search
HomeTechnology peripheralsAIWu Riping analyzes Ericsson's AI practices and prepares for the new wave of 5G!

Last week, 3GPP ushered in an important milestone: at the 3GPP plenary meeting from December 11 to 15, the first version of 5G Advanced (referred to as "5G-A"), Rel-18, was announced Finish. At the same time, the meeting also approved the main scope of Rel-19 and determined the future direction of 5G-A. This marks the official arrival of the 5G-A era

Faced with the continuous evolution of 5G networks, Ericsson proposed the "Next Wave of 5G" development plan. The plan is based on excellent performance, green and low carbon, empowered growth and high degree of self-intelligence as its pillars, aiming to build an excellent value-driven network

2023 is a stage of vigorous development for the communications industry. On the one hand, our country continues to lead the development of the entire 5G industry and technology. On the other hand, we see that the global market is showing a hundred flowers blooming. At the "2023 Communications Industry Conference", Wu Riping, general manager of Ericsson China Network Product Solutions, pointed out that the sustainable development of communications networks has great potential. At the same time, with the emergence of more innovative technologies, telecom operators are putting forward higher requirements for sustainable development and network value realization. The "5G new wave" is Ericsson's answer when facing these challenges

Wu Riping analyzes Ericssons AI practices and prepares for the new wave of 5G!

The development potential of 5G is still very huge

According to the latest "Ericsson Mobile Market Report", by the end of 2023, the number of 5G subscription users is expected to reach 1.6 billion, accounting for nearly one-fifth of the total global mobile subscriptions. It is expected that the number of new 5G contracts will reach 610 million in 2023, an increase of 63% from 2022. Specifically, in the third quarter of 2023, China’s new contract signings reached 13 million, making it the fastest growing country

Wu Riping said that we realize that the sustainable development of the entire network has good potential. It is expected that the traffic generated by mobile phone users will increase to about three times between the end of 2023 and the end of 2029, while the mobile data traffic carried by 5G networks will increase from 25% at the end of 2023 to 76% in 2029. It can be said that 5G networks still have huge potential in terms of coverage and capacity development

He also mentioned the GSMA report and emphasized the impact on operators’ average revenue per user (ARPU) after the introduction of 5G in eight markets around the world. According to the report, six of the markets have reversed the downward trend of ARPU values ​​and showed positive growth. Even in the European market, where 5G development is slow, there are signs of significant improvement in ARPU values

The combination of communication networks and artificial intelligence is inevitable

Among the four pillars mentioned above, a high degree of self-intelligence means that Ericsson has successfully combined artificial intelligence (AI) with communication network technology. Wu Riping said that the industry has sufficient motivation to introduce AI, because both the network itself and the services and terminals carried on it are becoming more and more complex. There is no doubt that AI can improve efficiency. He emphasized that the combination of communication networks and AI is not a choice, but a necessity

Based on this, Ericsson began to work on combining artificial intelligence with networks in the early days, and divided its technology development into four stages: the first stage is rule-based automation, and all situations need to be taken into consideration when designing automation functions; The second stage is a self-intelligent network based on artificial intelligence/machine learning, which uses artificial intelligence/machine learning to predict and adapt to some unknown situations; the third stage is an intent-based cognitive network, which can express business needs more abstractly, not just It is just an implementation plan; the fourth stage is a zero-touch network, which is a native artificial intelligence network. The network can self-configure and self-optimize, and rarely requires manual intervention

Wu Riping analyzes Ericssons AI practices and prepares for the new wave of 5G!

Ericsson has made significant progress in commercial deployment and technology accumulation, and is developing towards the third stage of intent-based cognitive networks. Wu Riping particularly emphasized, “Our goal is not to use artificial intelligence for the sake of artificial intelligence, but to use artificial intelligence to improve the performance and experience of communication networks.” Ericsson believes that by choosing the most suitable network architecture, we can better utilize the benefits of artificial intelligence. ability

For optimal AI deployment, you need to choose the most appropriate architecture

In September 2023, GTI, together with China Mobile, Ericsson and other industry partners, jointly released the "GTI 5G Wireless Network Intelligent Technology Requirements White Paper", which proposed a three-layer architecture: cross-domain intelligence, network intelligence and network element intelligence. This is consistent with Ericsson’s concept of an architecture that combines centralized AI and distributed AI

