SoftBank plans to build a next-generation network that takes into account cooperation with conventional networks, in addition to linkage with external systems and the introduction of RIC*3 using Artificial Intelligence (AI) and Machine Learning (ML).

About Ericsson Japan K.K.

Ericsson enables communications service providers and enterprises to capture the full value of connectivity. The company's portfolio spans the following business areas: Networks, Cloud Software and Services, Enterprise Wireless Solutions, Global Communications Platform, and Technologies and New Businesses. It is designed to help our customers go digital, increase efficiency and find new revenue streams. Ericsson's innovation investments have delivered the benefits of mobility and mobile broadband to billions of people globally. Ericsson's Cognitive Software has automated the design and optimization of the network and the company is working to further evolve its products. Ericsson stock is listed on Nasdaq Stockholm and on Nasdaq New York.

  1. *1
    The High-speed Automatic Optimization Capability was operated for base stations in a stadium to evaluate network performance, etc., mainly during a timeslot when an official professional baseball game was held.
  2. *2
    Evaluation based on data that was acquired on the wireless device side.
  3. *3
    Abbreviation for RAN Intelligent Controller, which is an advanced next-generation RAN controller that assumes the use of AI/ML.
  • SoftBank, the SoftBank name and logo are registered trademarks or trademarks of SoftBank Group Corp. in Japan and other countries.
  • Other company, product and service names in this press release are registered trademarks or trademarks of the respective companies.