en.Wedoany.com Reported - Recently, Uzbekistan mobile operator Ucell and China's ZTE Corporation completed the full-network commercial deployment of a RAN AI energy-saving solution. The solution covers Ucell's existing mobile network in Uzbekistan, utilizing real-time traffic prediction, base station-level intelligent execution, and multi-layer energy-saving strategies to improve network data energy efficiency by 10.6%, providing a new case for low-carbon telecom network operations in Central Asia.
The energy consumption pressure on mobile communication networks is continuously rising with data traffic growth. For operators, energy saving cannot simply rely on shutting down equipment or reducing network capacity, as user experience, coverage quality, service continuity, and key indicator stability must all be simultaneously ensured. The solution deployed by Ucell this time pushes energy-saving control down to the radio access network level, using network-level AI for traffic prediction and strategy orchestration, with base station-level AI executing real-time monitoring and action adjustments. The system can automatically select symbol-level, channel-level, carrier-level, and equipment-level energy-saving methods based on traffic load changes in different time periods, areas, and cells, reducing energy consumption during low-traffic periods and exiting energy-saving mode when service demand recovers or indicator thresholds are triggered, avoiding impacts on communication quality due to power saving.
The 10.6% improvement in data energy efficiency means that Ucell's network can carry more data traffic for the same amount of electricity consumed.
This type of deployment reflects that communication network energy saving is shifting from traditional hardware power saving to intelligent operations. In the past, operators mainly reduced costs through more efficient power supplies, air conditioning, radio frequency equipment, and site renovations; now, with the increase in 5G network site density, frequency band count, and business complexity, relying solely on equipment energy efficiency can no longer cover all operational pressures. With AI entering wireless networks, energy-saving strategies can be dynamically adjusted around real traffic curves, enabling the network to form a more granular response mechanism between high daytime loads, low nighttime loads, holiday traffic surges, and regional business fluctuations. For a growing mobile communication market like Uzbekistan, full-network energy saving is not only related to operational costs but also to the long-term sustainability of communication infrastructure expansion.
For ZTE, the Ucell project further validates its system delivery capability in intelligent wireless network operations. The solution adopts a dual-layer intelligent architecture, combining network-level prediction and orchestration with base station-side execution, and continuously monitors key performance indicators before, during, and after energy saving. If network quality falls below set thresholds, the system automatically exits energy-saving mode, prioritizing user experience and network reliability. This moves the AI energy-saving solution beyond single-site or local pilots into full-network commercial operation scenarios. As operators increasingly focus on carbon emissions, energy costs, and network automation operations, RAN-side intelligent energy saving may become a standard capability in future mobile network upgrades.
The cooperation between Ucell and ZTE also shows that the Central Asian telecom market is shifting from basic coverage expansion to network efficiency improvement. The next phase of competition for mobile operators will simultaneously focus on coverage quality, user experience, energy costs, and automated operations capabilities. In the short term, AI energy-saving solutions can help operators reduce power consumption and operational expenses; in the long term, they may combine with intelligent planning, fault prediction, capacity scheduling, and green site construction to form a more complete intelligent wireless network operations system.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