Wu Riping explained: "AI in communication networks should have a layered architecture, that is, a combination of centralized AI and distributed AI. Depending on the characteristics, including whether the delay involves network-wide collaboration or single node optimization, etc. , choose the best node to implement AI, rather than forcibly doing all AI on a certain node." Among them, centralized AI involves network-level collaboration, and the decisions made are complex, but the frequency is low, and it is real-time. The requirements are low and manual access is required. Distributed AI involves node-level intelligence. The decisions made are simple, but the frequency is high. At the same time, the real-time requirements are high and need to be executed automatically

In order to deal with this problem, Ericsson developed a centralized artificial intelligence platform architecture based on EIAP/rAPP. This platform can provide powerful artificial intelligence support and has a completely open interface, which can be well integrated with the communication network. At the same time, Ericsson’s base station product series is continuously upgraded through the capabilities of the hardware platform (Silicon Core Technology) to enhance its support for distributed artificial intelligence

Ericsson AI network practical results refer to the results achieved in research and practice in the field of artificial intelligence. These achievements include the development of network applications based on artificial intelligence technology, optimization of network performance, improvement of network security and other innovations. By applying artificial intelligence technology to the network field, Ericsson has made significant breakthroughs and achievements, making important contributions to promoting the development and innovation of network technology

As a global enterprise based in China, Ericsson has always been committed to introducing the best and most advanced technologies to the Chinese market first, which also includes artificial intelligence solutions for communication networks

Wu Riping introduced the innovative practices of Ericsson and China Mobile in the Chinese market in his speech. They introduced intent-based AI multi-dimensional base station energy-saving optimization, adopted multi-dimensional joint optimization, high-speed closed-loop control (based on KPI intentions: such as energy-saving or performance-first control), and judged and predicted wireless scenarios based on data and machine learning. Based on the same power-saving function, Ericsson uses intent-driven AI base station energy-saving optimization to achieve an average energy-saving gain of 13.1% in performance-priority scenarios and an average energy-saving gain of 19.3% in energy-saving-priority scenarios

At the same time, Wu Riping pointed out that generative AI has good application scenarios in communication networks. He said: “In the future, we can see the application of generative AI in semantic communication, such as effectively extracting feature words, and the ability to simplify digital twin investment in digital twins, replacing a large amount of code development, both of which can achieve very good results. Good results." However, Wu Riping believes that the key points of the application of generative AI and other AI in communication networks are the same, that is, AI must be combined with communication expertise to produce the best results, which is what Ericsson has been doing Direction of efforts

In terms of global AI practice, Ericsson is conducting comprehensive development with data, algorithms and computing power as the core. In terms of data, as of early 2023, Ericsson's AI platform has processed more than 175 TB of network data every day. In terms of algorithms, Ericsson focuses on selecting suitable AI algorithms and combines its professional experience in communications to customize more than 200 AI applications for operators. In terms of computing power, Ericsson has established three ICT centers around the world to provide sufficient R&D computing power for model training

At the end of the speech, Wu Riping emphasized that in the face of the new wave of 5G, Ericsson will continue to be committed to introducing advanced technologies into China's networks, helping operators build better 5G networks, and sharing a beautiful digital future together

The above is the detailed content of Wu Riping analyzes Ericsson's AI practices and prepares for the new wave of 5G!. For more information, please follow other related articles on the PHP Chinese website!

Statement
This article is reproduced at:搜狐. If there is any infringement, please contact admin@php.cn delete
The Hidden Dangers Of AI Internal Deployment: Governance Gaps And Catastrophic RisksThe Hidden Dangers Of AI Internal Deployment: Governance Gaps And Catastrophic RisksApr 28, 2025 am 11:12 AM

The unchecked internal deployment of advanced AI systems poses significant risks, according to a new report from Apollo Research. This lack of oversight, prevalent among major AI firms, allows for potential catastrophic outcomes, ranging from uncont

Building The AI PolygraphBuilding The AI PolygraphApr 28, 2025 am 11:11 AM

Traditional lie detectors are outdated. Relying on the pointer connected by the wristband, a lie detector that prints out the subject's vital signs and physical reactions is not accurate in identifying lies. This is why lie detection results are not usually adopted by the court, although it has led to many innocent people being jailed. In contrast, artificial intelligence is a powerful data engine, and its working principle is to observe all aspects. This means that scientists can apply artificial intelligence to applications seeking truth through a variety of ways. One approach is to analyze the vital sign responses of the person being interrogated like a lie detector, but with a more detailed and precise comparative analysis. Another approach is to use linguistic markup to analyze what people actually say and use logic and reasoning. As the saying goes, one lie breeds another lie, and eventually

