
Share
A large-scale deployment of an AI-driven energy-saving solution in Uzbekistan's telecom network showcases how advanced analytics can reduce carbon emissions without sacrificing user experience.
ZTE and Ucell, one of Uzbekistan’s largest mobile operators, have completed the full commercial rollout of ZTE’s RAN (Radio Access Network) AI-powered energy-saving solution across Ucell’s extensive network. This deployment marks a significant step forward in Ucell's commitment to sustainable and energy-efficient telecommunications infrastructure.
The AI-powered energy-saving solution leverages advanced artificial intelligence analytics to dynamically optimize network energy consumption based on real-time traffic patterns. By enabling per-site, per-cell intelligent energy-saving strategies, the system automatically activates energy-saving modes during low-traffic periods while ensuring seamless service continuity and a high-quality user experience.
A key achievement of this deployment is a measurable improvement in network energy efficiency. The solution has increased the energy efficiency ratio-defined as the volume of data traffic delivered per kilowatt-hour (GB/kWh)-by 10.6% across the network. This means that for every unit of electricity consumed, the network now delivers 10.6% more data, directly contributing to lower carbon emissions and reduced operational costs.
The AI-powered energy-saving solution employs a distributed computing architecture with dual-layer intelligence:
It implements multi-dimensional energy-saving techniques, including:
These strategies are autonomously configured and continuously optimized through machine learning, ensuring an optimal balance between energy savings and network performance.
To safeguard user experience, the system conducts real-time monitoring before, during, and after energy-saving actions. It evaluates KPIs (Key Performance Indicators) and automatically exits energy-saving mode if any performance thresholds are exceeded, achieving a balanced approach to energy efficiency and network performance.

Mr. Wang Guangdong, CEO of ZTE Uzbekistan, said, "We are proud to support Ucell in this landmark green network transformation. The 10.6% improvement in energy efficiency ratio demonstrates that AI-driven intelligence can deliver both environmental and economic value without compromising user experience. This deployment sets a strong example for sustainable telecom operations in Central Asia and beyond."
Mr. Andrey Shishkovsky, CEO of Ucell, commented, "At Ucell, digital transformation and environmental responsibility are at the forefront of our strategy. This AI-powered energy-saving solution not only helps us reduce operational costs but also aligns with our commitment to sustainability."
The distributed computing architecture of the AI-powered energy-saving solution is designed to handle the complexity of a large-scale network efficiently:
The system's multi-dimensional energy-saving techniques are implemented through a combination of software-defined networking (SDN) and machine learning algorithms. SDN allows for flexible control over the network infrastructure, while machine learning ensures that energy-saving actions are dynamically adjusted based on current traffic demands.
This deployment by ZTE and Ucell sets a precedent for how AI can be leveraged to create more sustainable and efficient telecommunications networks, offering valuable insights for other operators looking to adopt similar solutions.
Tags
Original Sources
Ucell and ZTE complete large-scale deployment of AI‑Powered green network solution in Uzbekistan
↗ https://www.theregister.com/networks/2026/05/26/ucell-and-zte-complete-large-scale-deployment-of-aipowered-green-network-solution-in-uzbekistan/5246097
About the author
Kai built ML infrastructure at a Bay Area startup before developing an obsession with transformer architectures and inference optimisation that eventually pulled him out of product work entirely. A stint at a compute research lab sharpened his instinct for what actually matters in a model release versus what is marketing. He writes from the inside — from the perspective of someone who has debugged the systems he is describing at three in the morning. He is allergic to hype and instinctively drawn to the unglamorous plumbing questions that everyone else skips over.
More from The Engineer →This Week's Edition
3 June 2026
133 articles
Related Articles

Smarter Engagement for Stronger Growth: How Payers Can Leverage AI to Do More with Less
Products & Applications · 3 min

Penn Medicine and K Health Deploy AI Clinical Agents to Enhance Patient Care
Products & Applications · 3 min

Wheel and b.well Partner to Build Turnkey AI-First Virtual Care Infrastructure
Products & Applications · 3 min
Related Articles

Smarter Engagement for Stronger Growth: How Payers Can Leverage AI to Do More with Less
Products & Applications · 3 min

Penn Medicine and K Health Deploy AI Clinical Agents to Enhance Patient Care
Products & Applications · 3 min

Wheel and b.well Partner to Build Turnkey AI-First Virtual Care Infrastructure
Products & Applications · 3 min
More Stories