Use Case Intelligence RSS Search use cases Search
Ericsson Telecommunications United States Company newsroom

T-Mobile

IT Operations Automation

T-Mobile needed to improve radio access network performance under rapidly changing radio conditions and high-demand usage so it could raise spectral efficiency, increase downlink throughput, and deliver a more consistent customer experience at scale.

Read the original story Explore all use cases
close to 10 percent increase in spectral efficiency
up to 15 percent boost in downlink throughput

Reported impact

Business outcome

The live commercial trials delivered higher spectral efficiency, increased downlink throughput, and a more consistent customer experience, including smoother streaming, more responsive gaming, and uninterrupted video calls during peak usage.

  • Customer Experience
  • Scalability

Solution

T-Mobile and Ericsson moved Ericsson's AI-native Scheduler with Link Adaptation into large-scale commercial trials on live 5G Advanced network traffic. In this implementation, live radio conditions and network traffic behavior from the RAN are evaluated by a neural network embedded directly in the scheduler software and executed on Ericsson TCO-optimized hardware. Rather than relying on legacy rule-based methods, the AI model predicts rapidly changing radio conditions in real time and adjusts link adaptation and scheduling decisions inside the live network path. The optimized decisions are then applied immediately to T-Mobile's commercial downlink traffic, improving spectral efficiency and throughput for subscribers. The source does not describe a separate storage layer, external orchestration platform, or third-party integrations; the AI capability is presented as an embedded RAN software function tightly coupled to Ericsson hardware in the production network environment.

Data flow

Live 5G Advanced network traffic and radio-condition signals in T-Mobile's RAN feed Ericsson's AI-native Scheduler with Link Adaptation, whose neural network runs on Ericsson TCO-optimized hardware to predict near-real-time radio conditions. The software then updates scheduling and link adaptation decisions on the downlink path, and those optimized decisions are served directly to subscribers on the commercial network.

Solution architecture

2 components · 1 layer
  1. Compute
    • AI-native Scheduler with Link Adaptation AI-driven RAN software that predicts radio conditions in real time and adjusts scheduling and link adaptation on live 5G Advanced traffic.
    • Ericsson TCO-optimized hardware Hardware platform that runs the neural network directly in the live RAN environment.

Architecture clues

  • AI capability is embedded directly in RAN software.
  • Deployed in large-scale commercial trials on live 5G Advanced network traffic.
  • Neural network runs directly on Ericsson TCO-optimized hardware.
  • Performance was measured against legacy rule-based methods.

Evidence from the source

"Customers experience smoother streaming, more responsive gaming, and uninterrupted video calls even during peak usage."
"During trials with T-Mobile, the AI-native Scheduler with Link Adaptation feature achieved close to 10 percent increase in spectral efficiency and up to 15 percent boost in downlink throughput compared to legacy rule-based methods."
"This innovative software uses a neural network – running directly on the Ericsson TCO-optimized hardware – to predict rapidly changing radio conditions in real time, improving spectral efficiency and boosting downlink data rates to deliver a more consistent customer experience."
Transparency Evidence & methodology 80/100 reference value · 84% confidence · 2 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value80/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence84%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability19/25
    9 of 12 key fields link to a named source.
  • Direct evidence15/20
    3 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency10/10
    2 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Ericsson

    T-Mobile 5G Advanced network achieves world first with Ericsson AI RAN innovation

    First-party
    https://www.ericsson.com/en/press-releases/6/2026/t-mobile-ericsson-ai-ran
    Source type
    Vendor-published customer story
    Published
    May 12, 2026
    Supports
    • Customer
    • Region
    • Business problem
    • Solution
    • Products
    • Business outcome
    • Metrics
    • Architecture
    • Publication date
  2. LinkedIn

    T-Mobile | LinkedIn

    Independent secondary
    https://www.linkedin.com/company/t-mobile/

    The company page lists 95,702 associated employees and a 10,001+ employee size band.

    Source type
    Structured company profile
    Supports
    • Company size

Date evidence

  • Published on source page May 12, 2026 · T-Mobile · First-party
    Open date source
Not separately sourced Industry. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Google Cloud Modified · Oct 8, 2026 Ericsson Telecommunications Sweden Telecom operators today face a rapid influx of artificial intelligence, orchestration, and automation tools. But converting these technologies into real business value is a constant challenge. To prove the business case… Accelerates and lowers the cost of launching new network services IT Operations Automation Gemini platform Google Cloud Archived · Oct 2, 2026 Nokia Telecommunications Finland Today's telecom networks generate massive volumes of complex data. Traditionally, managing this has been a highly manual process, with operators spending hours digging through minor alert logs to find the root cause of… Slashes troubleshooting times by 50% to 80%, resolving complex network issues in minutes instead of hours IT Operations Automation Agent Development Kit (ADK) · Cloud Storage · Gemini Enterprise IBM Sep 25, 2026 Vodafone Idea Telecommunications India Vodafone Idea needed to embed generative AI across software delivery at scale while maintaining governance, protecting sensitive engineering data under sovereignty requirements, and reducing duplicated effort across… 120+ AI assistants embedded across the SDLC IT Operations Automation IBM Consulting Advantage