Is AI Cleared For Takeoff In The Aerospace Industry?Is AI Cleared For Takeoff In The Aerospace Industry?Apr 28, 2025 am 11:10 AM

The aerospace industry, a pioneer of innovation, is leveraging AI to tackle its most intricate challenges. Modern aviation's increasing complexity necessitates AI's automation and real-time intelligence capabilities for enhanced safety, reduced oper

Watching Beijing's Spring Robot RaceWatching Beijing's Spring Robot RaceApr 28, 2025 am 11:09 AM

The rapid development of robotics has brought us a fascinating case study. The N2 robot from Noetix weighs over 40 pounds and is 3 feet tall and is said to be able to backflip. Unitree's G1 robot weighs about twice the size of the N2 and is about 4 feet tall. There are also many smaller humanoid robots participating in the competition, and there is even a robot that is driven forward by a fan. Data interpretation The half marathon attracted more than 12,000 spectators, but only 21 humanoid robots participated. Although the government pointed out that the participating robots conducted "intensive training" before the competition, not all robots completed the entire competition. Champion - Tiangong Ult developed by Beijing Humanoid Robot Innovation Center

The Mirror Trap: AI Ethics And The Collapse Of Human ImaginationThe Mirror Trap: AI Ethics And The Collapse Of Human ImaginationApr 28, 2025 am 11:08 AM

Artificial intelligence, in its current form, isn't truly intelligent; it's adept at mimicking and refining existing data. We're not creating artificial intelligence, but rather artificial inference—machines that process information, while humans su

New Google Leak Reveals Handy Google Photos Feature UpdateNew Google Leak Reveals Handy Google Photos Feature UpdateApr 28, 2025 am 11:07 AM

A report found that an updated interface was hidden in the code for Google Photos Android version 7.26, and each time you view a photo, a row of newly detected face thumbnails are displayed at the bottom of the screen. The new facial thumbnails are missing name tags, so I suspect you need to click on them individually to see more information about each detected person. For now, this feature provides no information other than those people that Google Photos has found in your images. This feature is not available yet, so we don't know how Google will use it accurately. Google can use thumbnails to speed up finding more photos of selected people, or may be used for other purposes, such as selecting the individual to edit. Let's wait and see. As for now

Guide to Reinforcement Finetuning - Analytics VidhyaGuide to Reinforcement Finetuning - Analytics VidhyaApr 28, 2025 am 09:30 AM

Reinforcement finetuning has shaken up AI development by teaching models to adjust based on human feedback. It blends supervised learning foundations with reward-based updates to make them safer, more accurate, and genuinely help

Let's Dance: Structured Movement To Fine-Tune Our Human Neural NetsLet's Dance: Structured Movement To Fine-Tune Our Human Neural NetsApr 27, 2025 am 11:09 AM

Scientists have extensively studied human and simpler neural networks (like those in C. elegans) to understand their functionality. However, a crucial question arises: how do we adapt our own neural networks to work effectively alongside novel AI s

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

Video Face Swap

Video Face Swap

Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Tools

MantisBT

MantisBT

Mantis is an easy-to-deploy web-based defect tracking tool designed to aid in product defect tracking. It requires PHP, MySQL and a web server. Check out our demo and hosting services.

EditPlus Chinese cracked version

EditPlus Chinese cracked version

Small size, syntax highlighting, does not support code prompt function

SublimeText3 Chinese version

SublimeText3 Chinese version

Chinese version, very easy to use

ZendStudio 13.5.1 Mac

ZendStudio 13.5.1 Mac

Powerful PHP integrated development environment

SecLists

SecLists

SecLists is the ultimate security tester's companion. It is a collection of various types of lists that are frequently used during security assessments, all in one place. SecLists helps make security testing more efficient and productive by conveniently providing all the lists a security tester might need. List types include usernames, passwords, URLs, fuzzing payloads, sensitive data patterns, web shells, and more. The tester can simply pull this repository onto a new test machine and he will have access to every type of list he needs.